Token | as |
Token ID | 355 |
Feature activation | -1.29e-04 |
Pos logit contributions | |
agreement | +0.039 |
date | +0.038 |
Everyday | +0.038 |
particular | +0.037 |
invite | +0.037 |
Neg logit contributions | |
w | -0.017 |
ls | -0.013 |
many | -0.012 |
ged | -0.012 |
s | -0.012 |
Token | fast |
Token ID | 3049 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
w | +0.000 |
ich | +0.000 |
ller | +0.000 |
aged | +0.000 |
llers | +0.000 |
Neg logit contributions | |
agreement | -0.000 |
particular | -0.000 |
date | -0.000 |
Everyday | -0.000 |
invite | -0.000 |
Token | as |
Token ID | 355 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
agreement | +0.018 |
particular | +0.017 |
date | +0.016 |
Everyday | +0.016 |
invite | +0.015 |
Neg logit contributions | |
w | -0.016 |
aged | -0.014 |
ller | -0.014 |
ich | -0.014 |
ged | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
agreement | +0.009 |
date | +0.008 |
Everyday | +0.008 |
particular | +0.007 |
invite | +0.007 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
ller | -0.003 |
nam | -0.003 |
aged | -0.003 |
Token | could |
Token ID | 714 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
agreement | +0.046 |
date | +0.040 |
particular | +0.038 |
Everyday | +0.037 |
basis | +0.036 |
Neg logit contributions | |
w | -0.032 |
aged | -0.028 |
Blood | -0.028 |
ich | -0.027 |
ged | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
agreement | +0.098 |
date | +0.094 |
Everyday | +0.094 |
checkout | +0.093 |
eater | +0.086 |
Neg logit contributions | |
uts | -0.052 |
w | -0.048 |
Blood | -0.047 |
touching | -0.047 |
EEP | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
umm | +0.124 |
date | +0.122 |
Everyday | +0.118 |
eater | +0.111 |
Whenever | +0.110 |
Neg logit contributions | |
touching | -0.063 |
screaming | -0.059 |
crossing | -0.058 |
hitting | -0.057 |
pressing | -0.057 |
Token | other |
Token ID | 584 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Everyday | +0.079 |
rily | +0.076 |
particular | +0.075 |
rene | +0.075 |
Whenever | +0.074 |
Neg logit contributions | |
ich | -0.044 |
w | -0.039 |
screaming | -0.038 |
RR | -0.037 |
shouting | -0.037 |
Token | side |
Token ID | 1735 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
rily | +0.039 |
surely | +0.037 |
rene | +0.035 |
Everyday | +0.035 |
date | +0.034 |
Neg logit contributions | |
pressing | -0.029 |
fighting | -0.028 |
reading | -0.028 |
ich | -0.028 |
EEP | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
agreement | +0.049 |
invite | +0.040 |
offer | +0.040 |
Everyday | +0.040 |
date | +0.040 |
Neg logit contributions | |
w | -0.033 |
uts | -0.032 |
pressing | -0.031 |
ich | -0.030 |
crying | -0.030 |
Token | He |
Token ID | 679 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.004 |
date | +0.004 |
invite | +0.004 |
offer | +0.004 |
Neg logit contributions | |
w | -0.003 |
ller | -0.003 |
aged | -0.003 |
llers | -0.003 |
ich | -0.003 |
Token | late |
Token ID | 2739 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
latable | +0.051 |
agreement | +0.050 |
date | +0.049 |
particular | +0.047 |
Everyday | +0.045 |
Neg logit contributions | |
reading | -0.029 |
crying | -0.028 |
breathing | -0.028 |
screaming | -0.027 |
w | -0.027 |
Token | with |
Token ID | 351 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
agreement | +0.021 |
particular | +0.019 |
date | +0.019 |
Everyday | +0.019 |
invite | +0.018 |
Neg logit contributions | |
w | -0.019 |
ller | -0.017 |
ich | -0.017 |
aged | -0.017 |
llers | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
agreement | +0.037 |
date | +0.036 |
particular | +0.033 |
invite | +0.033 |
Everyday | +0.032 |
Neg logit contributions | |
w | -0.016 |
bleeding | -0.015 |
crying | -0.015 |
flashing | -0.015 |
nam | -0.015 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
agreement | +0.019 |
Everyday | +0.017 |
date | +0.017 |
particular | +0.017 |
Whenever | +0.016 |
Neg logit contributions | |
w | -0.016 |
ich | -0.016 |
elbows | -0.014 |
ller | -0.014 |
aged | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
agreement | +0.032 |
particular | +0.029 |
Everyday | +0.027 |
surely | +0.026 |
offer | +0.026 |
Neg logit contributions | |
w | -0.013 |
reading | -0.013 |
ich | -0.013 |
crying | -0.012 |
Pur | -0.012 |
Token | M |
Token ID | 337 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
agreement | +0.029 |
particular | +0.027 |
date | +0.026 |
Everyday | +0.025 |
offer | +0.025 |
Neg logit contributions | |
ich | -0.017 |
nam | -0.015 |
w | -0.015 |
Pur | -0.015 |
crying | -0.015 |
Token | andy |
Token ID | 10757 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
agreement | +0.118 |
surely | +0.105 |
date | +0.101 |
fill | +0.100 |
tow | +0.099 |
Neg logit contributions | |
ich | -0.089 |
w | -0.082 |
ller | -0.076 |
uts | -0.075 |
llers | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
agreement | +0.043 |
particular | +0.040 |
date | +0.038 |
Everyday | +0.038 |
offer | +0.036 |
Neg logit contributions | |
w | -0.029 |
ich | -0.029 |
ller | -0.028 |
aged | -0.027 |
llers | -0.026 |
Token | |
Token ID | 220 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
agreement | +0.022 |
date | +0.020 |
particular | +0.020 |
invite | +0.019 |
offer | +0.019 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.010 |
llers | -0.010 |
aged | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
w | +0.011 |
ich | +0.009 |
ller | +0.009 |
aged | +0.009 |
llers | +0.009 |
Neg logit contributions | |
agreement | -0.014 |
particular | -0.013 |
Everyday | -0.013 |
date | -0.013 |
invite | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
agreement | +0.030 |
particular | +0.028 |
date | +0.027 |
Everyday | +0.027 |
invite | +0.027 |
Neg logit contributions | |
w | -0.017 |
ich | -0.014 |
ller | -0.013 |
aged | -0.013 |
irens | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
w | +0.006 |
ich | +0.005 |
ller | +0.005 |
aged | +0.005 |
llers | +0.005 |
Neg logit contributions | |
agreement | -0.008 |
particular | -0.008 |
Everyday | -0.008 |
date | -0.007 |
invite | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
agreement | +0.032 |
particular | +0.030 |
Everyday | +0.029 |
date | +0.028 |
invite | +0.028 |
Neg logit contributions | |
w | -0.023 |
ich | -0.020 |
ller | -0.020 |
aged | -0.019 |
llers | -0.019 |
Token | But |
Token ID | 1537 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
agreement | +0.043 |
particular | +0.039 |
Everyday | +0.038 |
date | +0.038 |
invite | +0.038 |
Neg logit contributions | |
w | -0.031 |
ich | -0.027 |
aged | -0.026 |
irens | -0.026 |
llers | -0.025 |
Token | then |
Token ID | 788 |
Feature activation | +9.72e-03 |
Pos logit contributions | |
agreement | +0.056 |
date | +0.049 |
Everyday | +0.048 |
particular | +0.048 |
offer | +0.048 |
Neg logit contributions | |
w | -0.046 |
aged | -0.042 |
ich | -0.041 |
ller | -0.038 |
llers | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
agreement | +0.018 |
particular | +0.016 |
Everyday | +0.016 |
date | +0.016 |
invite | +0.015 |
Neg logit contributions | |
w | -0.013 |
ich | -0.011 |
aged | -0.011 |
ller | -0.011 |
llers | -0.011 |
Token | M |
Token ID | 337 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
agreement | +0.047 |
particular | +0.042 |
Everyday | +0.042 |
date | +0.041 |
invite | +0.040 |
Neg logit contributions | |
w | -0.024 |
ich | -0.020 |
aged | -0.020 |
ller | -0.019 |
irens | -0.018 |
Token | andy |
Token ID | 10757 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
agreement | +0.107 |
date | +0.094 |
particular | +0.088 |
surely | +0.087 |
invite | +0.086 |
Neg logit contributions | |
w | -0.098 |
ich | -0.096 |
ouncing | -0.086 |
inches | -0.086 |
ller | -0.085 |
Token | found |
Token ID | 1043 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
agreement | +0.043 |
particular | +0.039 |
date | +0.037 |
Everyday | +0.037 |
offer | +0.035 |
Neg logit contributions | |
w | -0.027 |
ich | -0.024 |
aged | -0.023 |
ller | -0.023 |
llers | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +4.45e-04 |
Pos logit contributions | |
agreement | +0.010 |
particular | +0.010 |
invite | +0.009 |
date | +0.009 |
Everyday | +0.009 |
Neg logit contributions | |
w | -0.004 |
aged | -0.004 |
ich | -0.004 |
nam | -0.003 |
irens | -0.003 |
Token | four |
Token ID | 1440 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
agreement | +0.001 |
Everyday | +0.001 |
date | +0.001 |
particular | +0.001 |
invite | +0.001 |
Neg logit contributions | |
w | -0.001 |
ich | -0.001 |
ller | -0.001 |
nam | -0.001 |
bleeding | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | -2.21e-04 |
Pos logit contributions | |
agreement | +0.015 |
date | +0.014 |
Everyday | +0.013 |
surely | +0.013 |
particular | +0.013 |
Neg logit contributions | |
w | -0.009 |
ich | -0.008 |
nam | -0.008 |
aged | -0.008 |
ller | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
w | +0.017 |
ich | +0.014 |
aged | +0.013 |
ller | +0.013 |
llers | +0.013 |
Neg logit contributions | |
agreement | -0.019 |
particular | -0.017 |
date | -0.016 |
Everyday | -0.015 |
offer | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
w | +0.011 |
ich | +0.010 |
aged | +0.009 |
ller | +0.009 |
llers | +0.009 |
Neg logit contributions | |
agreement | -0.025 |
particular | -0.024 |
Everyday | -0.023 |
offer | -0.022 |
date | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -7.96e-03 |
Pos logit contributions | |
agreement | +0.011 |
date | +0.011 |
Everyday | +0.010 |
particular | +0.010 |
invite | +0.010 |
Neg logit contributions | |
nam | -0.006 |
reading | -0.005 |
w | -0.005 |
crying | -0.005 |
praying | -0.005 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
w | +0.012 |
ich | +0.011 |
ller | +0.010 |
irens | +0.010 |
llers | +0.010 |
Neg logit contributions | |
agreement | -0.013 |
particular | -0.011 |
Everyday | -0.011 |
offer | -0.011 |
date | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
agreement | +0.007 |
particular | +0.006 |
Everyday | +0.006 |
date | +0.006 |
invite | +0.006 |
Neg logit contributions | |
w | -0.006 |
ich | -0.006 |
aged | -0.006 |
ller | -0.006 |
llers | -0.006 |
Token | M |
Token ID | 337 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
agreement | +0.089 |
date | +0.088 |
choice | +0.080 |
offer | +0.079 |
promise | +0.079 |
Neg logit contributions | |
Blood | -0.042 |
elt | -0.033 |
AAAA | -0.029 |
Ding | -0.029 |
Boom | -0.029 |
Token | andy |
Token ID | 10757 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
agreement | +0.112 |
date | +0.099 |
surely | +0.098 |
fill | +0.096 |
invite | +0.092 |
Neg logit contributions | |
ich | -0.090 |
w | -0.089 |
azes | -0.079 |
inches | -0.078 |
ouncing | -0.078 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.59e-03 |
Pos logit contributions | |
agreement | +0.006 |
particular | +0.005 |
date | +0.005 |
Everyday | +0.005 |
offer | +0.004 |
Neg logit contributions | |
w | -0.005 |
ller | -0.004 |
ich | -0.004 |
aged | -0.004 |
llers | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
Everyday | +0.003 |
date | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
aged | -0.002 |
llers | -0.002 |
Token | help |
Token ID | 1037 |
Feature activation | -5.12e-05 |
Pos logit contributions | |
agreement | +0.030 |
rily | +0.028 |
lated | +0.027 |
mer | +0.026 |
rant | +0.026 |
Neg logit contributions | |
Blood | -0.020 |
touching | -0.019 |
reading | -0.018 |
w | -0.018 |
crying | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
w | +0.000 |
aged | +0.000 |
ller | +0.000 |
ich | +0.000 |
irens | +0.000 |
Neg logit contributions | |
agreement | -0.000 |
Everyday | -0.000 |
particular | -0.000 |
date | -0.000 |
surely | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
agreement | +0.045 |
date | +0.040 |
particular | +0.038 |
Everyday | +0.037 |
offer | +0.036 |
Neg logit contributions | |
w | -0.039 |
ich | -0.033 |
aged | -0.033 |
AAAA | -0.032 |
ller | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
agreement | +0.052 |
date | +0.047 |
offer | +0.045 |
particular | +0.045 |
Everyday | +0.045 |
Neg logit contributions | |
w | -0.025 |
ich | -0.022 |
flashing | -0.022 |
Blood | -0.021 |
aged | -0.021 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
agreement | +0.054 |
Everyday | +0.050 |
particular | +0.047 |
date | +0.046 |
Whenever | +0.045 |
Neg logit contributions | |
w | -0.042 |
ich | -0.042 |
ller | -0.037 |
AAAA | -0.035 |
RR | -0.035 |
Token | march |
Token ID | 9960 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
agreement | +0.030 |
Everyday | +0.029 |
date | +0.027 |
particular | +0.027 |
Whenever | +0.025 |
Neg logit contributions | |
ich | -0.032 |
w | -0.031 |
ller | -0.029 |
AAAA | -0.028 |
EEP | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
agreement | +0.066 |
particular | +0.057 |
Everyday | +0.057 |
rily | +0.053 |
offer | +0.053 |
Neg logit contributions | |
w | -0.040 |
EEP | -0.035 |
ich | -0.035 |
ller | -0.033 |
Pur | -0.033 |
Token | full |
Token ID | 1336 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
agreement | +0.015 |
date | +0.013 |
particular | +0.013 |
Everyday | +0.013 |
offer | +0.012 |
Neg logit contributions | |
w | -0.010 |
ich | -0.010 |
ller | -0.009 |
llers | -0.009 |
aged | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
agreement | +0.083 |
rene | +0.083 |
date | +0.082 |
surely | +0.079 |
particular | +0.078 |
Neg logit contributions | |
irens | -0.089 |
flashing | -0.089 |
EEP | -0.089 |
uts | -0.085 |
Pur | -0.084 |
Token | shouts |
Token ID | 34757 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
agreement | +0.062 |
date | +0.062 |
particular | +0.061 |
Everyday | +0.058 |
surely | +0.058 |
Neg logit contributions | |
w | -0.034 |
irens | -0.032 |
aged | -0.031 |
flashing | -0.030 |
nam | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
agreement | +0.038 |
particular | +0.035 |
Everyday | +0.034 |
date | +0.033 |
invite | +0.032 |
Neg logit contributions | |
w | -0.034 |
ich | -0.031 |
ller | -0.030 |
aged | -0.029 |
llers | -0.029 |
Token | laughter |
Token ID | 20263 |
Feature activation | -2.84e-03 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
date | +0.002 |
Everyday | +0.002 |
invite | +0.002 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
llers | -0.002 |
aged | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
w | +0.004 |
ich | +0.004 |
ller | +0.004 |
aged | +0.003 |
llers | +0.003 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.005 |
Everyday | -0.004 |
date | -0.004 |
offer | -0.004 |
Token | dad |
Token ID | 9955 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
w | +0.019 |
RR | +0.017 |
ller | +0.016 |
irens | +0.016 |
ich | +0.016 |
Neg logit contributions | |
agreement | -0.016 |
invite | -0.015 |
particular | -0.014 |
Everyday | -0.014 |
offer | -0.014 |
Token | about |
Token ID | 546 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
date | +0.003 |
Everyday | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.003 |
ich | -0.003 |
ller | -0.003 |
aged | -0.003 |
llers | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
agreement | +0.015 |
particular | +0.014 |
date | +0.014 |
Everyday | +0.013 |
invite | +0.013 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.010 |
llers | -0.010 |
aged | -0.009 |
Token | new |
Token ID | 649 |
Feature activation | -6.67e-03 |
Pos logit contributions | |
agreement | +0.023 |
Everyday | +0.021 |
date | +0.021 |
particular | +0.021 |
cloth | +0.019 |
Neg logit contributions | |
w | -0.023 |
ich | -0.022 |
reading | -0.021 |
ller | -0.020 |
aged | -0.020 |
Token | friend |
Token ID | 1545 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
w | +0.010 |
ich | +0.009 |
ller | +0.009 |
aged | +0.009 |
llers | +0.009 |
Neg logit contributions | |
agreement | -0.011 |
particular | -0.010 |
Everyday | -0.010 |
date | -0.010 |
invite | -0.009 |
Token | Vin |
Token ID | 11820 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
Everyday | +0.011 |
ainer | +0.011 |
date | +0.011 |
Neg logit contributions | |
reading | -0.006 |
ich | -0.006 |
crying | -0.006 |
Pur | -0.006 |
w | -0.005 |
Token | ny |
Token ID | 3281 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
agreement | +0.088 |
date | +0.079 |
Everyday | +0.075 |
particular | +0.073 |
fill | +0.073 |
Neg logit contributions | |
w | -0.102 |
EEP | -0.089 |
RR | -0.086 |
ouncing | -0.085 |
Pur | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
ich | +0.004 |
reading | +0.003 |
w | +0.003 |
crying | +0.003 |
aged | +0.003 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.006 |
Everyday | -0.006 |
date | -0.005 |
surely | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
agreement | +0.004 |
date | +0.004 |
particular | +0.004 |
Everyday | +0.004 |
offer | +0.003 |
Neg logit contributions | |
ich | -0.003 |
crying | -0.002 |
w | -0.002 |
bleeding | -0.002 |
ller | -0.002 |
Token | magic |
Token ID | 5536 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
agreement | +0.004 |
date | +0.003 |
particular | +0.003 |
Everyday | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.003 |
ich | -0.003 |
AAAA | -0.003 |
irens | -0.003 |
ller | -0.003 |
Token | vine |
Token ID | 17793 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
w | +0.003 |
ich | +0.003 |
ller | +0.002 |
uts | +0.002 |
aged | +0.002 |
Neg logit contributions | |
agreement | -0.005 |
date | -0.004 |
Everyday | -0.004 |
particular | -0.004 |
invite | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
agreement | +0.024 |
date | +0.023 |
invite | +0.022 |
Everyday | +0.022 |
particular | +0.022 |
Neg logit contributions | |
w | -0.014 |
bleeding | -0.011 |
touching | -0.011 |
reading | -0.011 |
ich | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
agreement | +0.025 |
particular | +0.022 |
date | +0.022 |
invite | +0.021 |
offer | +0.021 |
Neg logit contributions | |
w | -0.016 |
Blood | -0.015 |
aged | -0.015 |
ich | -0.014 |
llers | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
agreement | +0.037 |
particular | +0.034 |
date | +0.033 |
invite | +0.033 |
Everyday | +0.033 |
Neg logit contributions | |
w | -0.021 |
ich | -0.018 |
aged | -0.016 |
ller | -0.016 |
irens | -0.016 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
agreement | +0.051 |
particular | +0.045 |
offer | +0.045 |
invite | +0.045 |
date | +0.044 |
Neg logit contributions | |
w | -0.029 |
ich | -0.024 |
aged | -0.023 |
Blood | -0.023 |
irens | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.004 |
Everyday | +0.004 |
date | +0.004 |
invite | +0.004 |
Neg logit contributions | |
w | -0.004 |
ich | -0.004 |
ller | -0.004 |
llers | -0.004 |
aged | -0.004 |
Token | M |
Token ID | 337 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
agreement | +0.042 |
date | +0.038 |
particular | +0.037 |
Everyday | +0.037 |
invite | +0.036 |
Neg logit contributions | |
w | -0.029 |
ich | -0.024 |
aged | -0.024 |
Blood | -0.023 |
ller | -0.022 |
Token | andy |
Token ID | 10757 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
agreement | +0.110 |
date | +0.098 |
surely | +0.092 |
particular | +0.092 |
invite | +0.092 |
Neg logit contributions | |
ich | -0.092 |
w | -0.091 |
OO | -0.078 |
inches | -0.076 |
EEP | -0.076 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
agreement | +0.029 |
particular | +0.027 |
Everyday | +0.026 |
date | +0.026 |
invite | +0.025 |
Neg logit contributions | |
w | -0.022 |
ich | -0.020 |
ller | -0.019 |
aged | -0.019 |
llers | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
agreement | +0.030 |
particular | +0.028 |
date | +0.027 |
Everyday | +0.027 |
invite | +0.026 |
Neg logit contributions | |
w | -0.018 |
ich | -0.016 |
ller | -0.016 |
aged | -0.016 |
irens | -0.015 |
Token | voice |
Token ID | 3809 |
Feature activation | +9.37e-03 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.015 |
date | +0.015 |
Everyday | +0.015 |
invite | +0.014 |
Neg logit contributions | |
w | -0.013 |
ich | -0.012 |
ller | -0.012 |
RR | -0.011 |
irens | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.014 |
Everyday | +0.014 |
date | +0.014 |
invite | +0.013 |
Neg logit contributions | |
w | -0.013 |
ich | -0.011 |
ller | -0.011 |
irens | -0.011 |
aged | -0.011 |
Token | looks |
Token ID | 3073 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
agreement | +0.026 |
date | +0.022 |
particular | +0.022 |
offer | +0.020 |
Everyday | +0.020 |
Neg logit contributions | |
w | -0.021 |
ller | -0.019 |
llers | -0.018 |
ich | -0.018 |
RR | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
date | +0.061 |
agreement | +0.057 |
particular | +0.056 |
basis | +0.055 |
Everyday | +0.051 |
Neg logit contributions | |
nam | -0.039 |
w | -0.038 |
fighting | -0.036 |
crying | -0.035 |
bleeding | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
agreement | +0.059 |
particular | +0.054 |
date | +0.053 |
Everyday | +0.051 |
invite | +0.049 |
Neg logit contributions | |
w | -0.024 |
nam | -0.021 |
ich | -0.019 |
happened | -0.019 |
bleeding | -0.019 |
Token | sport |
Token ID | 6332 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
agreement | +0.045 |
Everyday | +0.043 |
particular | +0.039 |
date | +0.039 |
Whenever | +0.039 |
Neg logit contributions | |
w | -0.037 |
ich | -0.035 |
ller | -0.034 |
RR | -0.033 |
AAAA | -0.031 |
Token | I |
Token ID | 314 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
agreement | +0.040 |
Everyday | +0.034 |
rene | +0.034 |
particular | +0.033 |
ainer | +0.033 |
Neg logit contributions | |
w | -0.022 |
ich | -0.019 |
uts | -0.018 |
inches | -0.017 |
reading | -0.017 |
Token | can |
Token ID | 460 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
agreement | +0.056 |
rily | +0.049 |
ainer | +0.048 |
umm | +0.047 |
date | +0.046 |
Neg logit contributions | |
w | -0.034 |
happened | -0.026 |
inches | -0.023 |
tri | -0.023 |
screamed | -0.023 |
Token | do |
Token ID | 466 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
agreement | +0.097 |
rily | +0.085 |
cloth | +0.080 |
umm | +0.080 |
particular | +0.079 |
Neg logit contributions | |
uts | -0.089 |
w | -0.087 |
inches | -0.078 |
touching | -0.074 |
crying | -0.074 |
Token | there |
Token ID | 612 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
agreement | +0.078 |
particular | +0.070 |
Everyday | +0.069 |
date | +0.066 |
invite | +0.063 |
Neg logit contributions | |
w | -0.046 |
uts | -0.039 |
aged | -0.037 |
ller | -0.036 |
reading | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +5.15e-04 |
Pos logit contributions | |
agreement | +0.045 |
particular | +0.038 |
latable | +0.037 |
date | +0.037 |
Everyday | +0.037 |
Neg logit contributions | |
w | -0.027 |
uts | -0.023 |
ich | -0.022 |
reading | -0.022 |
ller | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
agreement | +0.001 |
particular | +0.001 |
date | +0.001 |
invite | +0.001 |
Everyday | +0.001 |
Neg logit contributions | |
w | -0.001 |
ller | -0.001 |
ich | -0.001 |
llers | -0.001 |
aged | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
w | +0.016 |
ich | +0.014 |
aged | +0.014 |
ller | +0.014 |
llers | +0.013 |
Neg logit contributions | |
agreement | -0.018 |
particular | -0.017 |
Everyday | -0.017 |
date | -0.016 |
invite | -0.015 |
Token | like |
Token ID | 588 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
agreement | +0.053 |
date | +0.052 |
Everyday | +0.046 |
particular | +0.046 |
basis | +0.045 |
Neg logit contributions | |
nam | -0.028 |
bleeding | -0.027 |
crying | -0.027 |
flashing | -0.026 |
w | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
agreement | +0.073 |
date | +0.067 |
particular | +0.065 |
Everyday | +0.065 |
offer | +0.062 |
Neg logit contributions | |
w | -0.024 |
nam | -0.024 |
flashing | -0.023 |
reading | -0.022 |
ich | -0.022 |
Token | march |
Token ID | 9960 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
agreement | +0.052 |
date | +0.051 |
rily | +0.049 |
ainer | +0.047 |
Everyday | +0.047 |
Neg logit contributions | |
w | -0.033 |
ich | -0.033 |
flashing | -0.029 |
nam | -0.029 |
Pur | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
agreement | +0.075 |
Everyday | +0.061 |
ainer | +0.060 |
particular | +0.060 |
latable | +0.059 |
Neg logit contributions | |
w | -0.045 |
uts | -0.043 |
happened | -0.041 |
flashing | -0.040 |
EEP | -0.040 |
Token | going |
Token ID | 1016 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
agreement | +0.067 |
date | +0.060 |
Everyday | +0.060 |
offer | +0.057 |
eater | +0.057 |
Neg logit contributions | |
flashing | -0.031 |
w | -0.031 |
pressing | -0.030 |
bleeding | -0.029 |
touching | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
agreement | +0.103 |
particular | +0.087 |
date | +0.087 |
Everyday | +0.087 |
offer | +0.086 |
Neg logit contributions | |
w | -0.055 |
irens | -0.049 |
ich | -0.047 |
ller | -0.047 |
llers | -0.044 |
Token | be |
Token ID | 307 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
agreement | +0.101 |
date | +0.100 |
eater | +0.095 |
rily | +0.093 |
Everyday | +0.091 |
Neg logit contributions | |
w | -0.070 |
pressing | -0.067 |
crossing | -0.066 |
AAAA | -0.066 |
Pur | -0.066 |
Token | delayed |
Token ID | 11038 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
agreement | +0.027 |
Everyday | +0.025 |
particular | +0.024 |
offer | +0.023 |
date | +0.023 |
Neg logit contributions | |
w | -0.017 |
ich | -0.016 |
aged | -0.015 |
irens | -0.015 |
llers | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
agreement | +0.027 |
Everyday | +0.025 |
date | +0.024 |
particular | +0.024 |
invite | +0.024 |
Neg logit contributions | |
w | -0.014 |
nam | -0.013 |
reading | -0.013 |
ich | -0.013 |
aged | -0.013 |
Token | While |
Token ID | 2893 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
w | +0.005 |
ich | +0.004 |
ller | +0.004 |
aged | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.006 |
date | -0.006 |
invite | -0.005 |
Everyday | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
agreement | +0.023 |
particular | +0.021 |
Everyday | +0.021 |
date | +0.021 |
offer | +0.020 |
Neg logit contributions | |
w | -0.011 |
ich | -0.009 |
aged | -0.008 |
ller | -0.008 |
irens | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
w | +0.000 |
ich | +0.000 |
ller | +0.000 |
aged | +0.000 |
llers | +0.000 |
Neg logit contributions | |
agreement | -0.000 |
particular | -0.000 |
Everyday | -0.000 |
date | -0.000 |
invite | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
agreement | +0.035 |
particular | +0.033 |
date | +0.033 |
Everyday | +0.032 |
offer | +0.031 |
Neg logit contributions | |
w | -0.014 |
ich | -0.014 |
irens | -0.014 |
llers | -0.014 |
ller | -0.014 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
agreement | +0.010 |
particular | +0.009 |
surely | +0.009 |
offer | +0.009 |
date | +0.009 |
Neg logit contributions | |
w | -0.007 |
ich | -0.007 |
irens | -0.006 |
bleeding | -0.006 |
AAAA | -0.006 |
Token | ," |
Token ID | 553 |
Feature activation | -9.77e-06 |
Pos logit contributions | |
w | +0.024 |
ich | +0.020 |
ller | +0.020 |
llers | +0.019 |
aged | +0.019 |
Neg logit contributions | |
agreement | -0.043 |
particular | -0.039 |
Everyday | -0.037 |
date | -0.037 |
invite | -0.036 |
Token | said |
Token ID | 531 |
Feature activation | +1.38e-02 |
Token | M |
Token ID | 337 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
agreement | +0.021 |
Everyday | +0.018 |
particular | +0.018 |
date | +0.018 |
invite | +0.017 |
Neg logit contributions | |
w | -0.021 |
aged | -0.020 |
Blood | -0.018 |
ich | -0.018 |
ller | -0.018 |
Token | andy |
Token ID | 10757 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
agreement | +0.104 |
date | +0.095 |
surely | +0.092 |
fill | +0.089 |
invite | +0.088 |
Neg logit contributions | |
w | -0.091 |
ich | -0.087 |
inches | -0.080 |
OO | -0.078 |
uts | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
agreement | +0.015 |
particular | +0.014 |
date | +0.013 |
Everyday | +0.013 |
invite | +0.012 |
Neg logit contributions | |
w | -0.015 |
aged | -0.015 |
ller | -0.014 |
ich | -0.014 |
llers | -0.013 |
Token | |
Token ID | 220 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.014 |
Everyday | +0.014 |
date | +0.014 |
invite | +0.013 |
Neg logit contributions | |
w | -0.012 |
ich | -0.011 |
ller | -0.011 |
aged | -0.010 |
llers | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
w | +0.035 |
ich | +0.032 |
ller | +0.030 |
llers | +0.030 |
RR | +0.029 |
Neg logit contributions | |
agreement | -0.034 |
particular | -0.034 |
Everyday | -0.033 |
date | -0.030 |
invite | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
agreement | +0.010 |
particular | +0.010 |
Everyday | +0.009 |
date | +0.009 |
invite | +0.009 |
Neg logit contributions | |
w | -0.008 |
ich | -0.007 |
ller | -0.007 |
llers | -0.007 |
aged | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
agreement | +0.031 |
date | +0.028 |
particular | +0.028 |
Everyday | +0.028 |
latable | +0.027 |
Neg logit contributions | |
w | -0.023 |
ich | -0.021 |
aged | -0.021 |
ller | -0.021 |
llers | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
date | +0.069 |
agreement | +0.068 |
rant | +0.067 |
Everyday | +0.065 |
igator | +0.064 |
Neg logit contributions | |
ich | -0.036 |
reading | -0.032 |
crying | -0.031 |
ller | -0.031 |
nam | -0.030 |
Token | for |
Token ID | 329 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
agreement | +0.051 |
latable | +0.049 |
particular | +0.049 |
date | +0.048 |
ainer | +0.048 |
Neg logit contributions | |
reading | -0.021 |
crying | -0.019 |
praying | -0.018 |
sitting | -0.017 |
ich | -0.017 |
Token | permitting |
Token ID | 29256 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
Everyday | +0.043 |
particular | +0.043 |
agreement | +0.043 |
date | +0.040 |
invite | +0.039 |
Neg logit contributions | |
w | -0.020 |
ich | -0.018 |
aged | -0.017 |
nam | -0.017 |
reading | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
agreement | +0.022 |
particular | +0.021 |
Everyday | +0.021 |
date | +0.020 |
latable | +0.020 |
Neg logit contributions | |
w | -0.010 |
irens | -0.009 |
aged | -0.008 |
reading | -0.008 |
Pur | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
agreement | +0.094 |
particular | +0.087 |
date | +0.084 |
Everyday | +0.082 |
rily | +0.079 |
Neg logit contributions | |
w | -0.043 |
uts | -0.038 |
aged | -0.037 |
EEP | -0.037 |
ich | -0.037 |
Token | march |
Token ID | 9960 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
rily | +0.089 |
eater | +0.086 |
agreement | +0.083 |
igator | +0.081 |
particular | +0.079 |
Neg logit contributions | |
w | -0.084 |
riding | -0.080 |
Pur | -0.079 |
crossing | -0.077 |
EEP | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-04 |
Pos logit contributions | |
agreement | +0.070 |
Everyday | +0.066 |
particular | +0.065 |
eater | +0.061 |
latable | +0.061 |
Neg logit contributions | |
w | -0.037 |
uts | -0.033 |
ller | -0.033 |
irens | -0.033 |
aged | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
agreement | +0.001 |
particular | +0.001 |
date | +0.001 |
invite | +0.001 |
offer | +0.001 |
Neg logit contributions | |
w | -0.001 |
ich | -0.000 |
ller | -0.000 |
llers | -0.000 |
aged | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
w | +0.003 |
ich | +0.002 |
ller | +0.002 |
aged | +0.002 |
llers | +0.002 |
Neg logit contributions | |
agreement | -0.004 |
particular | -0.003 |
date | -0.003 |
Everyday | -0.003 |
invite | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
agreement | +0.008 |
particular | +0.007 |
fill | +0.007 |
offer | +0.007 |
Everyday | +0.007 |
Neg logit contributions | |
w | -0.005 |
ich | -0.005 |
aged | -0.004 |
irens | -0.004 |
AAAA | -0.004 |
Token | look |
Token ID | 804 |
Feature activation | +8.78e-03 |
Pos logit contributions | |
rily | +0.078 |
rant | +0.075 |
umm | +0.074 |
year | +0.070 |
cloth | +0.069 |
Neg logit contributions | |
riding | -0.047 |
fighting | -0.047 |
hitting | -0.047 |
pushing | -0.046 |
touching | -0.045 |
Token | for |
Token ID | 329 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
agreement | +0.016 |
date | +0.016 |
particular | +0.016 |
Everyday | +0.015 |
invite | +0.015 |
Neg logit contributions | |
w | -0.010 |
nam | -0.009 |
ller | -0.008 |
aged | -0.008 |
inches | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
particular | +0.056 |
agreement | +0.056 |
date | +0.055 |
surely | +0.053 |
Everyday | +0.053 |
Neg logit contributions | |
nam | -0.030 |
w | -0.027 |
llers | -0.027 |
irens | -0.026 |
ller | -0.025 |
Token | sport |
Token ID | 6332 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
agreement | +0.039 |
Everyday | +0.036 |
particular | +0.034 |
date | +0.033 |
cloth | +0.032 |
Neg logit contributions | |
w | -0.029 |
ich | -0.028 |
ller | -0.026 |
EEP | -0.026 |
AAAA | -0.026 |
Token | he |
Token ID | 339 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
agreement | +0.050 |
Everyday | +0.045 |
particular | +0.044 |
rene | +0.044 |
ainer | +0.044 |
Neg logit contributions | |
w | -0.020 |
uts | -0.019 |
ich | -0.019 |
inches | -0.018 |
reading | -0.017 |
Token | could |
Token ID | 714 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
agreement | +0.051 |
ainer | +0.046 |
date | +0.042 |
rily | +0.041 |
particular | +0.041 |
Neg logit contributions | |
w | -0.028 |
tri | -0.023 |
happened | -0.022 |
screamed | -0.022 |
ounced | -0.021 |
Token | do |
Token ID | 466 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
umm | +0.098 |
agreement | +0.098 |
isher | +0.097 |
rily | +0.097 |
rant | +0.092 |
Neg logit contributions | |
uts | -0.071 |
touching | -0.064 |
w | -0.062 |
riding | -0.061 |
swinging | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -7.26e-03 |
Pos logit contributions | |
agreement | +0.074 |
Everyday | +0.067 |
particular | +0.066 |
date | +0.061 |
invite | +0.061 |
Neg logit contributions | |
w | -0.048 |
aged | -0.042 |
uts | -0.041 |
reading | -0.038 |
ich | -0.037 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
w | +0.013 |
ich | +0.012 |
ller | +0.011 |
aged | +0.011 |
llers | +0.011 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.009 |
Everyday | -0.009 |
date | -0.008 |
invite | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
w | +0.021 |
ich | +0.020 |
ller | +0.018 |
llers | +0.018 |
aged | +0.018 |
Neg logit contributions | |
agreement | -0.024 |
particular | -0.023 |
Everyday | -0.021 |
date | -0.021 |
invite | -0.021 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
agreement | +0.043 |
particular | +0.039 |
Everyday | +0.038 |
date | +0.038 |
offer | +0.037 |
Neg logit contributions | |
w | -0.023 |
ich | -0.019 |
ounced | -0.018 |
aged | -0.018 |
inches | -0.018 |
Token | shows |
Token ID | 2523 |
Feature activation | +5.91e-03 |
Pos logit contributions | |
agreement | +0.017 |
date | +0.017 |
particular | +0.016 |
basis | +0.015 |
Everyday | +0.015 |
Neg logit contributions | |
w | -0.005 |
inches | -0.005 |
okes | -0.004 |
ller | -0.004 |
ls | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
agreement | +0.009 |
particular | +0.008 |
date | +0.008 |
Everyday | +0.008 |
invite | +0.007 |
Neg logit contributions | |
w | -0.009 |
aged | -0.008 |
irens | -0.008 |
ller | -0.008 |
llers | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
agreement | +0.032 |
date | +0.029 |
particular | +0.029 |
Everyday | +0.027 |
invite | +0.026 |
Neg logit contributions | |
w | -0.017 |
aged | -0.015 |
llers | -0.014 |
inches | -0.014 |
uts | -0.014 |
Token | big |
Token ID | 1263 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
agreement | +0.021 |
Everyday | +0.019 |
date | +0.019 |
particular | +0.018 |
invite | +0.017 |
Neg logit contributions | |
w | -0.019 |
ich | -0.017 |
ller | -0.017 |
AAAA | -0.016 |
bleeding | -0.016 |
Token | tub |
Token ID | 12202 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
agreement | +0.037 |
particular | +0.035 |
date | +0.034 |
Everyday | +0.034 |
invite | +0.032 |
Neg logit contributions | |
w | -0.040 |
ller | -0.035 |
AAAA | -0.034 |
bleeding | -0.033 |
ich | -0.033 |
Token | full |
Token ID | 1336 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
agreement | +0.042 |
rene | +0.036 |
Everyday | +0.036 |
particular | +0.035 |
basis | +0.034 |
Neg logit contributions | |
w | -0.020 |
uts | -0.019 |
o | -0.017 |
aged | -0.016 |
ages | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
rene | +0.103 |
agreement | +0.096 |
date | +0.095 |
surely | +0.092 |
zzy | +0.090 |
Neg logit contributions | |
w | -0.071 |
uts | -0.067 |
bleeding | -0.067 |
s | -0.065 |
EEP | -0.065 |
Token | water |
Token ID | 1660 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
date | +0.045 |
agreement | +0.044 |
surely | +0.042 |
particular | +0.042 |
Everyday | +0.039 |
Neg logit contributions | |
w | -0.034 |
elbows | -0.026 |
nam | -0.026 |
bleeding | -0.026 |
blood | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +7.20e-03 |
Pos logit contributions | |
agreement | +0.036 |
particular | +0.033 |
date | +0.031 |
Everyday | +0.030 |
rene | +0.030 |
Neg logit contributions | |
w | -0.018 |
uts | -0.016 |
inches | -0.015 |
ages | -0.014 |
aged | -0.014 |
Token | foam |
Token ID | 19828 |
Feature activation | +9.23e-03 |
Pos logit contributions | |
agreement | +0.013 |
date | +0.013 |
particular | +0.012 |
Everyday | +0.011 |
basis | +0.011 |
Neg logit contributions | |
w | -0.009 |
aged | -0.008 |
nam | -0.008 |
elbows | -0.008 |
llers | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.16e-04 |
Pos logit contributions | |
agreement | +0.018 |
particular | +0.017 |
Everyday | +0.016 |
date | +0.016 |
surely | +0.015 |
Neg logit contributions | |
w | -0.012 |
uts | -0.011 |
aged | -0.011 |
inches | -0.010 |
ages | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
w | +0.005 |
ich | +0.004 |
aged | +0.004 |
ller | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.007 |
particular | -0.007 |
date | -0.006 |
Everyday | -0.006 |
invite | -0.006 |
Token | discuss |
Token ID | 2112 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
date | +0.033 |
agreement | +0.030 |
tted | +0.029 |
rily | +0.029 |
kin | +0.029 |
Neg logit contributions | |
nam | -0.023 |
touching | -0.021 |
reading | -0.020 |
examining | -0.019 |
fighting | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +6.14e-04 |
Pos logit contributions | |
agreement | +0.015 |
date | +0.015 |
particular | +0.014 |
invite | +0.014 |
surely | +0.014 |
Neg logit contributions | |
w | -0.008 |
nam | -0.008 |
ller | -0.007 |
llers | -0.007 |
ich | -0.007 |
Token | berries |
Token ID | 36322 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
agreement | +0.001 |
date | +0.001 |
surely | +0.001 |
particular | +0.001 |
invite | +0.001 |
Neg logit contributions | |
w | -0.001 |
ich | -0.001 |
aged | -0.001 |
llers | -0.001 |
Blood | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
agreement | +0.040 |
date | +0.037 |
particular | +0.036 |
Everyday | +0.034 |
invite | +0.033 |
Neg logit contributions | |
uts | -0.022 |
w | -0.019 |
ls | -0.017 |
es | -0.017 |
crying | -0.017 |
Token | M |
Token ID | 337 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
nam | +0.007 |
reading | +0.007 |
llers | +0.006 |
touching | +0.006 |
crying | +0.006 |
Neg logit contributions | |
date | -0.012 |
agreement | -0.011 |
particular | -0.011 |
surely | -0.010 |
date | -0.010 |
Token | illy |
Token ID | 6548 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
agreement | +0.106 |
particular | +0.092 |
surely | +0.092 |
date | +0.092 |
tow | +0.091 |
Neg logit contributions | |
w | -0.087 |
ich | -0.086 |
llers | -0.077 |
inches | -0.075 |
uts | -0.075 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
agreement | +0.006 |
particular | +0.006 |
date | +0.006 |
surely | +0.005 |
Everyday | +0.005 |
Neg logit contributions | |
aged | -0.004 |
w | -0.004 |
ich | -0.003 |
ller | -0.003 |
uts | -0.003 |
Token | they |
Token ID | 484 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
agreement | +0.072 |
date | +0.070 |
ainer | +0.061 |
surely | +0.060 |
host | +0.060 |
Neg logit contributions | |
w | -0.021 |
happened | -0.021 |
ls | -0.019 |
ons | -0.018 |
uts | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
agreement | +0.021 |
date | +0.018 |
particular | +0.018 |
ainer | +0.017 |
basis | +0.017 |
Neg logit contributions | |
w | -0.011 |
nam | -0.009 |
aged | -0.009 |
uts | -0.008 |
llers | -0.008 |
Token | delicious |
Token ID | 12625 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
agreement | +0.009 |
date | +0.009 |
particular | +0.009 |
Everyday | +0.008 |
surely | +0.008 |
Neg logit contributions | |
nam | -0.006 |
reading | -0.005 |
ich | -0.005 |
w | -0.005 |
praying | -0.005 |
Token | like |
Token ID | 588 |
Feature activation | +3.69e-04 |
Pos logit contributions | |
w | +0.006 |
aged | +0.005 |
EEP | +0.005 |
uts | +0.005 |
ich | +0.005 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.005 |
Everyday | -0.005 |
date | -0.005 |
latable | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
agreement | +0.001 |
date | +0.001 |
particular | +0.001 |
Everyday | +0.001 |
offer | +0.001 |
Neg logit contributions | |
w | -0.000 |
llers | -0.000 |
irens | -0.000 |
ller | -0.000 |
ich | -0.000 |
Token | sunscreen |
Token ID | 44221 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
date | +0.040 |
agreement | +0.037 |
surely | +0.037 |
Everyday | +0.037 |
iona | +0.035 |
Neg logit contributions | |
w | -0.025 |
flashing | -0.024 |
blood | -0.024 |
elbows | -0.023 |
crying | -0.023 |
Token | because |
Token ID | 780 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
agreement | +0.037 |
particular | +0.031 |
date | +0.030 |
Everyday | +0.030 |
iona | +0.029 |
Neg logit contributions | |
w | -0.020 |
uts | -0.019 |
bleeding | -0.018 |
ich | -0.018 |
aged | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
agreement | +0.045 |
date | +0.040 |
invite | +0.039 |
offer | +0.038 |
basis | +0.037 |
Neg logit contributions | |
w | -0.016 |
irens | -0.012 |
ller | -0.011 |
uts | -0.011 |
nam | -0.011 |
Token | felt |
Token ID | 2936 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
agreement | +0.034 |
date | +0.027 |
particular | +0.026 |
Everyday | +0.026 |
offer | +0.025 |
Neg logit contributions | |
w | -0.024 |
llers | -0.020 |
aged | -0.020 |
ller | -0.020 |
ich | -0.019 |
Token | tight |
Token ID | 5381 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
date | +0.136 |
agreement | +0.129 |
particular | +0.116 |
basis | +0.114 |
iona | +0.112 |
Neg logit contributions | |
bleeding | -0.057 |
hurting | -0.048 |
crying | -0.047 |
breathing | -0.045 |
w | -0.045 |
Token | on |
Token ID | 319 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
agreement | +0.033 |
particular | +0.032 |
date | +0.029 |
Everyday | +0.029 |
invite | +0.028 |
Neg logit contributions | |
w | -0.022 |
aged | -0.021 |
ich | -0.019 |
uts | -0.019 |
bleeding | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
agreement | +0.024 |
date | +0.023 |
particular | +0.022 |
Everyday | +0.022 |
invite | +0.022 |
Neg logit contributions | |
w | -0.015 |
aged | -0.013 |
ller | -0.012 |
ich | -0.012 |
llers | -0.012 |
Token | skin |
Token ID | 4168 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
agreement | +0.026 |
Everyday | +0.025 |
particular | +0.025 |
date | +0.024 |
invite | +0.023 |
Neg logit contributions | |
w | -0.019 |
ich | -0.018 |
aged | -0.018 |
elbows | -0.018 |
ller | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-03 |
Pos logit contributions | |
agreement | +0.034 |
particular | +0.030 |
date | +0.030 |
invite | +0.028 |
Everyday | +0.028 |
Neg logit contributions | |
w | -0.021 |
uts | -0.020 |
aged | -0.019 |
ller | -0.019 |
bleeding | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
agreement | +0.043 |
particular | +0.040 |
date | +0.039 |
Everyday | +0.039 |
invite | +0.037 |
Neg logit contributions | |
w | -0.025 |
ller | -0.023 |
ich | -0.022 |
aged | -0.022 |
llers | -0.021 |
Token | permit |
Token ID | 8749 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
rily | +0.078 |
umm | +0.078 |
eater | +0.076 |
ited | +0.072 |
rant | +0.070 |
Neg logit contributions | |
Hel | -0.048 |
w | -0.048 |
riding | -0.046 |
pressing | -0.046 |
EEP | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.004 |
date | +0.004 |
Everyday | +0.004 |
invite | +0.003 |
Neg logit contributions | |
w | -0.002 |
ller | -0.002 |
llers | -0.002 |
irens | -0.002 |
nam | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
agreement | +0.031 |
rant | +0.029 |
rily | +0.029 |
cloth | +0.028 |
date | +0.028 |
Neg logit contributions | |
ich | -0.016 |
w | -0.014 |
EEP | -0.013 |
happened | -0.013 |
crying | -0.013 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
agreement | +0.007 |
Everyday | +0.006 |
latable | +0.006 |
particular | +0.006 |
date | +0.006 |
Neg logit contributions | |
w | -0.003 |
ich | -0.003 |
crying | -0.003 |
nam | -0.003 |
happened | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
agreement | +0.078 |
particular | +0.070 |
ainer | +0.068 |
date | +0.068 |
Everyday | +0.067 |
Neg logit contributions | |
aged | -0.016 |
reading | -0.015 |
uts | -0.015 |
w | -0.015 |
ages | -0.014 |
Token | march |
Token ID | 9960 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
rily | +0.103 |
umm | +0.099 |
eater | +0.099 |
agreement | +0.093 |
rant | +0.089 |
Neg logit contributions | |
w | -0.070 |
EEP | -0.068 |
Hel | -0.064 |
Pur | -0.063 |
riding | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
agreement | +0.042 |
Everyday | +0.039 |
particular | +0.038 |
latable | +0.037 |
ainer | +0.036 |
Neg logit contributions | |
w | -0.023 |
nam | -0.020 |
aged | -0.019 |
irens | -0.018 |
crying | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
w | +0.012 |
ich | +0.011 |
ller | +0.010 |
aged | +0.010 |
llers | +0.010 |
Neg logit contributions | |
agreement | -0.013 |
particular | -0.012 |
Everyday | -0.012 |
date | -0.011 |
invite | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
w | +0.005 |
ich | +0.005 |
ller | +0.004 |
aged | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.008 |
particular | -0.008 |
Everyday | -0.007 |
date | -0.007 |
invite | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.003 |
date | +0.003 |
Everyday | +0.003 |
offer | +0.003 |
Neg logit contributions | |
w | -0.003 |
ich | -0.003 |
ller | -0.003 |
llers | -0.003 |
RR | -0.003 |
Token | Let |
Token ID | 3914 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
agreement | +0.037 |
particular | +0.036 |
date | +0.034 |
choice | +0.033 |
offer | +0.032 |
Neg logit contributions | |
ich | -0.017 |
w | -0.016 |
EEP | -0.016 |
llers | -0.016 |
Pur | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
agreement | +0.068 |
particular | +0.064 |
Everyday | +0.060 |
date | +0.060 |
offer | +0.059 |
Neg logit contributions | |
w | -0.035 |
ich | -0.027 |
aged | -0.024 |
ller | -0.024 |
EEP | -0.024 |
Token | go |
Token ID | 467 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
agreement | +0.029 |
rily | +0.028 |
year | +0.028 |
mer | +0.027 |
particular | +0.027 |
Neg logit contributions | |
w | -0.019 |
Brown | -0.017 |
reading | -0.016 |
riding | -0.016 |
not | -0.015 |
Token | home |
Token ID | 1363 |
Feature activation | +2.33e-03 |
Pos logit contributions | |
agreement | +0.022 |
particular | +0.021 |
Everyday | +0.020 |
date | +0.019 |
unison | +0.019 |
Neg logit contributions | |
w | -0.012 |
ich | -0.010 |
shadow | -0.010 |
enn | -0.010 |
reading | -0.009 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.003 |
Everyday | +0.003 |
date | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
ller | -0.003 |
aged | -0.003 |
llers | -0.003 |
Token | Mack |
Token ID | 16640 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
agreement | +0.046 |
particular | +0.043 |
date | +0.043 |
invite | +0.040 |
Everyday | +0.040 |
Neg logit contributions | |
w | -0.033 |
ich | -0.028 |
aged | -0.028 |
inches | -0.027 |
ller | -0.027 |
Token | enzie |
Token ID | 26389 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
agreement | +0.107 |
date | +0.106 |
tow | +0.104 |
checkout | +0.097 |
fill | +0.096 |
Neg logit contributions | |
w | -0.089 |
RR | -0.063 |
awed | -0.063 |
es | -0.061 |
ouncing | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
agreement | +0.037 |
particular | +0.035 |
date | +0.034 |
Everyday | +0.031 |
offer | +0.030 |
Neg logit contributions | |
aged | -0.025 |
w | -0.024 |
ller | -0.023 |
ages | -0.022 |
ich | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
date | +0.010 |
agreement | +0.010 |
latable | +0.009 |
particular | +0.009 |
Everyday | +0.009 |
Neg logit contributions | |
w | -0.006 |
aged | -0.006 |
Pur | -0.005 |
nam | -0.005 |
crying | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.54e-04 |
Pos logit contributions | |
agreement | +0.055 |
date | +0.054 |
Everyday | +0.052 |
particular | +0.051 |
rily | +0.051 |
Neg logit contributions | |
ich | -0.022 |
w | -0.021 |
crying | -0.021 |
bleeding | -0.020 |
aged | -0.019 |
Token | my |
Token ID | 1820 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.002 |
date | +0.002 |
Everyday | +0.002 |
offer | +0.002 |
Neg logit contributions | |
w | -0.001 |
aged | -0.001 |
ich | -0.001 |
ller | -0.001 |
llers | -0.001 |
Token | like |
Token ID | 588 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
agreement | +0.037 |
checkout | +0.037 |
umm | +0.036 |
rily | +0.036 |
particular | +0.035 |
Neg logit contributions | |
w | -0.032 |
reading | -0.024 |
whist | -0.023 |
listening | -0.022 |
shadow | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
agreement | +0.046 |
date | +0.042 |
particular | +0.042 |
surely | +0.040 |
rily | +0.039 |
Neg logit contributions | |
w | -0.020 |
reading | -0.016 |
ich | -0.014 |
praying | -0.014 |
irens | -0.014 |
Token | join |
Token ID | 4654 |
Feature activation | +7.14e-04 |
Pos logit contributions | |
rily | +0.075 |
agreement | +0.069 |
cloth | +0.069 |
umm | +0.069 |
eater | +0.068 |
Neg logit contributions | |
w | -0.056 |
ich | -0.050 |
flying | -0.050 |
Pur | -0.049 |
whist | -0.049 |
Token | me |
Token ID | 502 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
agreement | +0.001 |
particular | +0.001 |
Everyday | +0.001 |
surely | +0.001 |
date | +0.001 |
Neg logit contributions | |
w | -0.001 |
ich | -0.001 |
RR | -0.001 |
reading | -0.001 |
icken | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
agreement | +0.063 |
particular | +0.058 |
Everyday | +0.055 |
Whenever | +0.053 |
cloth | +0.052 |
Neg logit contributions | |
w | -0.032 |
ich | -0.028 |
reading | -0.025 |
ller | -0.025 |
inches | -0.024 |
Token | an |
Token ID | 281 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
agreement | +0.047 |
particular | +0.042 |
date | +0.040 |
offer | +0.040 |
Everyday | +0.040 |
Neg logit contributions | |
w | -0.029 |
ich | -0.026 |
ller | -0.025 |
llers | -0.024 |
irens | -0.023 |
Token | adventure |
Token ID | 8855 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
cloth | +0.089 |
date | +0.085 |
agreement | +0.081 |
surely | +0.080 |
tted | +0.076 |
Neg logit contributions | |
ich | -0.075 |
ller | -0.075 |
w | -0.073 |
praying | -0.068 |
llers | -0.067 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
agreement | +0.071 |
particular | +0.062 |
Everyday | +0.061 |
Whenever | +0.061 |
tow | +0.060 |
Neg logit contributions | |
w | -0.023 |
ich | -0.019 |
ller | -0.017 |
reading | -0.016 |
enn | -0.014 |
Token | |
Token ID | 220 |
Feature activation | -5.32e-03 |
Pos logit contributions | |
agreement | +0.018 |
particular | +0.017 |
date | +0.016 |
Everyday | +0.015 |
invite | +0.015 |
Neg logit contributions | |
w | -0.014 |
ller | -0.012 |
ich | -0.012 |
llers | -0.012 |
aged | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +6.90e-03 |
Pos logit contributions | |
w | +0.007 |
ich | +0.006 |
ller | +0.006 |
aged | +0.006 |
llers | +0.006 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.009 |
Everyday | -0.009 |
date | -0.009 |
invite | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
Everyday | +0.012 |
date | +0.011 |
invite | +0.011 |
Neg logit contributions | |
w | -0.009 |
ich | -0.008 |
ller | -0.008 |
aged | -0.007 |
llers | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
w | +0.001 |
ich | +0.001 |
uts | +0.001 |
reading | +0.001 |
ller | +0.001 |
Neg logit contributions | |
agreement | -0.002 |
particular | -0.001 |
Everyday | -0.001 |
date | -0.001 |
offer | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
agreement | +0.037 |
date | +0.033 |
particular | +0.033 |
offer | +0.032 |
invite | +0.031 |
Neg logit contributions | |
w | -0.026 |
Blood | -0.025 |
ich | -0.024 |
aged | -0.024 |
llers | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
agreement | +0.030 |
particular | +0.028 |
date | +0.027 |
Everyday | +0.027 |
invite | +0.026 |
Neg logit contributions | |
w | -0.017 |
ich | -0.015 |
ller | -0.014 |
aged | -0.014 |
llers | -0.014 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
agreement | +0.043 |
offer | +0.039 |
Everyday | +0.038 |
particular | +0.038 |
invite | +0.037 |
Neg logit contributions | |
w | -0.026 |
ich | -0.021 |
Blood | -0.020 |
aged | -0.019 |
RR | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
Everyday | +0.003 |
date | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
ller | -0.003 |
llers | -0.003 |
aged | -0.003 |
Token | M |
Token ID | 337 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
agreement | +0.035 |
particular | +0.031 |
date | +0.031 |
Everyday | +0.030 |
offer | +0.030 |
Neg logit contributions | |
w | -0.026 |
ich | -0.022 |
aged | -0.021 |
ller | -0.021 |
Blood | -0.021 |
Token | andy |
Token ID | 10757 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
agreement | +0.098 |
date | +0.086 |
particular | +0.081 |
surely | +0.079 |
invite | +0.079 |
Neg logit contributions | |
w | -0.098 |
ich | -0.096 |
inches | -0.086 |
ouncing | -0.084 |
icken | -0.084 |
Token | noticed |
Token ID | 6810 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
agreement | +0.005 |
particular | +0.005 |
Everyday | +0.005 |
invite | +0.005 |
date | +0.005 |
Neg logit contributions | |
w | -0.005 |
ich | -0.005 |
irens | -0.005 |
ller | -0.005 |
nam | -0.005 |
Token | something |
Token ID | 1223 |
Feature activation | +9.47e-04 |
Pos logit contributions | |
agreement | +0.035 |
particular | +0.032 |
date | +0.031 |
invite | +0.031 |
Everyday | +0.031 |
Neg logit contributions | |
w | -0.019 |
ich | -0.016 |
ller | -0.016 |
aged | -0.015 |
llers | -0.015 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
agreement | +0.002 |
date | +0.002 |
Everyday | +0.002 |
particular | +0.001 |
invite | +0.001 |
Neg logit contributions | |
w | -0.001 |
ich | -0.001 |
bleeding | -0.001 |
ller | -0.001 |
aged | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
w | +0.003 |
bleeding | +0.002 |
ller | +0.002 |
happened | +0.002 |
awed | +0.002 |
Neg logit contributions | |
agreement | -0.005 |
date | -0.005 |
invite | -0.005 |
Everyday | -0.005 |
particular | -0.005 |
Token | j |
Token ID | 474 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
w | +0.011 |
ich | +0.010 |
ller | +0.010 |
aged | +0.010 |
llers | +0.009 |
Neg logit contributions | |
agreement | -0.014 |
particular | -0.013 |
Everyday | -0.012 |
date | -0.012 |
invite | -0.012 |
Token | ogging |
Token ID | 30853 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
invite | +0.011 |
Everyday | +0.011 |
date | +0.011 |
Neg logit contributions | |
w | -0.010 |
ich | -0.008 |
inches | -0.008 |
irens | -0.008 |
aged | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
agreement | +0.051 |
particular | +0.044 |
date | +0.041 |
Everyday | +0.041 |
invite | +0.041 |
Neg logit contributions | |
w | -0.043 |
aged | -0.036 |
ich | -0.036 |
ller | -0.035 |
uts | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
agreement | +0.048 |
date | +0.046 |
rily | +0.042 |
particular | +0.041 |
Everyday | +0.040 |
Neg logit contributions | |
w | -0.021 |
bleeding | -0.019 |
aged | -0.019 |
ich | -0.017 |
llers | -0.017 |
Token | way |
Token ID | 835 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
agreement | +0.032 |
Everyday | +0.031 |
rily | +0.029 |
date | +0.029 |
Whenever | +0.027 |
Neg logit contributions | |
ich | -0.023 |
w | -0.023 |
RR | -0.021 |
AAAA | -0.020 |
EEP | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
agreement | +0.038 |
date | +0.034 |
particular | +0.033 |
Everyday | +0.032 |
invite | +0.031 |
Neg logit contributions | |
w | -0.021 |
ich | -0.018 |
uts | -0.017 |
ller | -0.017 |
aged | -0.016 |
Token | exercise |
Token ID | 5517 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
date | +0.086 |
rily | +0.085 |
agreement | +0.083 |
eater | +0.080 |
umm | +0.080 |
Neg logit contributions | |
w | -0.081 |
crossing | -0.077 |
touching | -0.076 |
Pur | -0.072 |
crying | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
agreement | +0.067 |
particular | +0.059 |
date | +0.058 |
Everyday | +0.058 |
invite | +0.057 |
Neg logit contributions | |
w | -0.048 |
uts | -0.038 |
ich | -0.038 |
inches | -0.038 |
irens | -0.038 |
Token | stay |
Token ID | 2652 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
agreement | +0.006 |
particular | +0.005 |
date | +0.005 |
Everyday | +0.005 |
rily | +0.004 |
Neg logit contributions | |
w | -0.006 |
llers | -0.005 |
aged | -0.005 |
ich | -0.005 |
ller | -0.005 |
Token | healthy |
Token ID | 5448 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Everyday | +0.010 |
agreement | +0.009 |
particular | +0.009 |
date | +0.009 |
Whenever | +0.009 |
Neg logit contributions | |
w | -0.007 |
aged | -0.006 |
ich | -0.006 |
shadow | -0.006 |
bleeding | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
agreement | +0.034 |
particular | +0.034 |
Everyday | +0.031 |
date | +0.031 |
tow | +0.030 |
Neg logit contributions | |
w | -0.016 |
uts | -0.014 |
ages | -0.013 |
ich | -0.013 |
reading | -0.013 |
Token | On |
Token ID | 2202 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
agreement | +0.009 |
particular | +0.008 |
Everyday | +0.008 |
offer | +0.008 |
invite | +0.007 |
Neg logit contributions | |
w | -0.006 |
ich | -0.005 |
aged | -0.005 |
irens | -0.005 |
uts | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
agreement | +0.036 |
date | +0.034 |
offer | +0.033 |
invite | +0.033 |
tted | +0.031 |
Neg logit contributions | |
w | -0.015 |
irens | -0.011 |
ich | -0.011 |
flashing | -0.010 |
praying | -0.010 |
Token | way |
Token ID | 835 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
agreement | +0.019 |
date | +0.016 |
particular | +0.015 |
Everyday | +0.015 |
cloth | +0.015 |
Neg logit contributions | |
w | -0.022 |
ich | -0.020 |
ller | -0.020 |
llers | -0.019 |
EEP | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +5.90e-03 |
Pos logit contributions | |
w | +0.010 |
ich | +0.009 |
aged | +0.009 |
ller | +0.008 |
EEP | +0.008 |
Neg logit contributions | |
agreement | -0.013 |
particular | -0.011 |
Everyday | -0.011 |
date | -0.011 |
invite | -0.011 |
Token | A |
Token ID | 317 |
Feature activation | +7.20e-03 |
Pos logit contributions | |
agreement | +0.010 |
particular | +0.009 |
Everyday | +0.009 |
date | +0.009 |
invite | +0.009 |
Neg logit contributions | |
w | -0.009 |
ich | -0.008 |
ller | -0.007 |
llers | -0.007 |
aged | -0.007 |
Token | str |
Token ID | 2536 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
agreement | +0.012 |
Everyday | +0.010 |
particular | +0.010 |
date | +0.010 |
invite | +0.010 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.010 |
llers | -0.009 |
RR | -0.009 |
Token | id |
Token ID | 312 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
nam | +0.091 |
w | +0.084 |
elbows | +0.083 |
AAAA | +0.080 |
viol | +0.078 |
Neg logit contributions | |
Everyday | -0.089 |
ini | -0.087 |
particular | -0.086 |
definitely | -0.085 |
agreement | -0.084 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
agreement | +0.005 |
particular | +0.005 |
date | +0.005 |
Everyday | +0.005 |
invite | +0.004 |
Neg logit contributions | |
w | -0.005 |
ich | -0.004 |
aged | -0.004 |
ller | -0.004 |
llers | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
agreement | +0.033 |
particular | +0.030 |
date | +0.029 |
invite | +0.029 |
Everyday | +0.029 |
Neg logit contributions | |
w | -0.020 |
ich | -0.017 |
aged | -0.017 |
irens | -0.016 |
ller | -0.016 |
Token | pond |
Token ID | 16723 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
w | +0.017 |
ich | +0.016 |
ller | +0.015 |
llers | +0.015 |
aged | +0.015 |
Neg logit contributions | |
agreement | -0.017 |
particular | -0.015 |
Everyday | -0.015 |
date | -0.014 |
invite | -0.014 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
agreement | +0.002 |
Everyday | +0.002 |
particular | +0.002 |
date | +0.002 |
Whenever | +0.002 |
Neg logit contributions | |
w | -0.001 |
ich | -0.001 |
crying | -0.001 |
reading | -0.001 |
screaming | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.015 |
Everyday | +0.014 |
date | +0.014 |
invite | +0.014 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.010 |
aged | -0.009 |
llers | -0.009 |
Token | arrived |
Token ID | 5284 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
agreement | +0.030 |
particular | +0.027 |
date | +0.027 |
Everyday | +0.026 |
offer | +0.025 |
Neg logit contributions | |
w | -0.022 |
AAAA | -0.016 |
ich | -0.015 |
awed | -0.015 |
RR | -0.015 |
Token | home |
Token ID | 1363 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
w | +0.019 |
ich | +0.017 |
ller | +0.017 |
aged | +0.016 |
llers | +0.016 |
Neg logit contributions | |
agreement | -0.022 |
particular | -0.020 |
Everyday | -0.019 |
date | -0.019 |
invite | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
w | +0.021 |
ich | +0.020 |
aged | +0.019 |
ller | +0.019 |
llers | +0.018 |
Neg logit contributions | |
agreement | -0.033 |
particular | -0.031 |
Everyday | -0.030 |
date | -0.029 |
invite | -0.028 |
Token | A |
Token ID | 317 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.002 |
Everyday | +0.002 |
date | +0.002 |
invite | +0.002 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
aged | -0.002 |
llers | -0.002 |
Token | str |
Token ID | 2536 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
agreement | +0.021 |
Everyday | +0.019 |
particular | +0.019 |
date | +0.019 |
invite | +0.018 |
Neg logit contributions | |
w | -0.019 |
ich | -0.018 |
ller | -0.017 |
llers | -0.016 |
AAAA | -0.016 |
Token | id |
Token ID | 312 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
nam | +0.088 |
w | +0.084 |
satellites | +0.077 |
elbows | +0.077 |
AAAA | +0.076 |
Neg logit contributions | |
agreement | -0.081 |
Everyday | -0.080 |
particular | -0.078 |
expert | -0.075 |
ini | -0.074 |
Token | put |
Token ID | 1234 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
agreement | +0.011 |
particular | +0.010 |
Everyday | +0.010 |
date | +0.010 |
invite | +0.010 |
Neg logit contributions | |
w | -0.010 |
ich | -0.009 |
aged | -0.008 |
ller | -0.008 |
irens | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
Everyday | +0.003 |
invite | +0.003 |
basis | +0.003 |
Neg logit contributions | |
w | -0.002 |
aged | -0.001 |
ich | -0.001 |
awed | -0.001 |
bleeding | -0.001 |
Token | balloon |
Token ID | 21190 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
agreement | +0.023 |
date | +0.021 |
Everyday | +0.021 |
particular | +0.021 |
invite | +0.020 |
Neg logit contributions | |
w | -0.021 |
ich | -0.020 |
ller | -0.018 |
aged | -0.017 |
nam | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ich | +0.013 |
w | +0.013 |
aged | +0.012 |
bleeding | +0.011 |
ller | +0.011 |
Neg logit contributions | |
agreement | -0.022 |
Everyday | -0.021 |
particular | -0.021 |
Whenever | -0.020 |
invite | -0.019 |
Token | ! |
Token ID | 0 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
w | +0.006 |
ich | +0.006 |
ller | +0.006 |
uts | +0.005 |
llers | +0.005 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.009 |
date | -0.009 |
Everyday | -0.009 |
invite | -0.009 |
Token | Mom |
Token ID | 11254 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
agreement | +0.018 |
particular | +0.016 |
Everyday | +0.015 |
date | +0.015 |
invite | +0.015 |
Neg logit contributions | |
w | -0.017 |
ich | -0.015 |
ller | -0.015 |
aged | -0.015 |
llers | -0.015 |
Token | my |
Token ID | 1820 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
agreement | +0.019 |
particular | +0.018 |
date | +0.018 |
offer | +0.017 |
Everyday | +0.017 |
Neg logit contributions | |
w | -0.009 |
ller | -0.008 |
ich | -0.008 |
llers | -0.007 |
aged | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
agreement | +0.007 |
particular | +0.007 |
date | +0.006 |
Everyday | +0.006 |
offer | +0.006 |
Neg logit contributions | |
w | -0.005 |
ich | -0.005 |
ller | -0.004 |
aged | -0.004 |
llers | -0.004 |
Token | A |
Token ID | 317 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
w | +0.019 |
ich | +0.017 |
ller | +0.017 |
llers | +0.016 |
aged | +0.016 |
Neg logit contributions | |
agreement | -0.020 |
particular | -0.019 |
Everyday | -0.018 |
date | -0.017 |
invite | -0.017 |
Token | str |
Token ID | 2536 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
agreement | +0.020 |
particular | +0.018 |
Everyday | +0.018 |
date | +0.017 |
invite | +0.017 |
Neg logit contributions | |
w | -0.018 |
ich | -0.018 |
ller | -0.016 |
llers | -0.016 |
aged | -0.016 |
Token | id |
Token ID | 312 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
nam | +0.084 |
w | +0.080 |
AAAA | +0.077 |
satellites | +0.075 |
elbows | +0.073 |
Neg logit contributions | |
agreement | -0.079 |
date | -0.079 |
Everyday | -0.078 |
ini | -0.077 |
particular | -0.076 |
Token | said |
Token ID | 531 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
agreement | +0.029 |
particular | +0.027 |
date | +0.027 |
Everyday | +0.026 |
invite | +0.025 |
Neg logit contributions | |
w | -0.028 |
aged | -0.025 |
ich | -0.024 |
ller | -0.022 |
ged | -0.021 |
Token | good |
Token ID | 922 |
Feature activation | +1.57e-03 |
Pos logit contributions | |
agreement | +0.059 |
particular | +0.056 |
date | +0.053 |
Everyday | +0.053 |
invite | +0.051 |
Neg logit contributions | |
w | -0.030 |
aged | -0.027 |
ich | -0.025 |
ller | -0.024 |
uts | -0.024 |
Token | bye |
Token ID | 33847 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.002 |
Everyday | +0.002 |
date | +0.002 |
invite | +0.002 |
Neg logit contributions | |
w | -0.003 |
ich | -0.002 |
ller | -0.002 |
aged | -0.002 |
llers | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.004 |
Everyday | +0.003 |
date | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
aged | -0.002 |
EEP | -0.002 |
Token | ie |
Token ID | 494 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
w | +0.025 |
ich | +0.022 |
ller | +0.021 |
aged | +0.020 |
irens | +0.020 |
Neg logit contributions | |
agreement | -0.016 |
Everyday | -0.014 |
particular | -0.014 |
offer | -0.012 |
date | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
w | +0.020 |
ich | +0.019 |
ller | +0.019 |
aged | +0.018 |
bleeding | +0.017 |
Neg logit contributions | |
agreement | -0.027 |
particular | -0.026 |
Everyday | -0.024 |
date | -0.023 |
invite | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
w | +0.066 |
ich | +0.060 |
elbows | +0.057 |
irens | +0.054 |
inches | +0.053 |
Neg logit contributions | |
agreement | -0.043 |
Everyday | -0.043 |
particular | -0.039 |
offer | -0.037 |
invite | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
w | +0.018 |
ich | +0.016 |
aged | +0.015 |
ller | +0.015 |
llers | +0.015 |
Neg logit contributions | |
agreement | -0.019 |
particular | -0.018 |
Everyday | -0.018 |
date | -0.017 |
invite | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
w | +0.010 |
ich | +0.009 |
ller | +0.008 |
aged | +0.008 |
llers | +0.008 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.011 |
Everyday | -0.011 |
date | -0.010 |
invite | -0.010 |
Token | Hello |
Token ID | 15496 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
inches | +0.059 |
aged | +0.056 |
ouncing | +0.055 |
w | +0.055 |
uts | +0.055 |
Neg logit contributions | |
agreement | -0.042 |
particular | -0.041 |
Everyday | -0.037 |
date | -0.034 |
offer | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
w | +0.118 |
elbows | +0.111 |
irens | +0.108 |
aged | +0.107 |
llers | +0.103 |
Neg logit contributions | |
agreement | -0.078 |
particular | -0.075 |
fill | -0.069 |
Everyday | -0.068 |
invite | -0.068 |
Token | little |
Token ID | 1310 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
w | +0.083 |
aged | +0.075 |
elbows | +0.074 |
irens | +0.073 |
ich | +0.073 |
Neg logit contributions | |
agreement | -0.062 |
particular | -0.057 |
Everyday | -0.053 |
offer | -0.053 |
invite | -0.052 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
w | +0.096 |
llers | +0.091 |
irens | +0.091 |
uts | +0.090 |
aged | +0.090 |
Neg logit contributions | |
agreement | -0.056 |
particular | -0.052 |
offer | -0.047 |
invite | -0.045 |
fill | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
w | +0.028 |
ich | +0.025 |
ller | +0.024 |
aged | +0.023 |
llers | +0.022 |
Neg logit contributions | |
agreement | -0.040 |
particular | -0.038 |
Everyday | -0.036 |
date | -0.036 |
invite | -0.034 |
Token | I |
Token ID | 314 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
w | +0.032 |
ich | +0.028 |
ller | +0.027 |
aged | +0.027 |
llers | +0.027 |
Neg logit contributions | |
agreement | -0.035 |
particular | -0.033 |
Everyday | -0.031 |
date | -0.031 |
invite | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
w | +0.008 |
ich | +0.007 |
ller | +0.007 |
llers | +0.007 |
irens | +0.007 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.009 |
Everyday | -0.009 |
date | -0.009 |
invite | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.013 |
date | +0.011 |
Everyday | +0.011 |
invite | +0.011 |
Neg logit contributions | |
w | -0.024 |
aged | -0.021 |
llers | -0.021 |
ller | -0.021 |
ich | -0.021 |
Token | bird |
Token ID | 6512 |
Feature activation | -6.52e-03 |
Pos logit contributions | |
agreement | +0.027 |
particular | +0.024 |
Everyday | +0.024 |
date | +0.024 |
invite | +0.023 |
Neg logit contributions | |
w | -0.021 |
ich | -0.019 |
ller | -0.018 |
llers | -0.017 |
RR | -0.017 |
Token | named |
Token ID | 3706 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
w | +0.013 |
ich | +0.012 |
ller | +0.012 |
llers | +0.012 |
aged | +0.012 |
Neg logit contributions | |
agreement | -0.007 |
particular | -0.006 |
Everyday | -0.006 |
date | -0.006 |
invite | -0.006 |
Token | O |
Token ID | 440 |
Feature activation | +4.89e-03 |
Pos logit contributions | |
w | +0.024 |
aged | +0.022 |
elbows | +0.022 |
irens | +0.022 |
ich | +0.022 |
Neg logit contributions | |
agreement | -0.017 |
Everyday | -0.016 |
particular | -0.016 |
fill | -0.016 |
invite | -0.015 |
Token | str |
Token ID | 2536 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
agreement | +0.009 |
particular | +0.009 |
date | +0.009 |
Everyday | +0.009 |
invite | +0.009 |
Neg logit contributions | |
w | -0.005 |
nam | -0.005 |
ller | -0.005 |
aged | -0.005 |
llers | -0.004 |
Token | ich |
Token ID | 488 |
Feature activation | +3.84e-03 |
Pos logit contributions | |
nam | +0.062 |
w | +0.053 |
AAAA | +0.050 |
elbows | +0.048 |
destruct | +0.045 |
Neg logit contributions | |
berry | -0.107 |
date | -0.107 |
particular | -0.102 |
Everyday | -0.098 |
ini | -0.098 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
Everyday | +0.003 |
date | +0.002 |
invite | +0.002 |
Neg logit contributions | |
w | -0.008 |
elbows | -0.008 |
irens | -0.008 |
nam | -0.008 |
ich | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.002 |
Everyday | +0.002 |
invite | +0.002 |
fill | +0.002 |
Neg logit contributions | |
w | -0.003 |
ich | -0.003 |
ller | -0.003 |
llers | -0.003 |
aged | -0.003 |
Token | swim |
Token ID | 9422 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
agreement | +0.022 |
particular | +0.018 |
Everyday | +0.017 |
date | +0.017 |
rily | +0.017 |
Neg logit contributions | |
w | -0.024 |
ich | -0.022 |
ller | -0.022 |
llers | -0.021 |
Blood | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
agreement | +0.027 |
Everyday | +0.024 |
particular | +0.024 |
Whenever | +0.023 |
tow | +0.023 |
Neg logit contributions | |
w | -0.013 |
nam | -0.009 |
ls | -0.008 |
ich | -0.008 |
RR | -0.008 |
Token | |
Token ID | 220 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
w | +0.045 |
nam | +0.043 |
elbows | +0.039 |
bleeding | +0.039 |
satellites | +0.039 |
Neg logit contributions | |
Everyday | -0.035 |
date | -0.033 |
particular | -0.033 |
agreement | -0.032 |
invite | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
w | +0.008 |
ich | +0.007 |
ller | +0.007 |
aged | +0.007 |
llers | +0.007 |
Neg logit contributions | |
agreement | -0.011 |
particular | -0.010 |
Everyday | -0.010 |
date | -0.009 |
invite | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +8.07e-03 |
Pos logit contributions | |
agreement | +0.017 |
particular | +0.016 |
date | +0.015 |
invite | +0.015 |
Everyday | +0.015 |
Neg logit contributions | |
w | -0.008 |
ich | -0.007 |
ller | -0.007 |
irens | -0.007 |
RR | -0.007 |
Token | Miss |
Token ID | 17140 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
agreement | +0.015 |
particular | +0.014 |
offer | +0.014 |
fill | +0.014 |
invite | +0.013 |
Neg logit contributions | |
w | -0.010 |
ich | -0.008 |
RR | -0.008 |
irens | -0.008 |
ller | -0.008 |
Token | O |
Token ID | 440 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
w | +0.010 |
ich | +0.009 |
ller | +0.009 |
aged | +0.009 |
llers | +0.009 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.010 |
Everyday | -0.009 |
date | -0.009 |
invite | -0.009 |
Token | str |
Token ID | 2536 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
Everyday | +0.012 |
date | +0.012 |
invite | +0.012 |
Neg logit contributions | |
w | -0.005 |
ich | -0.005 |
nam | -0.004 |
aged | -0.004 |
ller | -0.004 |
Token | ich |
Token ID | 488 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
nam | +0.059 |
w | +0.049 |
AAAA | +0.047 |
satellites | +0.045 |
elbows | +0.044 |
Neg logit contributions | |
Everyday | -0.104 |
agreement | -0.103 |
date | -0.102 |
particular | -0.100 |
berry | -0.099 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
agreement | +0.032 |
particular | +0.029 |
date | +0.028 |
Everyday | +0.027 |
invite | +0.027 |
Neg logit contributions | |
w | -0.021 |
ller | -0.018 |
ich | -0.018 |
aged | -0.017 |
llers | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
particular | +0.025 |
date | +0.024 |
agreement | +0.024 |
invite | +0.023 |
Everyday | +0.022 |
Neg logit contributions | |
aged | -0.014 |
ller | -0.014 |
ich | -0.013 |
w | -0.013 |
crying | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
w | +0.004 |
ich | +0.004 |
ller | +0.004 |
aged | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.008 |
particular | -0.007 |
date | -0.007 |
Everyday | -0.007 |
invite | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
agreement | +0.039 |
particular | +0.037 |
Everyday | +0.035 |
date | +0.034 |
invite | +0.034 |
Neg logit contributions | |
w | -0.031 |
ich | -0.027 |
ller | -0.027 |
aged | -0.026 |
llers | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
w | +0.011 |
ich | +0.011 |
ller | +0.011 |
uts | +0.011 |
reading | +0.010 |
Neg logit contributions | |
agreement | -0.019 |
particular | -0.018 |
Everyday | -0.016 |
date | -0.016 |
latable | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
agreement | +0.039 |
particular | +0.038 |
date | +0.035 |
offer | +0.033 |
end | +0.032 |
Neg logit contributions | |
ller | -0.021 |
Blood | -0.021 |
EEP | -0.021 |
aged | -0.020 |
llers | -0.020 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
w | +0.019 |
ich | +0.017 |
ller | +0.017 |
aged | +0.017 |
llers | +0.016 |
Neg logit contributions | |
agreement | -0.019 |
particular | -0.018 |
Everyday | -0.017 |
date | -0.017 |
invite | -0.016 |
Token | lots |
Token ID | 6041 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
w | +0.009 |
ich | +0.008 |
ller | +0.008 |
aged | +0.007 |
llers | +0.007 |
Neg logit contributions | |
agreement | -0.009 |
particular | -0.008 |
Everyday | -0.008 |
date | -0.008 |
invite | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.002 |
date | +0.002 |
Everyday | +0.001 |
invite | +0.001 |
Neg logit contributions | |
w | -0.005 |
ich | -0.005 |
ller | -0.005 |
irens | -0.004 |
aged | -0.004 |
Token | old |
Token ID | 1468 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
w | +0.036 |
ich | +0.033 |
ller | +0.032 |
llers | +0.031 |
aged | +0.031 |
Neg logit contributions | |
agreement | -0.034 |
particular | -0.031 |
Everyday | -0.030 |
invite | -0.029 |
offer | -0.028 |
Token | things |
Token ID | 1243 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
w | +0.122 |
shadow | +0.119 |
RR | +0.113 |
Blood | +0.113 |
EEP | +0.113 |
Neg logit contributions | |
of | -0.061 |
agreement | -0.061 |
invite | -0.059 |
offer | -0.059 |
est | -0.059 |
Token | like |
Token ID | 588 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
w | +0.003 |
ich | +0.003 |
ller | +0.003 |
uts | +0.003 |
aged | +0.003 |
Neg logit contributions | |
agreement | -0.004 |
particular | -0.004 |
date | -0.004 |
Everyday | -0.004 |
invite | -0.003 |
Token | swords |
Token ID | 19735 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
w | +0.001 |
ich | +0.001 |
ller | +0.001 |
llers | +0.001 |
aged | +0.001 |
Neg logit contributions | |
agreement | -0.002 |
particular | -0.002 |
date | -0.002 |
Everyday | -0.002 |
invite | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
w | +0.020 |
ich | +0.018 |
ller | +0.018 |
aged | +0.017 |
llers | +0.017 |
Neg logit contributions | |
agreement | -0.019 |
particular | -0.017 |
Everyday | -0.016 |
date | -0.016 |
invite | -0.016 |
Token | shields |
Token ID | 21132 |
Feature activation | -6.07e-03 |
Pos logit contributions | |
w | +0.014 |
ich | +0.012 |
ller | +0.012 |
nam | +0.012 |
llers | +0.012 |
Neg logit contributions | |
agreement | -0.020 |
particular | -0.019 |
date | -0.018 |
Everyday | -0.017 |
invite | -0.016 |
Token | balloon |
Token ID | 21190 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
agreement | +0.017 |
particular | +0.015 |
date | +0.014 |
Everyday | +0.014 |
invite | +0.014 |
Neg logit contributions | |
w | -0.013 |
ich | -0.011 |
ller | -0.011 |
inches | -0.010 |
llers | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
Everyday | +0.002 |
date | +0.002 |
invite | +0.002 |
Neg logit contributions | |
w | -0.002 |
ller | -0.002 |
ich | -0.002 |
uts | -0.002 |
inches | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
agreement | +0.026 |
particular | +0.024 |
offer | +0.023 |
date | +0.023 |
fill | +0.023 |
Neg logit contributions | |
w | -0.013 |
ller | -0.013 |
Blood | -0.012 |
uts | -0.012 |
llers | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
w | +0.009 |
ich | +0.007 |
ller | +0.007 |
irens | +0.007 |
Blood | +0.007 |
Neg logit contributions | |
agreement | -0.017 |
particular | -0.016 |
date | -0.016 |
invite | -0.016 |
fill | -0.016 |
Token | A |
Token ID | 32 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
w | +0.011 |
ich | +0.010 |
ller | +0.009 |
irens | +0.009 |
RR | +0.009 |
Neg logit contributions | |
agreement | -0.015 |
particular | -0.014 |
Everyday | -0.013 |
date | -0.013 |
invite | -0.013 |
Token | str |
Token ID | 2536 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
agreement | +0.021 |
Everyday | +0.019 |
particular | +0.019 |
date | +0.018 |
invite | +0.018 |
Neg logit contributions | |
w | -0.018 |
ich | -0.017 |
ller | -0.017 |
RR | -0.015 |
AAAA | -0.015 |
Token | id |
Token ID | 312 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
w | +0.044 |
nam | +0.044 |
elbows | +0.044 |
AAAA | +0.044 |
Whe | +0.041 |
Neg logit contributions | |
agreement | -0.113 |
date | -0.112 |
rily | -0.106 |
particular | -0.105 |
ini | -0.105 |
Token | held |
Token ID | 2714 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.004 |
date | +0.004 |
Everyday | +0.004 |
invite | +0.004 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
aged | -0.003 |
ller | -0.003 |
llers | -0.003 |
Token | onto |
Token ID | 4291 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
w | +0.002 |
aged | +0.002 |
ich | +0.002 |
ller | +0.002 |
nam | +0.002 |
Neg logit contributions | |
agreement | -0.003 |
date | -0.003 |
particular | -0.003 |
invite | -0.003 |
Everyday | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
date | +0.012 |
Everyday | +0.012 |
invite | +0.012 |
Neg logit contributions | |
w | -0.010 |
ich | -0.009 |
ller | -0.009 |
aged | -0.009 |
llers | -0.008 |
Token | balloon |
Token ID | 21190 |
Feature activation | -7.98e-03 |
Pos logit contributions | |
agreement | +0.034 |
date | +0.033 |
Everyday | +0.033 |
particular | +0.032 |
invite | +0.031 |
Neg logit contributions | |
ich | -0.024 |
ller | -0.023 |
w | -0.022 |
nam | -0.021 |
bleeding | -0.021 |
Token | around |
Token ID | 1088 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
w | +0.019 |
ich | +0.017 |
ller | +0.016 |
aged | +0.016 |
llers | +0.016 |
Neg logit contributions | |
agreement | -0.021 |
particular | -0.020 |
date | -0.019 |
Everyday | -0.019 |
invite | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
w | +0.004 |
ller | +0.004 |
ich | +0.004 |
aged | +0.004 |
Blood | +0.004 |
Neg logit contributions | |
agreement | -0.006 |
date | -0.006 |
Everyday | -0.006 |
particular | -0.006 |
invite | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
w | +0.025 |
ich | +0.024 |
irens | +0.022 |
ller | +0.022 |
uts | +0.022 |
Neg logit contributions | |
agreement | -0.020 |
particular | -0.019 |
invite | -0.018 |
Everyday | -0.018 |
fill | -0.018 |
Token | lots |
Token ID | 6041 |
Feature activation | +9.65e-04 |
Pos logit contributions | |
agreement | +0.007 |
particular | +0.006 |
date | +0.006 |
Everyday | +0.006 |
invite | +0.006 |
Neg logit contributions | |
w | -0.004 |
ich | -0.004 |
ller | -0.004 |
aged | -0.004 |
nam | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
agreement | +0.001 |
date | +0.001 |
particular | +0.001 |
surely | +0.001 |
invite | +0.001 |
Neg logit contributions | |
irens | -0.002 |
ller | -0.002 |
uts | -0.002 |
flashing | -0.002 |
ls | -0.002 |
Token | interesting |
Token ID | 3499 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
w | +0.037 |
ich | +0.034 |
ller | +0.032 |
aged | +0.031 |
llers | +0.031 |
Neg logit contributions | |
agreement | -0.046 |
particular | -0.043 |
Everyday | -0.041 |
date | -0.040 |
invite | -0.040 |
Token | things |
Token ID | 1243 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
w | +0.114 |
ich | +0.109 |
EEP | +0.098 |
shadow | +0.097 |
AAAA | +0.095 |
Neg logit contributions | |
particular | -0.084 |
agreement | -0.082 |
Everyday | -0.078 |
offer | -0.077 |
invite | -0.076 |
Token | in |
Token ID | 287 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
w | +0.001 |
uts | +0.001 |
ller | +0.001 |
ich | +0.001 |
aged | +0.001 |
Neg logit contributions | |
agreement | -0.002 |
particular | -0.002 |
date | -0.002 |
Everyday | -0.002 |
invite | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
agreement | +0.022 |
date | +0.021 |
Everyday | +0.019 |
invite | +0.019 |
particular | +0.019 |
Neg logit contributions | |
w | -0.012 |
irens | -0.011 |
nam | -0.011 |
ller | -0.010 |
ich | -0.010 |
Token | room |
Token ID | 2119 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
w | +0.062 |
ich | +0.058 |
ller | +0.056 |
aged | +0.055 |
llers | +0.055 |
Neg logit contributions | |
agreement | -0.056 |
particular | -0.052 |
Everyday | -0.049 |
date | -0.048 |
invite | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
agreement | +0.026 |
particular | +0.023 |
Everyday | +0.023 |
date | +0.022 |
iona | +0.021 |
Neg logit contributions | |
w | -0.014 |
aged | -0.014 |
uts | -0.014 |
ich | -0.014 |
reading | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
w | +0.033 |
aged | +0.029 |
ich | +0.028 |
llers | +0.028 |
ller | +0.028 |
Neg logit contributions | |
agreement | -0.049 |
particular | -0.046 |
date | -0.044 |
Everyday | -0.043 |
offer | -0.041 |
Token | box |
Token ID | 3091 |
Feature activation | -2.22e-03 |
Pos logit contributions | |
w | +0.022 |
ich | +0.021 |
nam | +0.019 |
praying | +0.019 |
ller | +0.019 |
Neg logit contributions | |
agreement | -0.026 |
Everyday | -0.024 |
particular | -0.023 |
date | -0.022 |
Whenever | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
w | +0.003 |
aged | +0.003 |
reading | +0.003 |
uts | +0.003 |
ich | +0.003 |
Neg logit contributions | |
agreement | -0.004 |
particular | -0.003 |
Everyday | -0.003 |
date | -0.003 |
Whenever | -0.003 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
w | +0.014 |
nam | +0.012 |
aged | +0.011 |
ller | +0.011 |
flashing | +0.011 |
Neg logit contributions | |
agreement | -0.021 |
date | -0.019 |
particular | -0.019 |
Everyday | -0.018 |
surely | -0.018 |
Token | or |
Token ID | 393 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
w | +0.027 |
ller | +0.023 |
ich | +0.023 |
aged | +0.023 |
llers | +0.022 |
Neg logit contributions | |
agreement | -0.044 |
particular | -0.041 |
date | -0.040 |
Everyday | -0.039 |
invite | -0.038 |
Token | nam |
Token ID | 7402 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
w | +0.011 |
ich | +0.009 |
ller | +0.009 |
aged | +0.008 |
llers | +0.008 |
Neg logit contributions | |
agreement | -0.032 |
particular | -0.030 |
Everyday | -0.029 |
date | -0.029 |
invite | -0.028 |
Token | ents |
Token ID | 658 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
AAAA | +0.104 |
w | +0.100 |
rob | +0.094 |
elbows | +0.092 |
ses | +0.091 |
Neg logit contributions | |
agreement | -0.079 |
Everyday | -0.079 |
of | -0.077 |
particular | -0.075 |
fill | -0.073 |
Token | that |
Token ID | 326 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
agreement | +0.011 |
particular | +0.009 |
Everyday | +0.009 |
date | +0.009 |
invite | +0.009 |
Neg logit contributions | |
w | -0.006 |
uts | -0.006 |
ich | -0.005 |
aged | -0.005 |
ller | -0.005 |
Token | spark |
Token ID | 9009 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
w | +0.024 |
ich | +0.019 |
aged | +0.019 |
ller | +0.019 |
nam | +0.018 |
Neg logit contributions | |
agreement | -0.043 |
particular | -0.037 |
date | -0.037 |
Everyday | -0.036 |
invite | -0.035 |
Token | led |
Token ID | 992 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
w | +0.007 |
ller | +0.006 |
aged | +0.006 |
uts | +0.005 |
llers | +0.005 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.010 |
Everyday | -0.010 |
date | -0.010 |
invite | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
agreement | +0.010 |
invite | +0.009 |
particular | +0.009 |
Everyday | +0.009 |
date | +0.009 |
Neg logit contributions | |
w | -0.004 |
nam | -0.004 |
reading | -0.003 |
aged | -0.003 |
flashing | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
date | +0.050 |
tted | +0.046 |
host | +0.046 |
surely | +0.046 |
agreement | +0.046 |
Neg logit contributions | |
reading | -0.013 |
crying | -0.010 |
pressing | -0.010 |
crossing | -0.010 |
touching | -0.009 |
Token | lake |
Token ID | 13546 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
w | +0.007 |
ich | +0.006 |
ller | +0.006 |
llers | +0.006 |
irens | +0.006 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.005 |
date | -0.004 |
Everyday | -0.004 |
invite | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.013 |
date | +0.012 |
Everyday | +0.012 |
surely | +0.012 |
Neg logit contributions | |
w | -0.006 |
ich | -0.006 |
nam | -0.006 |
reading | -0.005 |
crying | -0.005 |
Token | But |
Token ID | 887 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.002 |
date | +0.002 |
invite | +0.002 |
Everyday | +0.002 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
aged | -0.002 |
llers | -0.002 |
Token | O |
Token ID | 440 |
Feature activation | +6.19e-04 |
Pos logit contributions | |
agreement | +0.007 |
particular | +0.006 |
Everyday | +0.006 |
date | +0.006 |
invite | +0.006 |
Neg logit contributions | |
w | -0.006 |
ich | -0.006 |
ller | -0.006 |
aged | -0.005 |
llers | -0.005 |
Token | str |
Token ID | 2536 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
particular | +0.001 |
agreement | +0.001 |
Everyday | +0.001 |
date | +0.001 |
offer | +0.001 |
Neg logit contributions | |
nam | -0.001 |
elbows | -0.001 |
irens | -0.000 |
ller | -0.000 |
w | -0.000 |
Token | ich |
Token ID | 488 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
nam | +0.064 |
elbows | +0.050 |
w | +0.048 |
AAAA | +0.047 |
RR | +0.044 |
Neg logit contributions | |
date | -0.104 |
Everyday | -0.102 |
ini | -0.101 |
particular | -0.101 |
finally | -0.098 |
Token | was |
Token ID | 373 |
Feature activation | -7.75e-05 |
Pos logit contributions | |
agreement | +0.032 |
particular | +0.029 |
Everyday | +0.027 |
date | +0.027 |
invite | +0.027 |
Neg logit contributions | |
w | -0.033 |
ich | -0.029 |
aged | -0.029 |
ller | -0.028 |
llers | -0.027 |
Token | scared |
Token ID | 12008 |
Feature activation | -4.49e-04 |
Pos logit contributions | |
w | +0.000 |
ich | +0.000 |
ller | +0.000 |
llers | +0.000 |
EEP | +0.000 |
Neg logit contributions | |
agreement | -0.000 |
particular | -0.000 |
Everyday | -0.000 |
invite | -0.000 |
fill | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
w | +0.001 |
ich | +0.001 |
ller | +0.001 |
aged | +0.001 |
llers | +0.001 |
Neg logit contributions | |
agreement | -0.001 |
particular | -0.001 |
date | -0.001 |
invite | -0.001 |
Everyday | -0.001 |
Token | water |
Token ID | 1660 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
w | +0.003 |
ich | +0.002 |
ller | +0.002 |
aged | +0.002 |
llers | +0.002 |
Neg logit contributions | |
agreement | -0.003 |
particular | -0.002 |
Everyday | -0.002 |
invite | -0.002 |
date | -0.002 |
Token | � |
Token ID | 95 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
w | +0.005 |
ich | +0.004 |
aged | +0.004 |
ller | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.005 |
Everyday | -0.004 |
date | -0.004 |
invite | -0.004 |
Token | € |
Token ID | 26391 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
w | +0.012 |
ich | +0.010 |
ller | +0.010 |
aged | +0.010 |
llers | +0.010 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.011 |
Everyday | -0.011 |
date | -0.011 |
invite | -0.011 |
Token | Hi |
Token ID | 17250 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
nam | +0.038 |
w | +0.036 |
elbows | +0.032 |
satellites | +0.032 |
destruct | +0.031 |
Neg logit contributions | |
date | -0.038 |
Everyday | -0.038 |
particular | -0.037 |
invite | -0.035 |
agreement | -0.035 |
Token | Miss |
Token ID | 4544 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
w | +0.012 |
ich | +0.011 |
ller | +0.011 |
RR | +0.010 |
llers | +0.010 |
Neg logit contributions | |
agreement | -0.019 |
particular | -0.017 |
Everyday | -0.017 |
date | -0.017 |
invite | -0.017 |
Token | O |
Token ID | 440 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
w | +0.017 |
ich | +0.015 |
ller | +0.015 |
aged | +0.014 |
llers | +0.014 |
Neg logit contributions | |
agreement | -0.018 |
particular | -0.016 |
Everyday | -0.016 |
date | -0.015 |
invite | -0.015 |
Token | str |
Token ID | 2536 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
agreement | +0.009 |
particular | +0.009 |
date | +0.008 |
Everyday | +0.008 |
invite | +0.008 |
Neg logit contributions | |
w | -0.003 |
aged | -0.002 |
nam | -0.002 |
elbows | -0.002 |
ich | -0.002 |
Token | ich |
Token ID | 488 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
nam | +0.050 |
AAAA | +0.048 |
w | +0.047 |
satellites | +0.042 |
Crash | +0.041 |
Neg logit contributions | |
agreement | -0.108 |
date | -0.106 |
Everyday | -0.105 |
berry | -0.105 |
particular | -0.104 |
Token | ! |
Token ID | 0 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
agreement | +0.044 |
particular | +0.042 |
date | +0.039 |
Everyday | +0.039 |
latable | +0.039 |
Neg logit contributions | |
w | -0.027 |
ller | -0.025 |
ich | -0.025 |
crying | -0.021 |
bleeding | -0.021 |
Token | That |
Token ID | 1320 |
Feature activation | -3.88e-04 |
Pos logit contributions | |
agreement | +0.028 |
particular | +0.026 |
date | +0.025 |
invite | +0.024 |
Everyday | +0.024 |
Neg logit contributions | |
w | -0.018 |
ich | -0.016 |
ller | -0.016 |
llers | -0.015 |
RR | -0.015 |
Token | sounds |
Token ID | 5238 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
w | +0.001 |
ich | +0.000 |
ller | +0.000 |
llers | +0.000 |
aged | +0.000 |
Neg logit contributions | |
agreement | -0.001 |
particular | -0.001 |
date | -0.001 |
Everyday | -0.001 |
invite | -0.001 |
Token | funny |
Token ID | 8258 |
Feature activation | +9.74e-04 |
Pos logit contributions | |
agreement | +0.032 |
date | +0.030 |
particular | +0.028 |
ainer | +0.027 |
Everyday | +0.026 |
Neg logit contributions | |
w | -0.031 |
happened | -0.028 |
nam | -0.026 |
bleeding | -0.026 |
ller | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
w | +0.035 |
ich | +0.032 |
ller | +0.031 |
aged | +0.030 |
llers | +0.030 |
Neg logit contributions | |
agreement | -0.027 |
particular | -0.025 |
Everyday | -0.023 |
date | -0.023 |
invite | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
agreement | +0.022 |
particular | +0.020 |
Everyday | +0.019 |
invite | +0.018 |
date | +0.018 |
Neg logit contributions | |
w | -0.024 |
ich | -0.022 |
ller | -0.021 |
llers | -0.020 |
aged | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.004 |
Everyday | +0.004 |
invite | +0.003 |
offer | +0.003 |
Neg logit contributions | |
w | -0.005 |
ich | -0.004 |
nam | -0.004 |
ller | -0.004 |
llers | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
agreement | +0.026 |
particular | +0.024 |
Everyday | +0.023 |
date | +0.023 |
invite | +0.022 |
Neg logit contributions | |
w | -0.020 |
ich | -0.018 |
ller | -0.017 |
aged | -0.017 |
llers | -0.016 |
Token | Bad |
Token ID | 22069 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
w | +0.020 |
ich | +0.018 |
ller | +0.017 |
aged | +0.017 |
llers | +0.016 |
Neg logit contributions | |
agreement | -0.023 |
particular | -0.021 |
Everyday | -0.021 |
date | -0.020 |
invite | -0.020 |
Token | wind |
Token ID | 2344 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
w | +0.083 |
aged | +0.078 |
nam | +0.078 |
shadow | +0.076 |
irens | +0.074 |
Neg logit contributions | |
agreement | -0.057 |
end | -0.052 |
particular | -0.050 |
date | -0.048 |
offer | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +6.28e-03 |
Pos logit contributions | |
w | +0.091 |
ich | +0.084 |
ller | +0.082 |
llers | +0.081 |
nam | +0.080 |
Neg logit contributions | |
agreement | -0.097 |
particular | -0.089 |
date | -0.086 |
Everyday | -0.085 |
invite | -0.084 |
Token | bad |
Token ID | 2089 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
agreement | +0.011 |
date | +0.011 |
particular | +0.010 |
Everyday | +0.010 |
invite | +0.009 |
Neg logit contributions | |
w | -0.009 |
ich | -0.008 |
ller | -0.007 |
Blood | -0.007 |
RR | -0.007 |
Token | wind |
Token ID | 2344 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
w | +0.089 |
ich | +0.084 |
aged | +0.082 |
llers | +0.081 |
ller | +0.081 |
Neg logit contributions | |
agreement | -0.075 |
particular | -0.069 |
offer | -0.066 |
invite | -0.065 |
Everyday | -0.065 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
w | +0.082 |
ich | +0.075 |
ller | +0.072 |
llers | +0.072 |
irens | +0.072 |
Neg logit contributions | |
agreement | -0.091 |
particular | -0.084 |
Everyday | -0.080 |
date | -0.079 |
invite | -0.079 |
Token | L |
Token ID | 406 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
agreement | +0.010 |
particular | +0.009 |
Everyday | +0.008 |
invite | +0.008 |
date | +0.008 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.009 |
llers | -0.009 |
aged | -0.009 |
Token | |
Token ID | 220 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
w | +0.033 |
nam | +0.031 |
bleeding | +0.028 |
aged | +0.028 |
destruct | +0.028 |
Neg logit contributions | |
Everyday | -0.032 |
agreement | -0.032 |
date | -0.031 |
particular | -0.031 |
invite | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
w | +0.004 |
ich | +0.004 |
ller | +0.004 |
aged | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.005 |
Everyday | -0.005 |
date | -0.005 |
invite | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
agreement | +0.011 |
particular | +0.010 |
date | +0.010 |
invite | +0.009 |
fill | +0.009 |
Neg logit contributions | |
w | -0.005 |
ich | -0.004 |
ller | -0.004 |
irens | -0.004 |
aged | -0.004 |
Token | Miss |
Token ID | 17140 |
Feature activation | -8.86e-03 |
Pos logit contributions | |
agreement | +0.015 |
fill | +0.014 |
particular | +0.014 |
invite | +0.014 |
offer | +0.014 |
Neg logit contributions | |
w | -0.010 |
ich | -0.008 |
irens | -0.008 |
RR | -0.008 |
uts | -0.007 |
Token | O |
Token ID | 440 |
Feature activation | +4.33e-03 |
Pos logit contributions | |
w | +0.013 |
ich | +0.012 |
ller | +0.012 |
aged | +0.011 |
llers | +0.011 |
Neg logit contributions | |
agreement | -0.015 |
particular | -0.013 |
Everyday | -0.013 |
date | -0.013 |
invite | -0.012 |
Token | str |
Token ID | 2536 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
agreement | +0.009 |
particular | +0.009 |
Everyday | +0.009 |
date | +0.008 |
invite | +0.008 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
nam | -0.003 |
aged | -0.003 |
ller | -0.003 |
Token | ich |
Token ID | 488 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
nam | +0.066 |
w | +0.051 |
elbows | +0.050 |
satellites | +0.049 |
AAAA | +0.048 |
Neg logit contributions | |
Everyday | -0.099 |
agreement | -0.097 |
date | -0.097 |
ini | -0.094 |
particular | -0.094 |
Token | told |
Token ID | 1297 |
Feature activation | +3.60e-03 |
Pos logit contributions | |
agreement | +0.034 |
particular | +0.031 |
date | +0.029 |
Everyday | +0.028 |
latable | +0.027 |
Neg logit contributions | |
w | -0.024 |
ller | -0.020 |
ich | -0.020 |
aged | -0.019 |
llers | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
agreement | +0.007 |
particular | +0.007 |
date | +0.006 |
Everyday | +0.006 |
latable | +0.006 |
Neg logit contributions | |
w | -0.004 |
ller | -0.003 |
irens | -0.003 |
aged | -0.003 |
llers | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
agreement | +0.011 |
date | +0.010 |
particular | +0.009 |
Everyday | +0.009 |
invite | +0.009 |
Neg logit contributions | |
w | -0.011 |
ller | -0.010 |
ich | -0.010 |
RR | -0.010 |
EEP | -0.010 |
Token | funny |
Token ID | 8258 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
agreement | +0.032 |
date | +0.031 |
Everyday | +0.028 |
fill | +0.028 |
particular | +0.027 |
Neg logit contributions | |
w | -0.025 |
ller | -0.023 |
ich | -0.022 |
aged | -0.022 |
uts | -0.021 |
Token | N |
Token ID | 45 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
w | +0.009 |
ich | +0.008 |
ller | +0.008 |
irens | +0.008 |
aged | +0.008 |
Neg logit contributions | |
agreement | -0.013 |
particular | -0.012 |
Everyday | -0.012 |
invite | -0.012 |
date | -0.012 |
Token | ina |
Token ID | 1437 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
w | +0.014 |
ich | +0.012 |
nam | +0.012 |
irens | +0.012 |
elbows | +0.012 |
Neg logit contributions | |
agreement | -0.015 |
particular | -0.014 |
Everyday | -0.013 |
date | -0.013 |
offer | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
agreement | +0.020 |
particular | +0.018 |
date | +0.018 |
Everyday | +0.017 |
invite | +0.016 |
Neg logit contributions | |
w | -0.016 |
ller | -0.015 |
aged | -0.014 |
ich | -0.014 |
llers | -0.014 |
Token | panic |
Token ID | 13619 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
particular | +0.004 |
agreement | +0.004 |
date | +0.004 |
offer | +0.004 |
Everyday | +0.004 |
Neg logit contributions | |
aged | -0.003 |
crying | -0.003 |
ich | -0.003 |
reading | -0.003 |
bleeding | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.013 |
date | +0.013 |
Everyday | +0.013 |
invite | +0.013 |
Neg logit contributions | |
w | -0.011 |
ller | -0.010 |
aged | -0.010 |
bleeding | -0.010 |
ich | -0.010 |
Token | str |
Token ID | 2536 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
w | +0.011 |
ich | +0.010 |
ller | +0.009 |
aged | +0.009 |
llers | +0.009 |
Neg logit contributions | |
agreement | -0.014 |
particular | -0.012 |
Everyday | -0.012 |
date | -0.012 |
invite | -0.012 |
Token | icken |
Token ID | 5973 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
AAAA | +0.051 |
nam | +0.048 |
w | +0.047 |
Crash | +0.044 |
RR | +0.044 |
Neg logit contributions | |
agreement | -0.107 |
date | -0.105 |
rily | -0.104 |
ini | -0.099 |
particular | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
particular | +0.036 |
agreement | +0.036 |
date | +0.033 |
invite | +0.032 |
surely | +0.031 |
Neg logit contributions | |
w | -0.025 |
aged | -0.024 |
ages | -0.022 |
ller | -0.021 |
icken | -0.021 |
Token | She |
Token ID | 1375 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
agreement | +0.027 |
particular | +0.024 |
date | +0.024 |
invite | +0.023 |
offer | +0.023 |
Neg logit contributions | |
w | -0.016 |
ich | -0.015 |
ller | -0.015 |
aged | -0.015 |
Blood | -0.014 |
Token | screamed |
Token ID | 25421 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
agreement | +0.029 |
date | +0.027 |
particular | +0.027 |
Everyday | +0.025 |
basis | +0.025 |
Neg logit contributions | |
w | -0.017 |
aged | -0.015 |
screamed | -0.014 |
ller | -0.014 |
bleeding | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.015 |
Everyday | +0.014 |
date | +0.014 |
invite | +0.014 |
Neg logit contributions | |
w | -0.013 |
aged | -0.012 |
ich | -0.012 |
ller | -0.012 |
bleeding | -0.011 |
Token | new |
Token ID | 649 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
w | +0.026 |
ich | +0.024 |
ller | +0.023 |
aged | +0.023 |
llers | +0.022 |
Neg logit contributions | |
agreement | -0.029 |
particular | -0.027 |
Everyday | -0.025 |
date | -0.025 |
invite | -0.025 |
Token | words |
Token ID | 2456 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
w | +0.042 |
ich | +0.040 |
Blood | +0.037 |
awed | +0.037 |
ounced | +0.036 |
Neg logit contributions | |
agreement | -0.039 |
offer | -0.036 |
particular | -0.034 |
invite | -0.033 |
Everyday | -0.033 |
Token | every |
Token ID | 790 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
agreement | +0.008 |
particular | +0.007 |
date | +0.007 |
Everyday | +0.007 |
latable | +0.007 |
Neg logit contributions | |
w | -0.006 |
ller | -0.006 |
uts | -0.006 |
ich | -0.005 |
llers | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
agreement | +0.022 |
Everyday | +0.020 |
particular | +0.019 |
date | +0.018 |
latable | +0.018 |
Neg logit contributions | |
w | -0.032 |
ich | -0.027 |
ller | -0.026 |
RR | -0.025 |
reading | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +8.74e-04 |
Pos logit contributions | |
agreement | +0.021 |
particular | +0.020 |
date | +0.019 |
Everyday | +0.018 |
latable | +0.017 |
Neg logit contributions | |
w | -0.016 |
uts | -0.014 |
ller | -0.013 |
ich | -0.013 |
reading | -0.013 |
Token | Conf |
Token ID | 7326 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.001 |
Everyday | +0.001 |
date | +0.001 |
invite | +0.001 |
Neg logit contributions | |
w | -0.001 |
ich | -0.001 |
ller | -0.001 |
aged | -0.001 |
llers | -0.001 |
Token | used |
Token ID | 1484 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
w | +0.080 |
ller | +0.071 |
ich | +0.070 |
aged | +0.068 |
llers | +0.067 |
Neg logit contributions | |
agreement | -0.107 |
particular | -0.098 |
date | -0.095 |
Everyday | -0.095 |
invite | -0.093 |
Token | is |
Token ID | 318 |
Feature activation | -3.52e-04 |
Pos logit contributions | |
agreement | +0.005 |
date | +0.005 |
particular | +0.005 |
Everyday | +0.005 |
invite | +0.004 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
ller | -0.003 |
aged | -0.003 |
RR | -0.003 |
Token | just |
Token ID | 655 |
Feature activation | +1.92e-04 |
Pos logit contributions | |
w | +0.000 |
ich | +0.000 |
ller | +0.000 |
aged | +0.000 |
llers | +0.000 |
Neg logit contributions | |
agreement | -0.001 |
particular | -0.001 |
date | -0.001 |
Everyday | -0.001 |
invite | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -8.78e-03 |
Pos logit contributions | |
agreement | +0.000 |
particular | +0.000 |
date | +0.000 |
Everyday | +0.000 |
invite | +0.000 |
Neg logit contributions | |
w | -0.000 |
ich | -0.000 |
aged | -0.000 |
ller | -0.000 |
nam | -0.000 |
Token | word |
Token ID | 1573 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
w | +0.014 |
ich | +0.013 |
ller | +0.012 |
llers | +0.012 |
aged | +0.012 |
Neg logit contributions | |
agreement | -0.013 |
particular | -0.012 |
Everyday | -0.012 |
date | -0.012 |
invite | -0.011 |
Token | cherry |
Token ID | 23612 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
w | +0.034 |
aged | +0.031 |
llers | +0.030 |
irens | +0.029 |
ller | +0.029 |
Neg logit contributions | |
agreement | -0.025 |
particular | -0.024 |
date | -0.022 |
Everyday | -0.021 |
invite | -0.021 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
w | +0.048 |
ich | +0.044 |
ller | +0.043 |
aged | +0.043 |
llers | +0.043 |
Neg logit contributions | |
agreement | -0.036 |
particular | -0.034 |
Everyday | -0.032 |
date | -0.031 |
invite | -0.030 |
Token | with |
Token ID | 351 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
w | +0.030 |
ich | +0.027 |
ller | +0.026 |
aged | +0.025 |
llers | +0.025 |
Neg logit contributions | |
agreement | -0.031 |
particular | -0.029 |
Everyday | -0.027 |
date | -0.027 |
invite | -0.026 |
Token | lots |
Token ID | 6041 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
w | +0.037 |
ich | +0.035 |
ller | +0.034 |
llers | +0.033 |
irens | +0.032 |
Neg logit contributions | |
agreement | -0.039 |
particular | -0.036 |
Everyday | -0.035 |
invite | -0.032 |
fill | -0.032 |
Token | of |
Token ID | 286 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
w | +0.007 |
ich | +0.006 |
ller | +0.006 |
aged | +0.006 |
irens | +0.006 |
Neg logit contributions | |
agreement | -0.002 |
particular | -0.002 |
date | -0.002 |
invite | -0.001 |
Everyday | -0.001 |
Token | cher |
Token ID | 21382 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
ich | +0.041 |
w | +0.040 |
ller | +0.038 |
llers | +0.036 |
irens | +0.036 |
Neg logit contributions | |
agreement | -0.056 |
Everyday | -0.053 |
particular | -0.052 |
offer | -0.049 |
fill | -0.048 |
Token | ries |
Token ID | 1678 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
RR | +0.088 |
EEP | +0.087 |
ses | +0.085 |
AAAA | +0.081 |
sed | +0.081 |
Neg logit contributions | |
particular | -0.076 |
Everyday | -0.073 |
fill | -0.072 |
agreement | -0.070 |
longer | -0.069 |
Token | on |
Token ID | 319 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
w | +0.017 |
ich | +0.015 |
ller | +0.015 |
aged | +0.014 |
llers | +0.014 |
Neg logit contributions | |
agreement | -0.015 |
particular | -0.014 |
Everyday | -0.013 |
date | -0.013 |
invite | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +8.58e-04 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
date | +0.003 |
invite | +0.003 |
Everyday | +0.003 |
Neg logit contributions | |
w | -0.003 |
ller | -0.003 |
ich | -0.003 |
llers | -0.003 |
aged | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.001 |
date | +0.001 |
invite | +0.001 |
Everyday | +0.001 |
Neg logit contributions | |
w | -0.001 |
uts | -0.001 |
ller | -0.001 |
aged | -0.001 |
ich | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
w | +0.015 |
ich | +0.013 |
ller | +0.012 |
aged | +0.012 |
llers | +0.012 |
Neg logit contributions | |
agreement | -0.014 |
particular | -0.013 |
Everyday | -0.012 |
date | -0.012 |
invite | -0.012 |
Token | went |
Token ID | 1816 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
w | +0.005 |
aged | +0.004 |
ich | +0.004 |
ller | +0.004 |
Blood | +0.004 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.004 |
Everyday | -0.004 |
date | -0.004 |
offer | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
w | +0.026 |
ich | +0.025 |
ller | +0.025 |
llers | +0.024 |
aged | +0.023 |
Neg logit contributions | |
particular | -0.021 |
agreement | -0.021 |
Everyday | -0.020 |
invite | -0.020 |
date | -0.020 |
Token | searched |
Token ID | 16499 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.011 |
Everyday | +0.011 |
date | +0.011 |
ainer | +0.011 |
Neg logit contributions | |
w | -0.008 |
aged | -0.007 |
ich | -0.006 |
Blood | -0.006 |
ller | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
w | +0.020 |
ich | +0.017 |
aged | +0.017 |
ller | +0.017 |
llers | +0.016 |
Neg logit contributions | |
agreement | -0.027 |
particular | -0.025 |
date | -0.024 |
Everyday | -0.024 |
invite | -0.023 |
Token | or |
Token ID | 393 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
w | +0.010 |
ich | +0.009 |
ller | +0.008 |
aged | +0.008 |
llers | +0.008 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.011 |
Everyday | -0.011 |
date | -0.011 |
invite | -0.010 |
Token | nam |
Token ID | 7402 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
w | +0.004 |
ich | +0.003 |
ller | +0.002 |
aged | +0.002 |
llers | +0.002 |
Neg logit contributions | |
agreement | -0.031 |
particular | -0.029 |
Everyday | -0.028 |
date | -0.028 |
invite | -0.028 |
Token | ents |
Token ID | 658 |
Feature activation | +9.65e-03 |
Pos logit contributions | |
AAAA | +0.100 |
w | +0.095 |
rob | +0.087 |
RR | +0.087 |
elbows | +0.087 |
Neg logit contributions | |
Everyday | -0.082 |
agreement | -0.081 |
of | -0.077 |
particular | -0.076 |
date | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
agreement | +0.019 |
particular | +0.017 |
Everyday | +0.016 |
date | +0.016 |
invite | +0.016 |
Neg logit contributions | |
w | -0.012 |
uts | -0.011 |
aged | -0.010 |
ich | -0.010 |
ller | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
w | +0.004 |
nam | +0.004 |
ich | +0.004 |
aged | +0.004 |
reading | +0.004 |
Neg logit contributions | |
agreement | -0.008 |
date | -0.007 |
Everyday | -0.007 |
particular | -0.007 |
invite | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
w | +0.009 |
ich | +0.008 |
aged | +0.007 |
nam | +0.007 |
ller | +0.007 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.009 |
date | -0.009 |
Everyday | -0.009 |
invite | -0.009 |
Token | more |
Token ID | 517 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
w | +0.031 |
ich | +0.029 |
ller | +0.028 |
aged | +0.027 |
nam | +0.027 |
Neg logit contributions | |
agreement | -0.032 |
particular | -0.029 |
date | -0.028 |
Everyday | -0.028 |
invite | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
agreement | +0.027 |
particular | +0.025 |
Everyday | +0.023 |
date | +0.023 |
invite | +0.023 |
Neg logit contributions | |
w | -0.032 |
ich | -0.029 |
ller | -0.028 |
aged | -0.027 |
llers | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
w | +0.042 |
nam | +0.040 |
bleeding | +0.036 |
elbows | +0.036 |
destruct | +0.035 |
Neg logit contributions | |
Everyday | -0.031 |
agreement | -0.028 |
particular | -0.028 |
Whenever | -0.028 |
invite | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
agreement | +0.010 |
particular | +0.009 |
date | +0.009 |
invite | +0.009 |
fill | +0.008 |
Neg logit contributions | |
w | -0.005 |
ich | -0.005 |
ller | -0.005 |
irens | -0.004 |
aged | -0.004 |
Token | Miss |
Token ID | 17140 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
fill | +0.012 |
invite | +0.012 |
offer | +0.012 |
Neg logit contributions | |
w | -0.009 |
ich | -0.008 |
RR | -0.007 |
irens | -0.007 |
ller | -0.007 |
Token | O |
Token ID | 440 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
w | +0.012 |
ich | +0.011 |
ller | +0.010 |
aged | +0.010 |
llers | +0.010 |
Neg logit contributions | |
agreement | -0.013 |
particular | -0.012 |
Everyday | -0.011 |
date | -0.011 |
invite | -0.011 |
Token | str |
Token ID | 2536 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.014 |
date | +0.014 |
Everyday | +0.013 |
invite | +0.013 |
Neg logit contributions | |
w | -0.006 |
nam | -0.005 |
ich | -0.005 |
elbows | -0.005 |
aged | -0.005 |
Token | ich |
Token ID | 488 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
nam | +0.066 |
elbows | +0.050 |
w | +0.050 |
satellites | +0.049 |
AAAA | +0.048 |
Neg logit contributions | |
Everyday | -0.097 |
agreement | -0.096 |
date | -0.094 |
ini | -0.093 |
particular | -0.093 |
Token | said |
Token ID | 531 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
agreement | +0.035 |
particular | +0.032 |
date | +0.031 |
Everyday | +0.029 |
offer | +0.029 |
Neg logit contributions | |
w | -0.023 |
ller | -0.020 |
ich | -0.019 |
aged | -0.018 |
llers | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +6.28e-03 |
Pos logit contributions | |
agreement | +0.055 |
particular | +0.052 |
Everyday | +0.049 |
date | +0.049 |
invite | +0.047 |
Neg logit contributions | |
w | -0.029 |
aged | -0.025 |
ller | -0.024 |
ich | -0.023 |
uts | -0.023 |
Token | � |
Token ID | 6184 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
date | +0.012 |
Everyday | +0.011 |
invite | +0.011 |
Neg logit contributions | |
w | -0.006 |
ller | -0.006 |
ich | -0.006 |
aged | -0.006 |
llers | -0.006 |
Token | � |
Token ID | 95 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
agreement | +0.018 |
particular | +0.016 |
Everyday | +0.015 |
date | +0.015 |
invite | +0.015 |
Neg logit contributions | |
w | -0.017 |
ich | -0.016 |
ller | -0.015 |
llers | -0.015 |
aged | -0.015 |
Token | explore |
Token ID | 7301 |
Feature activation | +6.71e-04 |
Pos logit contributions | |
agreement | +0.015 |
particular | +0.014 |
Everyday | +0.013 |
date | +0.013 |
invite | +0.012 |
Neg logit contributions | |
w | -0.021 |
ich | -0.020 |
ller | -0.019 |
aged | -0.019 |
llers | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -4.80e-03 |
Pos logit contributions | |
agreement | +0.001 |
particular | +0.001 |
Everyday | +0.001 |
date | +0.001 |
invite | +0.001 |
Neg logit contributions | |
w | -0.001 |
ich | -0.001 |
ller | -0.001 |
aged | -0.001 |
llers | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
w | +0.009 |
ich | +0.008 |
ller | +0.007 |
aged | +0.007 |
llers | +0.007 |
Neg logit contributions | |
agreement | -0.007 |
particular | -0.006 |
Everyday | -0.006 |
date | -0.006 |
invite | -0.006 |
Token | noticed |
Token ID | 6810 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
agreement | +0.008 |
date | +0.007 |
particular | +0.007 |
Everyday | +0.007 |
offer | +0.007 |
Neg logit contributions | |
w | -0.006 |
ich | -0.005 |
aged | -0.005 |
ller | -0.005 |
llers | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
w | +0.006 |
ich | +0.005 |
ller | +0.005 |
EEP | +0.005 |
aged | +0.005 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.004 |
Everyday | -0.004 |
date | -0.004 |
invite | -0.004 |
Token | old |
Token ID | 1468 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
w | +0.054 |
ich | +0.049 |
ller | +0.048 |
aged | +0.048 |
llers | +0.048 |
Neg logit contributions | |
agreement | -0.046 |
particular | -0.041 |
Everyday | -0.039 |
offer | -0.038 |
invite | -0.037 |
Token | chest |
Token ID | 7721 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
w | +0.128 |
inches | +0.120 |
ich | +0.117 |
irens | +0.114 |
llers | +0.114 |
Neg logit contributions | |
agreement | -0.068 |
particular | -0.060 |
offer | -0.060 |
Everyday | -0.057 |
fill | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
w | +0.018 |
reading | +0.017 |
aged | +0.017 |
ich | +0.017 |
crying | +0.017 |
Neg logit contributions | |
agreement | -0.033 |
date | -0.029 |
Everyday | -0.027 |
particular | -0.027 |
basis | -0.027 |
Token | kn |
Token ID | 638 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
w | +0.018 |
ich | +0.017 |
ller | +0.016 |
llers | +0.015 |
irens | +0.015 |
Neg logit contributions | |
agreement | -0.018 |
particular | -0.017 |
Everyday | -0.016 |
invite | -0.015 |
offer | -0.015 |
Token | elt |
Token ID | 2120 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
w | +0.027 |
AAAA | +0.025 |
RR | +0.024 |
rob | +0.023 |
ller | +0.022 |
Neg logit contributions | |
agreement | -0.039 |
Everyday | -0.039 |
sill | -0.039 |
fill | -0.037 |
date | -0.037 |
Token | down |
Token ID | 866 |
Feature activation | -5.81e-04 |
Pos logit contributions | |
w | +0.034 |
ich | +0.031 |
ller | +0.030 |
llers | +0.029 |
aged | +0.028 |
Neg logit contributions | |
agreement | -0.049 |
particular | -0.045 |
Everyday | -0.043 |
date | -0.042 |
invite | -0.042 |
Token | continued |
Token ID | 3767 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.015 |
date | +0.014 |
Everyday | +0.014 |
invite | +0.014 |
Neg logit contributions | |
w | -0.013 |
ich | -0.011 |
aged | -0.011 |
ller | -0.011 |
llers | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
w | +0.009 |
ich | +0.008 |
ller | +0.007 |
aged | +0.007 |
llers | +0.007 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.011 |
Everyday | -0.010 |
date | -0.010 |
invite | -0.010 |
Token | climb |
Token ID | 12080 |
Feature activation | -1.16e-03 |
Pos logit contributions | |
agreement | +0.028 |
particular | +0.026 |
date | +0.026 |
Everyday | +0.025 |
cloth | +0.023 |
Neg logit contributions | |
w | -0.025 |
ich | -0.022 |
ller | -0.022 |
llers | -0.021 |
aged | -0.020 |
Token | until |
Token ID | 1566 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
w | +0.002 |
ller | +0.001 |
ich | +0.001 |
irens | +0.001 |
llers | +0.001 |
Neg logit contributions | |
agreement | -0.002 |
date | -0.002 |
particular | -0.002 |
invite | -0.002 |
Everyday | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
agreement | +0.061 |
particular | +0.055 |
date | +0.055 |
Everyday | +0.053 |
invite | +0.053 |
Neg logit contributions | |
w | -0.035 |
ich | -0.030 |
ller | -0.030 |
llers | -0.029 |
irens | -0.029 |
Token | couldn |
Token ID | 3521 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.013 |
date | +0.012 |
Everyday | +0.012 |
invite | +0.011 |
Neg logit contributions | |
w | -0.013 |
ich | -0.012 |
ller | -0.011 |
aged | -0.011 |
llers | -0.011 |
Token | 't |
Token ID | 470 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
agreement | +0.095 |
particular | +0.084 |
date | +0.082 |
invite | +0.080 |
offer | +0.079 |
Neg logit contributions | |
w | -0.039 |
ller | -0.031 |
uts | -0.031 |
ich | -0.030 |
llers | -0.029 |
Token | climb |
Token ID | 12080 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
agreement | +0.020 |
particular | +0.018 |
date | +0.018 |
Everyday | +0.018 |
cloth | +0.016 |
Neg logit contributions | |
w | -0.021 |
ich | -0.020 |
ller | -0.019 |
uts | -0.018 |
llers | -0.018 |
Token | any |
Token ID | 597 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
agreement | +0.011 |
particular | +0.010 |
date | +0.010 |
invite | +0.010 |
Everyday | +0.010 |
Neg logit contributions | |
w | -0.010 |
ller | -0.009 |
ich | -0.009 |
llers | -0.009 |
irens | -0.008 |
Token | higher |
Token ID | 2440 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
agreement | +0.012 |
date | +0.011 |
Everyday | +0.011 |
particular | +0.010 |
invite | +0.010 |
Neg logit contributions | |
w | -0.011 |
ls | -0.009 |
ich | -0.009 |
irens | -0.009 |
elbows | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
w | +0.013 |
ich | +0.012 |
ller | +0.012 |
llers | +0.011 |
uts | +0.010 |
Neg logit contributions | |
agreement | -0.019 |
date | -0.017 |
invite | -0.016 |
Everyday | -0.016 |
particular | -0.016 |
Token | play |
Token ID | 711 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
rily | +0.024 |
agreement | +0.023 |
surely | +0.020 |
checkout | +0.019 |
refreshing | +0.019 |
Neg logit contributions | |
w | -0.020 |
Blood | -0.018 |
elbows | -0.018 |
reading | -0.017 |
crying | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
agreement | +0.030 |
particular | +0.028 |
Everyday | +0.028 |
offer | +0.025 |
invite | +0.025 |
Neg logit contributions | |
w | -0.019 |
ich | -0.017 |
aged | -0.016 |
RR | -0.015 |
elbows | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
agreement | +0.011 |
particular | +0.010 |
date | +0.010 |
Everyday | +0.010 |
invite | +0.009 |
Neg logit contributions | |
w | -0.009 |
ich | -0.009 |
ller | -0.008 |
llers | -0.008 |
irens | -0.008 |
Token | park |
Token ID | 3952 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
w | +0.002 |
ich | +0.002 |
irens | +0.002 |
ller | +0.002 |
llers | +0.002 |
Neg logit contributions | |
agreement | -0.002 |
particular | -0.002 |
Everyday | -0.002 |
date | -0.002 |
invite | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.014 |
Everyday | +0.014 |
date | +0.014 |
latable | +0.013 |
Neg logit contributions | |
w | -0.009 |
ich | -0.008 |
reading | -0.008 |
aged | -0.007 |
uts | -0.007 |
Token | One |
Token ID | 1881 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
agreement | +0.022 |
date | +0.020 |
particular | +0.018 |
offer | +0.018 |
invite | +0.018 |
Neg logit contributions | |
w | -0.025 |
llers | -0.023 |
Blood | -0.023 |
ller | -0.023 |
RR | -0.023 |
Token | day |
Token ID | 1110 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
agreement | +0.059 |
date | +0.050 |
rily | +0.049 |
Everyday | +0.045 |
invite | +0.045 |
Neg logit contributions | |
w | -0.068 |
ich | -0.058 |
EEP | -0.054 |
Blood | -0.054 |
aged | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
ich | +0.038 |
ller | +0.038 |
llers | +0.037 |
w | +0.036 |
elbows | +0.035 |
Neg logit contributions | |
particular | -0.022 |
agreement | -0.019 |
Everyday | -0.018 |
of | -0.018 |
invite | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
agreement | +0.005 |
particular | +0.005 |
Everyday | +0.005 |
date | +0.005 |
invite | +0.005 |
Neg logit contributions | |
w | -0.004 |
ich | -0.004 |
ller | -0.004 |
llers | -0.004 |
aged | -0.004 |
Token | see |
Token ID | 766 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
agreement | +0.019 |
particular | +0.017 |
Everyday | +0.017 |
date | +0.017 |
rily | +0.016 |
Neg logit contributions | |
w | -0.014 |
ich | -0.011 |
AAAA | -0.011 |
nam | -0.011 |
Blood | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
w | +0.003 |
ller | +0.002 |
ich | +0.002 |
llers | +0.002 |
aged | +0.002 |
Neg logit contributions | |
agreement | -0.003 |
particular | -0.003 |
Everyday | -0.002 |
invite | -0.002 |
date | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
agreement | +0.051 |
particular | +0.048 |
date | +0.046 |
Everyday | +0.043 |
invite | +0.041 |
Neg logit contributions | |
w | -0.037 |
aged | -0.034 |
ller | -0.032 |
ich | -0.030 |
llers | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
w | +0.007 |
ich | +0.006 |
ller | +0.006 |
aged | +0.006 |
llers | +0.006 |
Neg logit contributions | |
agreement | -0.007 |
particular | -0.006 |
Everyday | -0.006 |
date | -0.006 |
invite | -0.005 |
Token | frog |
Token ID | 21264 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
agreement | +0.031 |
date | +0.028 |
particular | +0.028 |
basis | +0.027 |
Everyday | +0.027 |
Neg logit contributions | |
w | -0.030 |
ich | -0.027 |
crying | -0.025 |
Blood | -0.024 |
bleeding | -0.024 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
agreement | +0.023 |
particular | +0.022 |
date | +0.021 |
Everyday | +0.020 |
basis | +0.019 |
Neg logit contributions | |
w | -0.017 |
aged | -0.016 |
ich | -0.014 |
awed | -0.014 |
ged | -0.013 |
Token | together |
Token ID | 1978 |
Feature activation | +7.51e-03 |
Pos logit contributions | |
w | +0.001 |
aged | +0.001 |
ller | +0.001 |
irens | +0.001 |
llers | +0.001 |
Neg logit contributions | |
agreement | -0.003 |
particular | -0.003 |
date | -0.003 |
invite | -0.003 |
Everyday | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.014 |
date | +0.014 |
Everyday | +0.014 |
invite | +0.014 |
Neg logit contributions | |
aged | -0.007 |
w | -0.007 |
uts | -0.006 |
pressing | -0.006 |
ged | -0.006 |
Token | clean |
Token ID | 3424 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
agreement | +0.056 |
date | +0.053 |
particular | +0.051 |
Everyday | +0.051 |
eater | +0.049 |
Neg logit contributions | |
w | -0.045 |
aged | -0.043 |
icken | -0.043 |
ich | -0.042 |
whist | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
agreement | +0.018 |
date | +0.018 |
particular | +0.017 |
invite | +0.017 |
Everyday | +0.017 |
Neg logit contributions | |
w | -0.009 |
ller | -0.008 |
aged | -0.008 |
icken | -0.008 |
llers | -0.008 |
Token | pond |
Token ID | 16723 |
Feature activation | +8.16e-03 |
Pos logit contributions | |
particular | +0.018 |
agreement | +0.017 |
date | +0.017 |
Everyday | +0.016 |
Whenever | +0.015 |
Neg logit contributions | |
w | -0.017 |
ich | -0.017 |
bleeding | -0.015 |
crying | -0.015 |
ller | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.015 |
date | +0.015 |
Everyday | +0.014 |
invite | +0.014 |
Neg logit contributions | |
aged | -0.009 |
w | -0.008 |
ages | -0.007 |
uts | -0.007 |
icken | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
agreement | +0.019 |
particular | +0.018 |
date | +0.018 |
offer | +0.017 |
invite | +0.017 |
Neg logit contributions | |
Blood | -0.010 |
aged | -0.010 |
llers | -0.010 |
ller | -0.010 |
uts | -0.010 |
Token | some |
Token ID | 617 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
agreement | +0.006 |
particular | +0.005 |
date | +0.005 |
Everyday | +0.005 |
offer | +0.005 |
Neg logit contributions | |
w | -0.003 |
aged | -0.003 |
ich | -0.003 |
llers | -0.003 |
Blood | -0.003 |
Token | special |
Token ID | 2041 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
agreement | +0.050 |
date | +0.048 |
surely | +0.045 |
particular | +0.044 |
basis | +0.042 |
Neg logit contributions | |
w | -0.038 |
bleeding | -0.034 |
blood | -0.032 |
bruises | -0.030 |
aged | -0.030 |
Token | plants |
Token ID | 6134 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
agreement | +0.021 |
surely | +0.019 |
particular | +0.019 |
date | +0.019 |
Everyday | +0.019 |
Neg logit contributions | |
w | -0.019 |
aged | -0.016 |
elbows | -0.015 |
inches | -0.015 |
bleeding | -0.015 |
Token | growing |
Token ID | 3957 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
agreement | +0.024 |
particular | +0.021 |
date | +0.020 |
Everyday | +0.019 |
ainer | +0.019 |
Neg logit contributions | |
w | -0.012 |
uts | -0.011 |
crying | -0.010 |
aged | -0.010 |
ich | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
agreement | +0.043 |
date | +0.038 |
invite | +0.037 |
particular | +0.036 |
Everyday | +0.035 |
Neg logit contributions | |
w | -0.019 |
ls | -0.015 |
aged | -0.013 |
uts | -0.013 |
ing | -0.013 |
Token | his |
Token ID | 465 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
agreement | +0.083 |
date | +0.081 |
invite | +0.079 |
rene | +0.075 |
host | +0.073 |
Neg logit contributions | |
w | -0.027 |
RR | -0.024 |
icken | -0.023 |
yourselves | -0.021 |
touching | -0.021 |
Token | body |
Token ID | 1767 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
agreement | +0.062 |
Everyday | +0.061 |
date | +0.060 |
particular | +0.057 |
rene | +0.054 |
Neg logit contributions | |
ich | -0.049 |
elbows | -0.043 |
w | -0.041 |
bleeding | -0.040 |
crying | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
agreement | +0.032 |
particular | +0.029 |
invite | +0.026 |
date | +0.026 |
Everyday | +0.026 |
Neg logit contributions | |
uts | -0.018 |
w | -0.018 |
ich | -0.016 |
ages | -0.015 |
aged | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
agreement | +0.032 |
particular | +0.031 |
date | +0.029 |
invite | +0.028 |
offer | +0.027 |
Neg logit contributions | |
w | -0.024 |
ller | -0.023 |
ich | -0.023 |
llers | -0.022 |
RR | -0.022 |
Token | took |
Token ID | 1718 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
w | +0.002 |
ller | +0.002 |
ich | +0.002 |
aged | +0.002 |
llers | +0.002 |
Neg logit contributions | |
agreement | -0.003 |
particular | -0.002 |
date | -0.002 |
Everyday | -0.002 |
offer | -0.002 |
Token | out |
Token ID | 503 |
Feature activation | +3.65e-04 |
Pos logit contributions | |
agreement | +0.021 |
particular | +0.019 |
date | +0.018 |
Everyday | +0.018 |
invite | +0.018 |
Neg logit contributions | |
w | -0.011 |
aged | -0.008 |
irens | -0.008 |
Blood | -0.007 |
Pur | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
date | +0.045 |
agreement | +0.041 |
surely | +0.040 |
invite | +0.040 |
particular | +0.040 |
Neg logit contributions | |
flashing | -0.016 |
nam | -0.015 |
pressing | -0.015 |
fighting | -0.014 |
crying | -0.014 |
Token | qualities |
Token ID | 14482 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
date | +0.023 |
agreement | +0.022 |
Everyday | +0.022 |
particular | +0.022 |
iona | +0.020 |
Neg logit contributions | |
reading | -0.017 |
crying | -0.016 |
aged | -0.016 |
ller | -0.016 |
praying | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
agreement | +0.011 |
date | +0.010 |
particular | +0.010 |
invite | +0.009 |
ainer | +0.009 |
Neg logit contributions | |
uts | -0.005 |
w | -0.005 |
flashing | -0.005 |
ller | -0.005 |
crying | -0.005 |
Token | skill |
Token ID | 5032 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
w | +0.014 |
aged | +0.014 |
llers | +0.013 |
ller | +0.013 |
nam | +0.013 |
Neg logit contributions | |
agreement | -0.022 |
particular | -0.020 |
date | -0.020 |
Everyday | -0.019 |
latable | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
w | +0.017 |
ich | +0.015 |
aged | +0.015 |
ller | +0.015 |
llers | +0.015 |
Neg logit contributions | |
agreement | -0.020 |
particular | -0.019 |
date | -0.018 |
Everyday | -0.018 |
invite | -0.017 |
Token | M |
Token ID | 337 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
agreement | +0.024 |
particular | +0.021 |
date | +0.021 |
offer | +0.021 |
invite | +0.020 |
Neg logit contributions | |
w | -0.013 |
Blood | -0.013 |
llers | -0.013 |
ich | -0.013 |
aged | -0.012 |
Token | illy |
Token ID | 6548 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
agreement | +0.059 |
date | +0.052 |
particular | +0.052 |
invite | +0.049 |
fill | +0.048 |
Neg logit contributions | |
w | -0.065 |
ich | -0.061 |
ller | -0.057 |
llers | -0.056 |
aged | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
agreement | +0.013 |
particular | +0.012 |
date | +0.011 |
Everyday | +0.011 |
offer | +0.010 |
Neg logit contributions | |
w | -0.009 |
ller | -0.008 |
aged | -0.008 |
ich | -0.008 |
llers | -0.008 |
Token | so |
Token ID | 523 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
agreement | +0.009 |
particular | +0.009 |
date | +0.008 |
offer | +0.008 |
Everyday | +0.008 |
Neg logit contributions | |
aged | -0.006 |
reading | -0.006 |
ich | -0.005 |
pressing | -0.005 |
crying | -0.005 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
w | +0.006 |
aged | +0.006 |
ich | +0.006 |
ller | +0.005 |
llers | +0.005 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.010 |
date | -0.010 |
Everyday | -0.009 |
invite | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
w | +0.029 |
ich | +0.027 |
ller | +0.026 |
llers | +0.025 |
aged | +0.025 |
Neg logit contributions | |
agreement | -0.039 |
particular | -0.036 |
date | -0.034 |
Everyday | -0.034 |
invite | -0.033 |
Token | € |
Token ID | 26391 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
agreement | +0.035 |
particular | +0.032 |
Everyday | +0.030 |
date | +0.030 |
invite | +0.029 |
Neg logit contributions | |
w | -0.040 |
ich | -0.035 |
ller | -0.034 |
aged | -0.034 |
llers | -0.034 |
Token | � |
Token ID | 447 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
w | +0.013 |
ich | +0.011 |
ller | +0.011 |
nam | +0.011 |
aged | +0.011 |
Neg logit contributions | |
agreement | -0.016 |
date | -0.015 |
particular | -0.015 |
Everyday | -0.015 |
invite | -0.015 |
Token | � |
Token ID | 251 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
agreement | +0.008 |
particular | +0.007 |
Everyday | +0.006 |
date | +0.006 |
invite | +0.005 |
Neg logit contributions | |
w | -0.019 |
ich | -0.018 |
ller | -0.018 |
aged | -0.018 |
llers | -0.017 |
Token | sw |
Token ID | 2032 |
Feature activation | +8.86e-03 |
Pos logit contributions | |
agreement | +0.049 |
particular | +0.046 |
date | +0.043 |
invite | +0.042 |
fill | +0.042 |
Neg logit contributions | |
w | -0.031 |
irens | -0.027 |
aged | -0.026 |
Pur | -0.026 |
Hel | -0.025 |
Token | imming |
Token ID | 27428 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.015 |
invite | +0.014 |
date | +0.014 |
Everyday | +0.014 |
Neg logit contributions | |
w | -0.012 |
ich | -0.011 |
ller | -0.011 |
llers | -0.010 |
aged | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
agreement | +0.014 |
date | +0.014 |
particular | +0.013 |
invite | +0.013 |
Everyday | +0.013 |
Neg logit contributions | |
w | -0.011 |
aged | -0.010 |
ged | -0.008 |
irens | -0.008 |
awed | -0.008 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
agreement | +0.017 |
date | +0.017 |
particular | +0.017 |
Everyday | +0.015 |
offer | +0.015 |
Neg logit contributions | |
w | -0.012 |
ich | -0.012 |
ller | -0.012 |
aged | -0.011 |
llers | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e-03 |
Pos logit contributions | |
particular | +0.019 |
Everyday | +0.018 |
agreement | +0.018 |
invite | +0.017 |
surely | +0.017 |
Neg logit contributions | |
w | -0.011 |
aged | -0.010 |
RR | -0.009 |
AAAA | -0.009 |
icken | -0.009 |
Token | making |
Token ID | 1642 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
w | +0.003 |
ich | +0.003 |
aged | +0.003 |
llers | +0.003 |
ller | +0.003 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.006 |
date | -0.006 |
Everyday | -0.006 |
offer | -0.005 |
Token | lots |
Token ID | 6041 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
agreement | +0.035 |
particular | +0.034 |
date | +0.032 |
Everyday | +0.032 |
surely | +0.030 |
Neg logit contributions | |
w | -0.023 |
aged | -0.021 |
ich | -0.020 |
llers | -0.020 |
ller | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
agreement | +0.026 |
date | +0.023 |
particular | +0.022 |
surely | +0.022 |
Everyday | +0.020 |
Neg logit contributions | |
uts | -0.033 |
irens | -0.033 |
w | -0.033 |
ller | -0.032 |
ouncing | -0.032 |
Token | dad |
Token ID | 9955 |
Feature activation | -7.10e-03 |
Pos logit contributions | |
w | +0.021 |
ller | +0.019 |
llers | +0.018 |
ich | +0.018 |
irens | +0.018 |
Neg logit contributions | |
agreement | -0.020 |
particular | -0.018 |
invite | -0.017 |
fill | -0.016 |
offer | -0.016 |
Token | give |
Token ID | 1577 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
w | +0.011 |
fighting | +0.009 |
inches | +0.009 |
aged | +0.009 |
reading | +0.009 |
Neg logit contributions | |
particular | -0.010 |
agreement | -0.010 |
date | -0.010 |
Everyday | -0.009 |
basis | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
agreement | +0.022 |
particular | +0.021 |
date | +0.020 |
Everyday | +0.020 |
basis | +0.019 |
Neg logit contributions | |
w | -0.020 |
aged | -0.017 |
inches | -0.016 |
irens | -0.016 |
ich | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
agreement | +0.041 |
particular | +0.039 |
date | +0.039 |
Everyday | +0.037 |
surely | +0.035 |
Neg logit contributions | |
w | -0.020 |
nam | -0.016 |
aged | -0.015 |
ich | -0.015 |
irens | -0.015 |
Token | net |
Token ID | 2010 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
agreement | +0.018 |
Everyday | +0.017 |
date | +0.017 |
particular | +0.016 |
Whenever | +0.016 |
Neg logit contributions | |
w | -0.016 |
ich | -0.014 |
inches | -0.013 |
AAAA | -0.013 |
Blood | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
agreement | +0.044 |
particular | +0.041 |
date | +0.039 |
Everyday | +0.039 |
rene | +0.037 |
Neg logit contributions | |
uts | -0.018 |
w | -0.017 |
ages | -0.015 |
inches | -0.014 |
aged | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
agreement | +0.007 |
date | +0.007 |
particular | +0.007 |
Everyday | +0.006 |
basis | +0.006 |
Neg logit contributions | |
w | -0.004 |
inches | -0.003 |
nam | -0.003 |
aged | -0.003 |
destruct | -0.003 |
Token | bucket |
Token ID | 19236 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
agreement | +0.009 |
Everyday | +0.009 |
particular | +0.009 |
date | +0.008 |
Whenever | +0.008 |
Neg logit contributions | |
w | -0.008 |
ich | -0.007 |
AAAA | -0.006 |
nam | -0.006 |
inches | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
agreement | +0.030 |
date | +0.029 |
particular | +0.028 |
basis | +0.026 |
Everyday | +0.025 |
Neg logit contributions | |
uts | -0.016 |
w | -0.015 |
inches | -0.014 |
aged | -0.014 |
ages | -0.012 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.96e-03 |
Pos logit contributions | |
agreement | +0.045 |
date | +0.044 |
particular | +0.042 |
surely | +0.039 |
basis | +0.038 |
Neg logit contributions | |
irens | -0.020 |
Blood | -0.020 |
uts | -0.019 |
inches | -0.019 |
AAAA | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
agreement | +0.005 |
date | +0.005 |
particular | +0.005 |
Everyday | +0.004 |
invite | +0.004 |
Neg logit contributions | |
w | -0.004 |
inches | -0.004 |
ich | -0.004 |
aged | -0.004 |
ller | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
agreement | +0.044 |
particular | +0.041 |
Everyday | +0.040 |
date | +0.039 |
invite | +0.037 |
Neg logit contributions | |
w | -0.029 |
ich | -0.024 |
aged | -0.024 |
ller | -0.023 |
EEP | -0.023 |
Token | you |
Token ID | 345 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
agreement | +0.029 |
date | +0.028 |
particular | +0.027 |
Everyday | +0.026 |
rene | +0.025 |
Neg logit contributions | |
w | -0.010 |
accidents | -0.007 |
ich | -0.007 |
fighting | -0.006 |
EEP | -0.006 |
Token | can |
Token ID | 460 |
Feature activation | +7.74e-03 |
Pos logit contributions | |
agreement | +0.012 |
particular | +0.011 |
date | +0.010 |
Everyday | +0.009 |
rily | +0.009 |
Neg logit contributions | |
w | -0.016 |
EEP | -0.013 |
aged | -0.013 |
RR | -0.012 |
ller | -0.012 |
Token | borrow |
Token ID | 8804 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
agreement | +0.012 |
particular | +0.011 |
refreshing | +0.010 |
igator | +0.010 |
rily | +0.010 |
Neg logit contributions | |
w | -0.012 |
ller | -0.010 |
llers | -0.010 |
ich | -0.010 |
uts | -0.010 |
Token | one |
Token ID | 530 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
agreement | +0.027 |
particular | +0.025 |
date | +0.024 |
Everyday | +0.024 |
invite | +0.023 |
Neg logit contributions | |
w | -0.017 |
ller | -0.015 |
ich | -0.015 |
llers | -0.014 |
irens | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
agreement | +0.043 |
Everyday | +0.038 |
date | +0.036 |
rene | +0.036 |
latable | +0.035 |
Neg logit contributions | |
w | -0.033 |
ich | -0.030 |
ller | -0.026 |
enn | -0.025 |
bleeding | -0.024 |
Token | Here |
Token ID | 3423 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
agreement | +0.017 |
particular | +0.016 |
date | +0.016 |
fill | +0.014 |
offer | +0.014 |
Neg logit contributions | |
w | -0.010 |
ller | -0.010 |
Pur | -0.009 |
llers | -0.009 |
EEP | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-03 |
Pos logit contributions | |
agreement | +0.032 |
particular | +0.030 |
date | +0.029 |
Everyday | +0.028 |
invite | +0.026 |
Neg logit contributions | |
w | -0.019 |
ich | -0.015 |
ller | -0.014 |
aged | -0.014 |
inches | -0.013 |
Token | take |
Token ID | 1011 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
w | +0.003 |
nam | +0.003 |
destruct | +0.003 |
Pur | +0.002 |
ich | +0.002 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.004 |
date | -0.004 |
Everyday | -0.004 |
latable | -0.004 |
Token | this |
Token ID | 428 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
agreement | +0.009 |
particular | +0.008 |
date | +0.008 |
Everyday | +0.008 |
invite | +0.008 |
Neg logit contributions | |
w | -0.006 |
aged | -0.004 |
irens | -0.004 |
ller | -0.004 |
ich | -0.004 |
Token | one |
Token ID | 530 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
agreement | +0.013 |
Everyday | +0.012 |
particular | +0.012 |
date | +0.011 |
Whenever | +0.011 |
Neg logit contributions | |
w | -0.008 |
ich | -0.008 |
ller | -0.007 |
aged | -0.007 |
bleeding | -0.007 |
Token | Their |
Token ID | 14574 |
Feature activation | +8.37e-03 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.013 |
Everyday | +0.012 |
date | +0.012 |
invite | +0.012 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.010 |
llers | -0.010 |
aged | -0.009 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.013 |
date | +0.012 |
Everyday | +0.012 |
invite | +0.012 |
Neg logit contributions | |
w | -0.012 |
ich | -0.011 |
ller | -0.011 |
aged | -0.011 |
llers | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
agreement | +0.008 |
particular | +0.008 |
date | +0.007 |
Everyday | +0.007 |
invite | +0.007 |
Neg logit contributions | |
w | -0.008 |
ich | -0.008 |
ller | -0.008 |
aged | -0.007 |
llers | -0.007 |
Token | dad |
Token ID | 9955 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.003 |
Everyday | +0.003 |
date | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
aged | -0.002 |
llers | -0.002 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
w | +0.016 |
ich | +0.014 |
ller | +0.014 |
aged | +0.013 |
llers | +0.013 |
Neg logit contributions | |
agreement | -0.018 |
particular | -0.016 |
Everyday | -0.015 |
date | -0.015 |
invite | -0.015 |
Token | at |
Token ID | 379 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
w | +0.013 |
ich | +0.011 |
aged | +0.011 |
ller | +0.011 |
inches | +0.011 |
Neg logit contributions | |
agreement | -0.022 |
particular | -0.021 |
date | -0.020 |
Everyday | -0.020 |
invite | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | -3.60e-04 |
Pos logit contributions | |
date | +0.058 |
agreement | +0.057 |
particular | +0.056 |
invite | +0.055 |
Everyday | +0.054 |
Neg logit contributions | |
w | -0.036 |
irens | -0.032 |
ich | -0.031 |
aged | -0.031 |
llers | -0.031 |
Token | with |
Token ID | 351 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
crying | +0.000 |
aged | +0.000 |
bleeding | +0.000 |
fighting | +0.000 |
reading | +0.000 |
Neg logit contributions | |
particular | -0.001 |
date | -0.001 |
agreement | -0.001 |
invite | -0.001 |
Everyday | -0.001 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
date | +0.019 |
particular | +0.018 |
agreement | +0.018 |
Everyday | +0.017 |
iona | +0.017 |
Neg logit contributions | |
elbows | -0.009 |
bleeding | -0.009 |
flashing | -0.009 |
w | -0.009 |
blood | -0.009 |
Token | eyes |
Token ID | 2951 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
w | +0.011 |
aged | +0.010 |
irens | +0.009 |
ller | +0.009 |
ich | +0.009 |
Neg logit contributions | |
agreement | -0.023 |
particular | -0.023 |
date | -0.022 |
Everyday | -0.022 |
invite | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
agreement | +0.049 |
date | +0.049 |
particular | +0.048 |
iona | +0.045 |
invite | +0.045 |
Neg logit contributions | |
aged | -0.026 |
uts | -0.026 |
bleeding | -0.026 |
w | -0.026 |
ller | -0.024 |
Token | have |
Token ID | 423 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
w | +0.009 |
ich | +0.008 |
crying | +0.008 |
llers | +0.008 |
ller | +0.008 |
Neg logit contributions | |
agreement | -0.007 |
particular | -0.007 |
Everyday | -0.007 |
rily | -0.006 |
date | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
agreement | +0.029 |
particular | +0.026 |
surely | +0.024 |
Everyday | +0.024 |
ainer | +0.023 |
Neg logit contributions | |
w | -0.012 |
uts | -0.011 |
reading | -0.010 |
happened | -0.010 |
icken | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
agreement | +0.060 |
date | +0.059 |
rily | +0.057 |
surely | +0.054 |
host | +0.053 |
Neg logit contributions | |
EEP | -0.037 |
llers | -0.036 |
irens | -0.035 |
ller | -0.034 |
Blood | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
agreement | +0.035 |
date | +0.031 |
ainer | +0.030 |
particular | +0.029 |
rily | +0.029 |
Neg logit contributions | |
w | -0.016 |
tri | -0.013 |
ller | -0.013 |
screamed | -0.013 |
happened | -0.013 |
Token | very |
Token ID | 845 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
agreement | +0.015 |
date | +0.013 |
particular | +0.013 |
basis | +0.013 |
offer | +0.013 |
Neg logit contributions | |
reading | -0.008 |
crying | -0.008 |
praying | -0.007 |
ich | -0.007 |
nam | -0.007 |
Token | loyal |
Token ID | 9112 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
agreement | +0.022 |
date | +0.021 |
Everyday | +0.020 |
particular | +0.019 |
basis | +0.019 |
Neg logit contributions | |
w | -0.013 |
aged | -0.011 |
ich | -0.011 |
nam | -0.011 |
Blood | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
particular | +0.011 |
agreement | +0.011 |
surely | +0.010 |
date | +0.010 |
Everyday | +0.010 |
Neg logit contributions | |
uts | -0.004 |
aged | -0.003 |
ich | -0.003 |
w | -0.003 |
crying | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
agreement | +0.024 |
particular | +0.021 |
date | +0.020 |
Everyday | +0.019 |
date | +0.018 |
Neg logit contributions | |
w | -0.019 |
aged | -0.017 |
nam | -0.016 |
ages | -0.016 |
ller | -0.016 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
w | +0.019 |
aged | +0.017 |
ich | +0.016 |
ller | +0.016 |
llers | +0.016 |
Neg logit contributions | |
agreement | -0.021 |
particular | -0.020 |
Everyday | -0.019 |
date | -0.019 |
invite | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
agreement | +0.029 |
particular | +0.026 |
Everyday | +0.026 |
date | +0.024 |
surely | +0.024 |
Neg logit contributions | |
w | -0.019 |
aged | -0.017 |
irens | -0.016 |
ich | -0.016 |
llers | -0.016 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.79e-03 |
Pos logit contributions | |
agreement | +0.042 |
rant | +0.040 |
particular | +0.039 |
Everyday | +0.039 |
iona | +0.038 |
Neg logit contributions | |
ich | -0.018 |
aged | -0.017 |
w | -0.016 |
ller | -0.015 |
ages | -0.015 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
w | +0.005 |
ller | +0.004 |
aged | +0.004 |
ich | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.008 |
particular | -0.007 |
date | -0.007 |
Everyday | -0.007 |
invite | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
w | +0.025 |
ich | +0.024 |
ller | +0.022 |
aged | +0.022 |
irens | +0.022 |
Neg logit contributions | |
agreement | -0.020 |
particular | -0.019 |
Everyday | -0.018 |
invite | -0.017 |
fill | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
w | +0.009 |
ich | +0.008 |
ller | +0.008 |
uts | +0.008 |
aged | +0.008 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.011 |
Everyday | -0.011 |
date | -0.011 |
invite | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
w | +0.022 |
ich | +0.021 |
ller | +0.020 |
llers | +0.019 |
irens | +0.019 |
Neg logit contributions | |
agreement | -0.020 |
particular | -0.018 |
Everyday | -0.017 |
invite | -0.017 |
date | -0.017 |
Token | something |
Token ID | 1223 |
Feature activation | -3.67e-04 |
Pos logit contributions | |
w | +0.010 |
ich | +0.009 |
ller | +0.008 |
aged | +0.008 |
llers | +0.008 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.011 |
Everyday | -0.010 |
date | -0.010 |
invite | -0.010 |
Token | new |
Token ID | 649 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
w | +0.000 |
ich | +0.000 |
ller | +0.000 |
flashing | +0.000 |
crying | +0.000 |
Neg logit contributions | |
agreement | -0.001 |
Everyday | -0.001 |
date | -0.001 |
particular | -0.001 |
basis | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e-03 |
Pos logit contributions | |
w | +0.024 |
ich | +0.023 |
ller | +0.022 |
uts | +0.021 |
aged | +0.020 |
Neg logit contributions | |
agreement | -0.039 |
particular | -0.034 |
Everyday | -0.034 |
date | -0.033 |
invite | -0.032 |
Token | amazing |
Token ID | 4998 |
Feature activation | -7.20e-03 |
Pos logit contributions | |
w | +0.003 |
nam | +0.003 |
ller | +0.003 |
ich | +0.003 |
aged | +0.003 |
Neg logit contributions | |
agreement | -0.004 |
date | -0.003 |
particular | -0.003 |
Everyday | -0.003 |
invite | -0.003 |
Token | each |
Token ID | 1123 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
w | +0.009 |
ller | +0.008 |
ich | +0.008 |
aged | +0.008 |
llers | +0.008 |
Neg logit contributions | |
agreement | -0.014 |
Everyday | -0.012 |
particular | -0.012 |
date | -0.012 |
invite | -0.011 |
Token | time |
Token ID | 640 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
agreement | +0.006 |
Everyday | +0.005 |
latable | +0.005 |
date | +0.005 |
rightful | +0.005 |
Neg logit contributions | |
w | -0.006 |
pressing | -0.005 |
happened | -0.004 |
crying | -0.004 |
touching | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
w | +0.020 |
ich | +0.018 |
ller | +0.018 |
aged | +0.017 |
llers | +0.017 |
Neg logit contributions | |
agreement | -0.025 |
particular | -0.023 |
Everyday | -0.022 |
date | -0.022 |
invite | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
agreement | +0.033 |
date | +0.032 |
particular | +0.032 |
Everyday | +0.030 |
invite | +0.029 |
Neg logit contributions | |
ller | -0.016 |
w | -0.016 |
uts | -0.015 |
aged | -0.015 |
llers | -0.015 |
Token | John |
Token ID | 1757 |
Feature activation | +2.17e-04 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.003 |
date | +0.003 |
Everyday | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.002 |
ller | -0.002 |
llers | -0.002 |
aged | -0.002 |
ich | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
agreement | +0.000 |
particular | +0.000 |
date | +0.000 |
Everyday | +0.000 |
latable | +0.000 |
Neg logit contributions | |
aged | -0.000 |
crying | -0.000 |
ller | -0.000 |
w | -0.000 |
reading | -0.000 |
Token | When |
Token ID | 1649 |
Feature activation | -9.15e-03 |
Pos logit contributions | |
w | +0.011 |
ich | +0.010 |
aged | +0.009 |
ller | +0.009 |
inches | +0.009 |
Neg logit contributions | |
agreement | -0.009 |
Everyday | -0.008 |
particular | -0.008 |
date | -0.007 |
invite | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
w | +0.013 |
ich | +0.012 |
ller | +0.011 |
aged | +0.011 |
llers | +0.011 |
Neg logit contributions | |
agreement | -0.016 |
particular | -0.015 |
Everyday | -0.014 |
date | -0.014 |
invite | -0.014 |
Token | heard |
Token ID | 2982 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
agreement | +0.010 |
particular | +0.009 |
date | +0.009 |
Everyday | +0.008 |
offer | +0.008 |
Neg logit contributions | |
w | -0.009 |
ich | -0.007 |
aged | -0.007 |
ller | -0.007 |
RR | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
w | +0.012 |
ich | +0.010 |
ller | +0.010 |
aged | +0.010 |
llers | +0.010 |
Neg logit contributions | |
agreement | -0.015 |
particular | -0.014 |
Everyday | -0.013 |
date | -0.013 |
invite | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | -3.36e-03 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.003 |
date | +0.003 |
Everyday | +0.003 |
invite | +0.003 |
Neg logit contributions | |
w | -0.003 |
ich | -0.003 |
ller | -0.003 |
aged | -0.003 |
llers | -0.003 |
Token | cheered |
Token ID | 34767 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
w | +0.005 |
ich | +0.004 |
ller | +0.004 |
aged | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.005 |
date | -0.005 |
Everyday | -0.005 |
offer | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
w | +0.004 |
ller | +0.004 |
ich | +0.004 |
aged | +0.004 |
llers | +0.004 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.005 |
Everyday | -0.005 |
date | -0.005 |
invite | -0.005 |
Token | But |
Token ID | 887 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
w | +0.010 |
ich | +0.009 |
aged | +0.008 |
elbows | +0.008 |
inches | +0.008 |
Neg logit contributions | |
agreement | -0.007 |
Everyday | -0.007 |
particular | -0.007 |
date | -0.006 |
invite | -0.006 |
Token | One |
Token ID | 1881 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
agreement | +0.016 |
date | +0.014 |
particular | +0.013 |
invite | +0.013 |
offer | +0.013 |
Neg logit contributions | |
w | -0.016 |
Blood | -0.015 |
llers | -0.015 |
ich | -0.015 |
ller | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
agreement | +0.038 |
particular | +0.031 |
Everyday | +0.030 |
date | +0.030 |
invite | +0.029 |
Neg logit contributions | |
w | -0.066 |
ich | -0.061 |
ller | -0.058 |
aged | -0.058 |
llers | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ich | +0.030 |
ller | +0.030 |
llers | +0.028 |
w | +0.028 |
irens | +0.027 |
Neg logit contributions | |
particular | -0.016 |
agreement | -0.016 |
date | -0.015 |
Everyday | -0.014 |
fill | -0.013 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
agreement | +0.019 |
particular | +0.017 |
Everyday | +0.016 |
date | +0.016 |
invite | +0.016 |
Neg logit contributions | |
w | -0.018 |
ich | -0.016 |
ller | -0.016 |
aged | -0.015 |
llers | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
agreement | +0.006 |
particular | +0.005 |
date | +0.005 |
Everyday | +0.005 |
offer | +0.005 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
aged | -0.003 |
ller | -0.003 |
llers | -0.003 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.76e-03 |
Pos logit contributions | |
w | +0.003 |
ller | +0.003 |
ich | +0.003 |
llers | +0.003 |
RR | +0.003 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.005 |
date | -0.005 |
invite | -0.005 |
Everyday | -0.005 |
Token | dolls |
Token ID | 36062 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
w | +0.004 |
ich | +0.004 |
ller | +0.004 |
aged | +0.004 |
llers | +0.003 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.004 |
Everyday | -0.004 |
date | -0.004 |
invite | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
agreement | +0.002 |
particular | +0.002 |
Everyday | +0.002 |
date | +0.002 |
invite | +0.002 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
aged | -0.002 |
llers | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
w | +0.003 |
nam | +0.002 |
irens | +0.002 |
ich | +0.002 |
llers | +0.002 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.004 |
Everyday | -0.004 |
offer | -0.004 |
date | -0.004 |
Token | friend |
Token ID | 1545 |
Feature activation | -3.53e-04 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
Everyday | +0.003 |
date | +0.003 |
offer | +0.003 |
Neg logit contributions | |
w | -0.002 |
ich | -0.001 |
ller | -0.001 |
aged | -0.001 |
llers | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
w | +0.000 |
ich | +0.000 |
aged | +0.000 |
ller | +0.000 |
llers | +0.000 |
Neg logit contributions | |
agreement | -0.001 |
particular | -0.001 |
Everyday | -0.001 |
offer | -0.001 |
date | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | -2.91e-03 |
Pos logit contributions | |
w | +0.018 |
ich | +0.016 |
ller | +0.016 |
llers | +0.015 |
aged | +0.015 |
Neg logit contributions | |
agreement | -0.018 |
particular | -0.016 |
date | -0.016 |
Everyday | -0.015 |
invite | -0.015 |
Token | okay |
Token ID | 8788 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
w | +0.004 |
ich | +0.003 |
ller | +0.003 |
aged | +0.003 |
llers | +0.003 |
Neg logit contributions | |
agreement | -0.005 |
particular | -0.005 |
date | -0.005 |
Everyday | -0.005 |
invite | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
w | +0.033 |
ich | +0.030 |
ller | +0.029 |
aged | +0.028 |
llers | +0.028 |
Neg logit contributions | |
agreement | -0.030 |
particular | -0.027 |
Everyday | -0.026 |
date | -0.026 |
invite | -0.025 |
Token | We |
Token ID | 775 |
Feature activation | -2.88e-04 |
Pos logit contributions | |
agreement | +0.022 |
particular | +0.020 |
date | +0.020 |
Everyday | +0.018 |
invite | +0.018 |
Neg logit contributions | |
w | -0.015 |
ller | -0.014 |
ich | -0.014 |
llers | -0.013 |
EEP | -0.013 |
Token | can |
Token ID | 460 |
Feature activation | -4.46e-03 |
Pos logit contributions | |
w | +0.001 |
aged | +0.000 |
ich | +0.000 |
EEP | +0.000 |
AAAA | +0.000 |
Neg logit contributions | |
agreement | -0.000 |
particular | -0.000 |
date | -0.000 |
latable | -0.000 |
Everyday | -0.000 |
Token | set |
Token ID | 900 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
w | +0.008 |
ich | +0.007 |
ller | +0.007 |
llers | +0.007 |
aged | +0.007 |
Neg logit contributions | |
agreement | -0.006 |
particular | -0.005 |
date | -0.005 |
Everyday | -0.005 |
offer | -0.004 |
Token | our |
Token ID | 674 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
w | +0.002 |
ich | +0.002 |
ller | +0.002 |
llers | +0.002 |
aged | +0.002 |
Neg logit contributions | |
agreement | -0.003 |
particular | -0.003 |
date | -0.003 |
Everyday | -0.003 |
invite | -0.003 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
w | +0.028 |
ich | +0.025 |
ller | +0.024 |
aged | +0.024 |
llers | +0.024 |
Neg logit contributions | |
agreement | -0.032 |
particular | -0.030 |
Everyday | -0.028 |
date | -0.028 |
invite | -0.027 |
Token | again |
Token ID | 757 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.003 |
Everyday | +0.003 |
date | +0.003 |
invite | +0.002 |
Neg logit contributions | |
w | -0.002 |
ich | -0.002 |
ller | -0.002 |
uts | -0.002 |
aged | -0.002 |
Token | later |
Token ID | 1568 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
w | +0.014 |
ich | +0.013 |
ller | +0.012 |
llers | +0.012 |
aged | +0.012 |
Neg logit contributions | |
agreement | -0.012 |
particular | -0.011 |
date | -0.010 |
Everyday | -0.010 |
invite | -0.010 |
Token | ." |
Token ID | 526 |
Feature activation | -8.53e-04 |
Pos logit contributions | |
agreement | +0.026 |
particular | +0.024 |
Everyday | +0.022 |
date | +0.022 |
invite | +0.021 |
Neg logit contributions | |
w | -0.021 |
ich | -0.019 |
ller | -0.019 |
llers | -0.018 |
uts | -0.018 |
Token | we |
Token ID | 356 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
agreement | +0.034 |
date | +0.034 |
Everyday | +0.031 |
rene | +0.030 |
particular | +0.030 |
Neg logit contributions | |
w | -0.010 |
accidents | -0.009 |
EEP | -0.009 |
ich | -0.008 |
bleeding | -0.008 |
Token | can |
Token ID | 460 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
rily | +0.027 |
particular | +0.026 |
agreement | +0.026 |
date | +0.023 |
iona | +0.023 |
Neg logit contributions | |
w | -0.018 |
EEP | -0.014 |
Crash | -0.014 |
broke | -0.014 |
fighting | -0.013 |
Token | play |
Token ID | 711 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
agreement | +0.025 |
particular | +0.022 |
date | +0.021 |
rily | +0.021 |
Everyday | +0.020 |
Neg logit contributions | |
w | -0.022 |
llers | -0.020 |
ller | -0.019 |
EEP | -0.019 |
ich | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
agreement | +0.038 |
particular | +0.038 |
Everyday | +0.037 |
Whenever | +0.034 |
surely | +0.033 |
Neg logit contributions | |
w | -0.021 |
ich | -0.018 |
AAAA | -0.018 |
RR | -0.017 |
bleeding | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
agreement | +0.016 |
particular | +0.015 |
Everyday | +0.014 |
date | +0.014 |
invite | +0.013 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.009 |
llers | -0.009 |
inches | -0.009 |
Token | rain |
Token ID | 6290 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
agreement | +0.015 |
particular | +0.014 |
Everyday | +0.014 |
date | +0.013 |
rily | +0.013 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
bleeding | -0.010 |
crying | -0.010 |
elbows | -0.009 |
Token | later |
Token ID | 1568 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
w | +0.002 |
ich | +0.002 |
uts | +0.002 |
ller | +0.002 |
llers | +0.002 |
Neg logit contributions | |
agreement | -0.004 |
particular | -0.003 |
Everyday | -0.003 |
date | -0.003 |
offer | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
agreement | +0.034 |
particular | +0.030 |
Everyday | +0.028 |
date | +0.028 |
invite | +0.027 |
Neg logit contributions | |
w | -0.024 |
ich | -0.020 |
ller | -0.020 |
uts | -0.020 |
EEP | -0.019 |
Token | When |
Token ID | 1649 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
agreement | +0.033 |
particular | +0.032 |
date | +0.031 |
offer | +0.028 |
Everyday | +0.027 |
Neg logit contributions | |
EEP | -0.021 |
w | -0.020 |
ller | -0.018 |
RR | -0.018 |
ich | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
agreement | +0.039 |
particular | +0.036 |
Everyday | +0.036 |
date | +0.036 |
offer | +0.033 |
Neg logit contributions | |
w | -0.016 |
ich | -0.013 |
EEP | -0.011 |
llers | -0.011 |
ller | -0.011 |
Token | stops |
Token ID | 9911 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
agreement | +0.017 |
particular | +0.015 |
date | +0.014 |
Everyday | +0.014 |
offer | +0.013 |
Neg logit contributions | |
w | -0.012 |
ller | -0.009 |
ich | -0.009 |
aged | -0.009 |
llers | -0.009 |
Token | that |
Token ID | 326 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
agreement | +0.014 |
particular | +0.013 |
Everyday | +0.013 |
date | +0.012 |
invite | +0.012 |
Neg logit contributions | |
w | -0.011 |
ich | -0.010 |
ller | -0.010 |
aged | -0.009 |
irens | -0.009 |
Token | night |
Token ID | 1755 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
elbows | +0.073 |
w | +0.073 |
ich | +0.072 |
nam | +0.071 |
inches | +0.071 |
Neg logit contributions | |
particular | -0.020 |
Everyday | -0.017 |
agreement | -0.016 |
invite | -0.012 |
end | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e-03 |
Pos logit contributions | |
w | +0.065 |
nam | +0.063 |
ich | +0.062 |
elbows | +0.062 |
ller | +0.058 |
Neg logit contributions | |
particular | -0.036 |
date | -0.035 |
fill | -0.034 |
of | -0.034 |
invite | -0.034 |
Token | Tim |
Token ID | 5045 |
Feature activation | -8.86e-03 |
Pos logit contributions | |
agreement | +0.005 |
particular | +0.005 |
Everyday | +0.005 |
date | +0.004 |
invite | +0.004 |
Neg logit contributions | |
w | -0.004 |
ich | -0.003 |
ller | -0.003 |
aged | -0.003 |
llers | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
w | +0.010 |
ich | +0.008 |
aged | +0.007 |
ller | +0.007 |
bleeding | +0.007 |
Neg logit contributions | |
agreement | -0.019 |
particular | -0.018 |
date | -0.017 |
offer | -0.017 |
Everyday | -0.017 |
Token | started |
Token ID | 2067 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
w | +0.017 |
ich | +0.014 |
aged | +0.014 |
ller | +0.014 |
llers | +0.013 |
Neg logit contributions | |
agreement | -0.027 |
particular | -0.025 |
date | -0.024 |
Everyday | -0.023 |
offer | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
w | +0.067 |
ich | +0.059 |
RR | +0.057 |
ller | +0.055 |
AAAA | +0.054 |
Neg logit contributions | |
agreement | -0.053 |
particular | -0.049 |
Everyday | -0.049 |
invite | -0.048 |
fill | -0.047 |
Token | cry |
Token ID | 3960 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
w | +0.038 |
ich | +0.034 |
ller | +0.033 |
aged | +0.033 |
llers | +0.033 |
Neg logit contributions | |
agreement | -0.040 |
particular | -0.037 |
date | -0.036 |
Everyday | -0.035 |
invite | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e-03 |
Pos logit contributions | |
w | +0.013 |
ich | +0.012 |
ller | +0.011 |
aged | +0.011 |
llers | +0.011 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.009 |
Everyday | -0.009 |
date | -0.009 |
invite | -0.008 |
Token | His |
Token ID | 2399 |
Feature activation | -4.24e-03 |
Pos logit contributions | |
agreement | +0.003 |
particular | +0.002 |
Everyday | +0.002 |
date | +0.002 |
invite | +0.002 |
Neg logit contributions | |
w | -0.003 |
ich | -0.003 |
ller | -0.003 |
aged | -0.003 |
llers | -0.003 |
Token | knee |
Token ID | 10329 |
Feature activation | -9.08e-03 |
Pos logit contributions | |
w | +0.006 |
ich | +0.006 |
aged | +0.005 |
ller | +0.005 |
llers | +0.005 |
Neg logit contributions | |
agreement | -0.007 |
particular | -0.007 |
date | -0.007 |
Everyday | -0.006 |
invite | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
w | +0.029 |
ich | +0.026 |
ller | +0.025 |
llers | +0.025 |
nam | +0.024 |
Neg logit contributions | |
agreement | -0.021 |
Everyday | -0.020 |
particular | -0.020 |
Whenever | -0.017 |
offer | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
w | +0.024 |
ich | +0.022 |
ller | +0.020 |
llers | +0.020 |
aged | +0.020 |
Neg logit contributions | |
agreement | -0.026 |
particular | -0.025 |
Everyday | -0.024 |
invite | -0.022 |
offer | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
w | +0.008 |
ich | +0.008 |
ller | +0.008 |
llers | +0.007 |
aged | +0.007 |
Neg logit contributions | |
agreement | -0.011 |
particular | -0.010 |
Everyday | -0.010 |
date | -0.009 |
invite | -0.009 |
Token | Hey |
Token ID | 10814 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
w | +0.024 |
ller | +0.024 |
ich | +0.024 |
llers | +0.023 |
aged | +0.023 |
Neg logit contributions | |
agreement | -0.026 |
particular | -0.024 |
date | -0.022 |
Everyday | -0.022 |
invite | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
w | +0.064 |
llers | +0.061 |
ller | +0.061 |
irens | +0.061 |
aged | +0.060 |
Neg logit contributions | |
agreement | -0.052 |
particular | -0.047 |
invite | -0.044 |
date | -0.043 |
offer | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
w | +0.029 |
ich | +0.026 |
ller | +0.024 |
aged | +0.024 |
llers | +0.024 |
Neg logit contributions | |
agreement | -0.038 |
particular | -0.036 |
Everyday | -0.034 |
date | -0.034 |
invite | -0.033 |
Token | 's |
Token ID | 338 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
w | +0.054 |
nam | +0.052 |
ich | +0.052 |
irens | +0.052 |
aged | +0.052 |
Neg logit contributions | |
agreement | -0.049 |
particular | -0.046 |
invite | -0.045 |
Everyday | -0.045 |
date | -0.045 |
Token | mine |
Token ID | 6164 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
w | +0.022 |
aged | +0.021 |
ich | +0.021 |
irens | +0.020 |
ller | +0.020 |
Neg logit contributions | |
agreement | -0.021 |
particular | -0.020 |
invite | -0.019 |
fill | -0.018 |
date | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
w | +0.055 |
ich | +0.050 |
aged | +0.048 |
ller | +0.048 |
llers | +0.048 |
Neg logit contributions | |
agreement | -0.056 |
particular | -0.052 |
Everyday | -0.049 |
date | -0.049 |
invite | -0.049 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
w | +0.036 |
ich | +0.034 |
ller | +0.032 |
llers | +0.032 |
aged | +0.031 |
Neg logit contributions | |
agreement | -0.026 |
particular | -0.025 |
Everyday | -0.024 |
invite | -0.022 |
offer | -0.022 |
Token | shouts |
Token ID | 34757 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
w | +0.015 |
ich | +0.014 |
nam | +0.013 |
ller | +0.012 |
aged | +0.012 |
Neg logit contributions | |
agreement | -0.018 |
Everyday | -0.017 |
invite | -0.017 |
offer | -0.016 |
fill | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -8.34e-03 |
Pos logit contributions | |
w | +0.028 |
ich | +0.025 |
ller | +0.024 |
aged | +0.024 |
llers | +0.023 |
Neg logit contributions | |
agreement | -0.033 |
particular | -0.031 |
date | -0.029 |
Everyday | -0.028 |
invite | -0.027 |
Token | electric |
Token ID | 5186 |
Feature activation | -6.52e-04 |
Pos logit contributions | |
w | +0.008 |
bleeding | +0.008 |
ich | +0.007 |
aged | +0.007 |
nam | +0.007 |
Neg logit contributions | |
agreement | -0.018 |
date | -0.018 |
particular | -0.017 |
Everyday | -0.016 |
basis | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
w | +0.001 |
aged | +0.001 |
bleeding | +0.001 |
ller | +0.001 |
irens | +0.001 |
Neg logit contributions | |
agreement | -0.001 |
particular | -0.001 |
date | -0.001 |
invite | -0.001 |
Everyday | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
w | +0.014 |
ich | +0.012 |
ller | +0.012 |
llers | +0.012 |
aged | +0.012 |
Neg logit contributions | |
agreement | -0.011 |
particular | -0.010 |
Everyday | -0.010 |
date | -0.009 |
invite | -0.009 |
Token | says |
Token ID | 1139 |
Feature activation | -2.59e-04 |
Pos logit contributions | |
w | +0.020 |
ller | +0.017 |
ich | +0.017 |
inches | +0.016 |
aged | +0.016 |
Neg logit contributions | |
agreement | -0.042 |
particular | -0.040 |
date | -0.040 |
Everyday | -0.037 |
invite | -0.036 |
Token | that |
Token ID | 326 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
w | +0.000 |
ich | +0.000 |
ller | +0.000 |
llers | +0.000 |
RR | +0.000 |
Neg logit contributions | |
agreement | -0.000 |
particular | -0.000 |
Everyday | -0.000 |
invite | -0.000 |
offer | -0.000 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.46e-04 |
Pos logit contributions | |
w | +0.058 |
ich | +0.053 |
ller | +0.052 |
llers | +0.051 |
aged | +0.051 |
Neg logit contributions | |
agreement | -0.054 |
particular | -0.052 |
Everyday | -0.050 |
invite | -0.048 |
offer | -0.047 |
Token | can |
Token ID | 460 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
agreement | +0.000 |
particular | +0.000 |
date | +0.000 |
Everyday | +0.000 |
invite | +0.000 |
Neg logit contributions | |
w | -0.000 |
ich | -0.000 |
aged | -0.000 |
ller | -0.000 |
inches | -0.000 |
Token | use |
Token ID | 779 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
w | +0.009 |
ller | +0.008 |
ich | +0.008 |
llers | +0.007 |
uts | +0.007 |
Neg logit contributions | |
agreement | -0.009 |
particular | -0.007 |
date | -0.007 |
Everyday | -0.007 |
rily | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -9.64e-03 |
Pos logit contributions | |
w | +0.015 |
ller | +0.012 |
ich | +0.012 |
aged | +0.012 |
llers | +0.012 |
Neg logit contributions | |
agreement | -0.023 |
particular | -0.021 |
date | -0.021 |
Everyday | -0.020 |
invite | -0.020 |
Token | regular |
Token ID | 3218 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
w | +0.013 |
ich | +0.011 |
aged | +0.011 |
ller | +0.011 |
inches | +0.010 |
Neg logit contributions | |
agreement | -0.018 |
particular | -0.017 |
date | -0.016 |
Everyday | -0.016 |
invite | -0.015 |
Token | Then |
Token ID | 3244 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
w | +0.023 |
ich | +0.021 |
elbows | +0.019 |
rob | +0.018 |
RR | +0.018 |
Neg logit contributions | |
Everyday | -0.012 |
agreement | -0.011 |
particular | -0.010 |
Whenever | -0.010 |
Every | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e-04 |
Pos logit contributions | |
w | +0.012 |
ich | +0.012 |
ller | +0.011 |
RR | +0.011 |
llers | +0.011 |
Neg logit contributions | |
agreement | -0.011 |
particular | -0.010 |
Everyday | -0.010 |
invite | -0.010 |
date | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
agreement | +0.001 |
particular | +0.001 |
Everyday | +0.001 |
date | +0.001 |
offer | +0.001 |
Neg logit contributions | |
w | -0.000 |
ich | -0.000 |
aged | -0.000 |
ller | -0.000 |
nam | -0.000 |
Token | all |
Token ID | 477 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
w | +0.009 |
aged | +0.008 |
ich | +0.008 |
nam | +0.007 |
bleeding | +0.007 |
Neg logit contributions | |
agreement | -0.011 |
particular | -0.011 |
Everyday | -0.009 |
date | -0.009 |
offer | -0.009 |
Token | went |
Token ID | 1816 |
Feature activation | -9.31e-03 |
Pos logit contributions | |
w | +0.020 |
aged | +0.018 |
ller | +0.016 |
bleeding | +0.016 |
ich | +0.016 |
Neg logit contributions | |
agreement | -0.021 |
particular | -0.020 |
date | -0.019 |
Everyday | -0.018 |
offer | -0.018 |
Token | back |
Token ID | 736 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
w | +0.012 |
ich | +0.012 |
aged | +0.011 |
irens | +0.011 |
ller | +0.011 |
Neg logit contributions | |
agreement | -0.016 |
particular | -0.016 |
Everyday | -0.015 |
date | -0.014 |
offer | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
w | +0.074 |
RR | +0.067 |
ller | +0.065 |
ich | +0.065 |
llers | +0.064 |
Neg logit contributions | |
invite | -0.035 |
fill | -0.034 |
agreement | -0.033 |
particular | -0.032 |
date | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
w | +0.015 |
ich | +0.013 |
ller | +0.012 |
aged | +0.012 |
llers | +0.012 |
Neg logit contributions | |
agreement | -0.017 |
particular | -0.016 |
Everyday | -0.015 |
date | -0.015 |
invite | -0.015 |
Token | party |
Token ID | 2151 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
w | +0.014 |
ich | +0.014 |
crying | +0.013 |
reading | +0.013 |
bleeding | +0.013 |
Neg logit contributions | |
agreement | -0.010 |
particular | -0.010 |
Everyday | -0.009 |
iona | -0.008 |
Whenever | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
w | +0.020 |
ich | +0.019 |
aged | +0.018 |
ller | +0.018 |
llers | +0.018 |
Neg logit contributions | |
agreement | -0.024 |
particular | -0.023 |
Everyday | -0.022 |
date | -0.020 |
offer | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
w | +0.027 |
ich | +0.024 |
aged | +0.024 |
ller | +0.024 |
llers | +0.023 |
Neg logit contributions | |
agreement | -0.029 |
particular | -0.027 |
Everyday | -0.025 |
date | -0.025 |
offer | -0.024 |
Token | every |
Token ID | 790 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
agreement | +0.007 |
particular | +0.006 |
latable | +0.006 |
date | +0.006 |
invite | +0.005 |
Neg logit contributions | |
reading | -0.004 |
ich | -0.004 |
ller | -0.004 |
w | -0.004 |
aged | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
latable | +0.040 |
agreement | +0.037 |
ola | +0.036 |
invite | +0.035 |
cloth | +0.035 |
Neg logit contributions | |
w | -0.027 |
reading | -0.026 |
crying | -0.025 |
praying | -0.025 |
ller | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
w | +0.001 |
ich | +0.001 |
aged | +0.001 |
uts | +0.001 |
ller | +0.001 |
Neg logit contributions | |
agreement | -0.002 |
particular | -0.002 |
date | -0.002 |
Everyday | -0.002 |
invite | -0.002 |
Token | supply |
Token ID | 5127 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
agreement | +0.027 |
date | +0.026 |
particular | +0.024 |
latable | +0.024 |
Everyday | +0.024 |
Neg logit contributions | |
w | -0.029 |
reading | -0.029 |
praying | -0.028 |
ller | -0.027 |
touching | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
agreement | +0.004 |
particular | +0.004 |
date | +0.004 |
Everyday | +0.004 |
invite | +0.004 |
Neg logit contributions | |
w | -0.003 |
aged | -0.003 |
ich | -0.003 |
ller | -0.003 |
irens | -0.003 |
Token | av |
Token ID | 1196 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
w | +0.039 |
ich | +0.036 |
ller | +0.035 |
aged | +0.034 |
llers | +0.034 |
Neg logit contributions | |
agreement | -0.041 |
particular | -0.038 |
date | -0.036 |
Everyday | -0.036 |
invite | -0.035 |
Token | oc |
Token ID | 420 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
w | +0.064 |
ich | +0.059 |
elbows | +0.058 |
aged | +0.057 |
inches | +0.057 |
Neg logit contributions | |
agreement | -0.048 |
particular | -0.044 |
Everyday | -0.042 |
date | -0.041 |
offer | -0.039 |
Token | ados |
Token ID | 22484 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
w | +0.032 |
ich | +0.025 |
elbows | +0.025 |
AAAA | +0.025 |
ller | +0.024 |
Neg logit contributions | |
agreement | -0.071 |
date | -0.065 |
Everyday | -0.065 |
particular | -0.064 |
offer | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
w | +0.005 |
uts | +0.005 |
ich | +0.005 |
nam | +0.004 |
aged | +0.004 |
Neg logit contributions | |
agreement | -0.008 |
particular | -0.007 |
date | -0.007 |
Everyday | -0.007 |
invite | -0.006 |
Token | And |
Token ID | 843 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
agreement | +0.007 |
particular | +0.006 |
date | +0.006 |
invite | +0.006 |
fill | +0.006 |
Neg logit contributions | |
ller | -0.005 |
llers | -0.005 |
w | -0.005 |
Blood | -0.005 |
uts | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
w | +0.006 |
aged | +0.005 |
ller | +0.005 |
ich | +0.005 |
nam | +0.005 |
Neg logit contributions | |
agreement | -0.008 |
date | -0.008 |
particular | -0.007 |
latable | -0.007 |
invite | -0.007 |