Token | coat |
Token ID | 31434 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ount | +0.054 |
ll | +0.046 |
udd | +0.043 |
inconvenience | +0.041 |
ari | +0.041 |
Neg logit contributions | |
Charlotte | -0.074 |
pillow | -0.072 |
Ruby | -0.072 |
ricia | -0.071 |
Becky | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
ount | +0.029 |
ll | +0.028 |
udd | +0.028 |
aris | +0.026 |
ari | +0.025 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.023 |
ricia | -0.022 |
pillow | -0.022 |
Ruby | -0.022 |
Token | boots |
Token ID | 14412 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
udd | +0.021 |
ll | +0.021 |
ount | +0.021 |
won | +0.019 |
aris | +0.018 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.024 |
ricia | -0.024 |
iflower | -0.023 |
creature | -0.023 |
Token | when |
Token ID | 618 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ount | +0.076 |
ll | +0.068 |
roc | +0.067 |
udd | +0.066 |
aris | +0.065 |
Neg logit contributions | |
Charlotte | -0.054 |
pillow | -0.050 |
Ruby | -0.050 |
Becky | -0.049 |
veil | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ll | +0.019 |
udd | +0.019 |
ount | +0.019 |
won | +0.017 |
aris | +0.017 |
Neg logit contributions | |
ricia | -0.016 |
Charlotte | -0.016 |
Becky | -0.016 |
pillow | -0.015 |
creature | -0.015 |
Token | r |
Token ID | 374 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
ount | +0.027 |
ll | +0.026 |
aris | +0.025 |
udd | +0.025 |
ari | +0.025 |
Neg logit contributions | |
Becky | -0.018 |
Charlotte | -0.018 |
Ruby | -0.017 |
ricia | -0.017 |
pillow | -0.016 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
pay | +0.111 |
ari | +0.104 |
des | +0.100 |
won | +0.099 |
ount | +0.099 |
Neg logit contributions | |
ricia | -0.138 |
sey | -0.136 |
bly | -0.136 |
crib | -0.135 |
cable | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
ount | +0.025 |
ll | +0.024 |
udd | +0.024 |
aris | +0.022 |
won | +0.021 |
Neg logit contributions | |
Charlotte | -0.025 |
Becky | -0.025 |
ricia | -0.024 |
pillow | -0.024 |
Ruby | -0.023 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ount | +0.003 |
ll | +0.003 |
udd | +0.003 |
aris | +0.002 |
inconvenience | +0.002 |
Neg logit contributions | |
Charlotte | -0.003 |
Becky | -0.002 |
Ruby | -0.002 |
pillow | -0.002 |
Elsa | -0.002 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ount | +0.034 |
udd | +0.033 |
ll | +0.033 |
aris | +0.029 |
ari | +0.028 |
Neg logit contributions | |
Charlotte | -0.043 |
Becky | -0.042 |
Ruby | -0.041 |
ricia | -0.040 |
pillow | -0.040 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ount | +0.015 |
udd | +0.014 |
ll | +0.014 |
aris | +0.012 |
won | +0.011 |
Neg logit contributions | |
Charlotte | -0.033 |
Becky | -0.033 |
ricia | -0.032 |
pillow | -0.031 |
Ruby | -0.031 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
ount | +0.021 |
udd | +0.020 |
ll | +0.020 |
aris | +0.018 |
won | +0.018 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.020 |
ricia | -0.020 |
pillow | -0.019 |
Ruby | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
ount | +0.031 |
udd | +0.029 |
ll | +0.029 |
aris | +0.027 |
ari | +0.026 |
Neg logit contributions | |
Becky | -0.025 |
Charlotte | -0.025 |
pillow | -0.024 |
Ruby | -0.023 |
creature | -0.023 |
Token | even |
Token ID | 772 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
ount | +0.010 |
ll | +0.009 |
udd | +0.009 |
aris | +0.009 |
ari | +0.009 |
Neg logit contributions | |
Charlotte | -0.008 |
Becky | -0.008 |
pillow | -0.008 |
Ruby | -0.008 |
veil | -0.008 |
Token | when |
Token ID | 618 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
ount | +0.038 |
ll | +0.038 |
udd | +0.037 |
won | +0.032 |
aris | +0.032 |
Neg logit contributions | |
Charlotte | -0.058 |
Becky | -0.057 |
ricia | -0.056 |
pillow | -0.054 |
Ruby | -0.054 |
Token | it |
Token ID | 340 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ll | +0.014 |
ount | +0.014 |
udd | +0.014 |
won | +0.013 |
aris | +0.013 |
Neg logit contributions | |
Charlotte | -0.012 |
ricia | -0.012 |
Becky | -0.012 |
pillow | -0.011 |
iflower | -0.011 |
Token | r |
Token ID | 374 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
ount | +0.033 |
udd | +0.032 |
ll | +0.031 |
aris | +0.030 |
arl | +0.030 |
Neg logit contributions | |
Becky | -0.022 |
ricia | -0.021 |
creature | -0.021 |
Ruby | -0.020 |
pillow | -0.020 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
pay | +0.102 |
des | +0.096 |
ount | +0.092 |
won | +0.091 |
're | +0.090 |
Neg logit contributions | |
ricia | -0.154 |
iflower | -0.151 |
sey | -0.149 |
lers | -0.144 |
led | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ount | +0.028 |
ll | +0.027 |
udd | +0.027 |
aris | +0.024 |
won | +0.024 |
Neg logit contributions | |
Charlotte | -0.029 |
Becky | -0.028 |
ricia | -0.027 |
pillow | -0.027 |
Ruby | -0.026 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
ount | +0.026 |
udd | +0.025 |
ll | +0.025 |
inconvenience | +0.023 |
ari | +0.023 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.020 |
Ruby | -0.020 |
Louise | -0.018 |
ricia | -0.017 |
Token | Anna |
Token ID | 31160 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ount | +0.031 |
udd | +0.030 |
ll | +0.029 |
aris | +0.025 |
ari | +0.025 |
Neg logit contributions | |
Charlotte | -0.043 |
Becky | -0.042 |
Ruby | -0.041 |
pillow | -0.040 |
ricia | -0.040 |
Token | likes |
Token ID | 7832 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ount | +0.025 |
udd | +0.025 |
ll | +0.025 |
won | +0.023 |
aris | +0.022 |
Neg logit contributions | |
Charlotte | -0.023 |
Becky | -0.023 |
ricia | -0.022 |
pillow | -0.022 |
Ruby | -0.021 |
Token | kept |
Token ID | 4030 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
Charlotte | +0.034 |
Becky | +0.033 |
ricia | +0.033 |
pillow | +0.031 |
veil | +0.031 |
Neg logit contributions | |
ll | -0.032 |
ount | -0.031 |
udd | -0.031 |
won | -0.030 |
aris | -0.027 |
Token | them |
Token ID | 606 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Charlotte | +0.043 |
Becky | +0.042 |
pillow | +0.039 |
ricia | +0.039 |
Ruby | +0.038 |
Neg logit contributions | |
ount | -0.060 |
udd | -0.059 |
ll | -0.058 |
aris | -0.054 |
ari | -0.054 |
Token | dry |
Token ID | 5894 |
Feature activation | -2.38e-04 |
Pos logit contributions | |
pillow | +0.028 |
Charlotte | +0.028 |
Becky | +0.027 |
veil | +0.026 |
iflower | +0.025 |
Neg logit contributions | |
ount | -0.041 |
udd | -0.038 |
ll | -0.037 |
aris | -0.035 |
ari | -0.035 |
Token | when |
Token ID | 618 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
Charlotte | +0.000 |
Becky | +0.000 |
ricia | +0.000 |
pillow | +0.000 |
Ruby | +0.000 |
Neg logit contributions | |
ount | -0.000 |
ll | -0.000 |
udd | -0.000 |
aris | -0.000 |
won | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
ount | +0.002 |
ll | +0.002 |
udd | +0.002 |
won | +0.002 |
aris | +0.002 |
Neg logit contributions | |
Charlotte | -0.002 |
ricia | -0.002 |
Becky | -0.002 |
Ruby | -0.002 |
pillow | -0.002 |
Token | r |
Token ID | 374 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
ount | +0.011 |
udd | +0.011 |
ll | +0.010 |
aris | +0.010 |
ari | +0.010 |
Neg logit contributions | |
Becky | -0.009 |
Charlotte | -0.009 |
pillow | -0.009 |
ricia | -0.009 |
Ruby | -0.009 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
pay | +0.105 |
des | +0.098 |
won | +0.097 |
inconvenience | +0.095 |
ount | +0.094 |
Neg logit contributions | |
iflower | -0.139 |
sey | -0.138 |
ricia | -0.138 |
crib | -0.135 |
lers | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
ount | +0.020 |
ll | +0.019 |
udd | +0.019 |
aris | +0.017 |
ari | +0.017 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.020 |
ricia | -0.019 |
pillow | -0.019 |
Ruby | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
ount | +0.004 |
udd | +0.004 |
ll | +0.004 |
aris | +0.004 |
arl | +0.004 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
Ruby | -0.004 |
pillow | -0.004 |
crib | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-03 |
Pos logit contributions | |
ount | +0.008 |
ll | +0.007 |
udd | +0.007 |
aris | +0.006 |
won | +0.006 |
Neg logit contributions | |
Charlotte | -0.013 |
Becky | -0.012 |
ricia | -0.012 |
pillow | -0.012 |
Ruby | -0.012 |
Token | One |
Token ID | 3198 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ount | +0.003 |
ll | +0.003 |
udd | +0.003 |
aris | +0.003 |
won | +0.003 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
ricia | -0.003 |
pillow | -0.003 |
Ruby | -0.003 |
Token | used |
Token ID | 973 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
ount | +0.038 |
udd | +0.037 |
ll | +0.037 |
aris | +0.033 |
ari | +0.032 |
Neg logit contributions | |
Charlotte | -0.035 |
Becky | -0.035 |
ricia | -0.034 |
pillow | -0.033 |
Ruby | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
ricia | +0.003 |
Becky | +0.003 |
Charlotte | +0.003 |
iflower | +0.003 |
pillow | +0.002 |
Neg logit contributions | |
ount | -0.006 |
udd | -0.006 |
ll | -0.006 |
won | -0.005 |
aris | -0.005 |
Token | umbrella |
Token ID | 25510 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
ount | +0.028 |
ll | +0.028 |
udd | +0.028 |
aris | +0.025 |
won | +0.025 |
Neg logit contributions | |
Charlotte | -0.021 |
Becky | -0.021 |
ricia | -0.020 |
pillow | -0.019 |
Ruby | -0.019 |
Token | when |
Token ID | 618 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
ount | +0.059 |
udd | +0.052 |
ll | +0.051 |
aris | +0.046 |
inconvenience | +0.046 |
Neg logit contributions | |
Charlotte | -0.057 |
Becky | -0.054 |
pillow | -0.054 |
Ruby | -0.053 |
creature | -0.052 |
Token | it |
Token ID | 340 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ll | +0.009 |
ount | +0.009 |
udd | +0.009 |
won | +0.009 |
aris | +0.008 |
Neg logit contributions | |
ricia | -0.007 |
Charlotte | -0.007 |
Becky | -0.007 |
pillow | -0.007 |
iflower | -0.007 |
Token | r |
Token ID | 374 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
ount | +0.026 |
udd | +0.025 |
ll | +0.025 |
aris | +0.024 |
arl | +0.023 |
Neg logit contributions | |
Becky | -0.017 |
Charlotte | -0.017 |
Ruby | -0.016 |
ricia | -0.016 |
pillow | -0.015 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
pay | +0.095 |
ari | +0.093 |
ount | +0.092 |
won | +0.087 |
aren | +0.087 |
Neg logit contributions | |
sey | -0.143 |
ricia | -0.141 |
frantically | -0.140 |
bly | -0.138 |
lers | -0.138 |
Token | and |
Token ID | 290 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.021 |
udd | +0.021 |
aris | +0.018 |
won | +0.018 |
Neg logit contributions | |
Charlotte | -0.021 |
Becky | -0.021 |
ricia | -0.021 |
pillow | -0.020 |
Ruby | -0.020 |
Token | never |
Token ID | 1239 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ount | +0.024 |
udd | +0.023 |
ll | +0.022 |
aris | +0.021 |
ari | +0.021 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.017 |
ricia | -0.016 |
Ruby | -0.016 |
pillow | -0.016 |
Token | let |
Token ID | 1309 |
Feature activation | -1.02e-03 |
Pos logit contributions | |
ount | +0.074 |
udd | +0.067 |
arl | +0.066 |
ari | +0.066 |
aris | +0.065 |
Neg logit contributions | |
Charlotte | -0.047 |
Becky | -0.047 |
Ruby | -0.046 |
bunny | -0.045 |
creature | -0.045 |
Token | go |
Token ID | 467 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
Charlotte | +0.001 |
Becky | +0.001 |
ricia | +0.001 |
pillow | +0.001 |
iflower | +0.001 |
Neg logit contributions | |
ount | -0.002 |
udd | -0.002 |
ll | -0.002 |
won | -0.002 |
aris | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
pillow | +0.005 |
iflower | +0.005 |
Neg logit contributions | |
ount | -0.008 |
udd | -0.008 |
ll | -0.008 |
won | -0.007 |
aris | -0.007 |
Token | z |
Token ID | 1976 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
Charlotte | +0.012 |
Becky | +0.012 |
ricia | +0.012 |
Ruby | +0.011 |
pillow | +0.011 |
Neg logit contributions | |
udd | -0.012 |
ll | -0.012 |
ount | -0.011 |
won | -0.011 |
lay | -0.010 |
Token | ipped |
Token ID | 3949 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
ount | +0.017 |
ll | +0.016 |
udd | +0.016 |
pay | +0.015 |
inconvenience | +0.015 |
Neg logit contributions | |
wand | -0.012 |
ricia | -0.011 |
Charlotte | -0.011 |
Becky | -0.011 |
iflower | -0.011 |
Token | when |
Token ID | 618 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.004 |
ricia | +0.004 |
iflower | +0.004 |
pillow | +0.004 |
Neg logit contributions | |
ount | -0.006 |
udd | -0.006 |
ll | -0.006 |
won | -0.005 |
aris | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ricia | +0.004 |
Charlotte | +0.004 |
Becky | +0.004 |
iflower | +0.003 |
pillow | +0.003 |
Neg logit contributions | |
ount | -0.006 |
ll | -0.006 |
udd | -0.006 |
won | -0.006 |
aris | -0.005 |
Token | r |
Token ID | 374 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.020 |
udd | +0.020 |
aris | +0.019 |
ari | +0.018 |
Neg logit contributions | |
Becky | -0.016 |
Charlotte | -0.016 |
ricia | -0.015 |
pillow | -0.015 |
creature | -0.015 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
pay | +0.110 |
won | +0.099 |
des | +0.097 |
inconvenience | +0.097 |
ari | +0.096 |
Neg logit contributions | |
sey | -0.141 |
ricia | -0.134 |
iflower | -0.134 |
bly | -0.134 |
led | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
ount | +0.019 |
ll | +0.019 |
udd | +0.019 |
aris | +0.017 |
won | +0.016 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.019 |
ricia | -0.019 |
pillow | -0.018 |
Ruby | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
Charlotte | +0.008 |
Becky | +0.007 |
Ruby | +0.007 |
ricia | +0.007 |
pillow | +0.007 |
Neg logit contributions | |
ll | -0.007 |
ount | -0.007 |
udd | -0.007 |
aris | -0.006 |
ari | -0.006 |
Token | rock |
Token ID | 3881 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
Charlotte | +0.002 |
Becky | +0.002 |
ricia | +0.002 |
Ruby | +0.002 |
pillow | +0.002 |
Neg logit contributions | |
ount | -0.002 |
udd | -0.002 |
ll | -0.002 |
aris | -0.002 |
won | -0.002 |
Token | z |
Token ID | 1976 |
Feature activation | -2.66e-03 |
Pos logit contributions | |
Charlotte | +0.013 |
Becky | +0.013 |
ricia | +0.012 |
Ruby | +0.012 |
pillow | +0.012 |
Neg logit contributions | |
udd | -0.015 |
ll | -0.015 |
ount | -0.014 |
won | -0.013 |
aris | -0.013 |
Token | just |
Token ID | 655 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ount | +0.017 |
ll | +0.017 |
udd | +0.017 |
won | +0.015 |
aris | +0.015 |
Neg logit contributions | |
Charlotte | -0.016 |
Becky | -0.015 |
ricia | -0.015 |
pillow | -0.015 |
iflower | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
ount | +0.043 |
ll | +0.042 |
udd | +0.041 |
won | +0.037 |
aris | +0.036 |
Neg logit contributions | |
Charlotte | -0.054 |
Becky | -0.053 |
ricia | -0.053 |
pillow | -0.051 |
iflower | -0.050 |
Token | time |
Token ID | 640 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
ricia | +0.009 |
iflower | +0.008 |
Charlotte | +0.008 |
Becky | +0.008 |
creature | +0.008 |
Neg logit contributions | |
ount | -0.007 |
ll | -0.007 |
udd | -0.007 |
won | -0.007 |
pay | -0.006 |
Token | before |
Token ID | 878 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
ount | +0.004 |
udd | +0.004 |
ll | +0.004 |
aris | +0.004 |
ari | +0.004 |
Neg logit contributions | |
Charlotte | -0.005 |
Becky | -0.005 |
ricia | -0.004 |
pillow | -0.004 |
Ruby | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ount | +0.015 |
udd | +0.014 |
ll | +0.014 |
aris | +0.013 |
ari | +0.013 |
Neg logit contributions | |
Charlotte | -0.010 |
Becky | -0.009 |
pillow | -0.009 |
ricia | -0.009 |
Ruby | -0.009 |
Token | r |
Token ID | 374 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
ount | +0.037 |
udd | +0.036 |
ll | +0.035 |
aris | +0.033 |
ari | +0.032 |
Neg logit contributions | |
Becky | -0.031 |
Charlotte | -0.031 |
Ruby | -0.029 |
ricia | -0.029 |
pillow | -0.028 |
Token | ained |
Token ID | 1328 |
Feature activation | +6.39e-03 |
Pos logit contributions | |
pay | +0.096 |
won | +0.095 |
ount | +0.090 |
aren | +0.089 |
aris | +0.087 |
Neg logit contributions | |
ricia | -0.145 |
sey | -0.143 |
bly | -0.142 |
Becky | -0.139 |
Charlotte | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
ount | +0.009 |
udd | +0.009 |
ll | +0.009 |
aris | +0.008 |
won | +0.008 |
Neg logit contributions | |
Charlotte | -0.011 |
Becky | -0.011 |
ricia | -0.010 |
pillow | -0.010 |
iflower | -0.010 |
Token | After |
Token ID | 2293 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
Charlotte | +0.013 |
Becky | +0.013 |
ricia | +0.012 |
Ruby | +0.012 |
pillow | +0.012 |
Neg logit contributions | |
ount | -0.012 |
ll | -0.012 |
udd | -0.012 |
aris | -0.011 |
won | -0.011 |
Token | this |
Token ID | 428 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
Charlotte | +0.020 |
Becky | +0.020 |
ricia | +0.019 |
pillow | +0.019 |
Ruby | +0.018 |
Neg logit contributions | |
ount | -0.028 |
ll | -0.028 |
udd | -0.028 |
aris | -0.025 |
ari | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
ount | +0.050 |
ll | +0.048 |
udd | +0.047 |
aris | +0.044 |
ari | +0.041 |
Neg logit contributions | |
Charlotte | -0.050 |
Becky | -0.049 |
ricia | -0.047 |
pillow | -0.047 |
Ruby | -0.047 |
Token | moved |
Token ID | 3888 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
udd | +0.010 |
ll | +0.010 |
ount | +0.010 |
won | +0.009 |
aris | +0.009 |
Neg logit contributions | |
Charlotte | -0.014 |
Becky | -0.014 |
ricia | -0.014 |
pillow | -0.013 |
iflower | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Charlotte | +0.006 |
Becky | +0.005 |
ricia | +0.005 |
iflower | +0.005 |
pillow | +0.005 |
Neg logit contributions | |
ount | -0.007 |
udd | -0.007 |
ll | -0.007 |
won | -0.007 |
lay | -0.007 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.52e-03 |
Pos logit contributions | |
Charlotte | +0.024 |
Becky | +0.024 |
ricia | +0.023 |
pillow | +0.022 |
Ruby | +0.022 |
Neg logit contributions | |
ount | -0.034 |
ll | -0.034 |
udd | -0.034 |
aris | -0.031 |
won | -0.030 |
Token | when |
Token ID | 618 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
Charlotte | +0.006 |
Becky | +0.006 |
ricia | +0.006 |
pillow | +0.005 |
iflower | +0.005 |
Neg logit contributions | |
ount | -0.005 |
ll | -0.005 |
udd | -0.005 |
won | -0.005 |
aris | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ll | +0.003 |
ount | +0.003 |
won | +0.003 |
udd | +0.003 |
aris | +0.003 |
Neg logit contributions | |
ricia | -0.003 |
Charlotte | -0.003 |
iflower | -0.003 |
Becky | -0.003 |
pillow | -0.002 |
Token | r |
Token ID | 374 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
ount | +0.022 |
ll | +0.022 |
udd | +0.022 |
aris | +0.020 |
won | +0.019 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.018 |
ricia | -0.017 |
pillow | -0.016 |
Ruby | -0.016 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
pay | +0.083 |
ount | +0.081 |
ll | +0.079 |
won | +0.078 |
des | +0.077 |
Neg logit contributions | |
ricia | -0.164 |
Charlotte | -0.159 |
Becky | -0.158 |
iflower | -0.156 |
frantically | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
ount | +0.016 |
udd | +0.015 |
ll | +0.015 |
won | +0.014 |
aris | +0.014 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.018 |
ricia | -0.018 |
iflower | -0.017 |
pillow | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.002 |
Ruby | +0.002 |
ricia | +0.002 |
Bonnie | +0.002 |
Neg logit contributions | |
ount | -0.003 |
ll | -0.003 |
udd | -0.003 |
aris | -0.002 |
ari | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
Charlotte | +0.013 |
Becky | +0.013 |
iflower | +0.013 |
ricia | +0.013 |
turkey | +0.012 |
Neg logit contributions | |
ll | -0.011 |
won | -0.011 |
udd | -0.011 |
ount | -0.010 |
paid | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
Charlotte | +0.035 |
Becky | +0.035 |
ricia | +0.034 |
pillow | +0.033 |
iflower | +0.033 |
Neg logit contributions | |
ount | -0.032 |
udd | -0.031 |
ll | -0.031 |
won | -0.028 |
aris | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ount | +0.014 |
ll | +0.014 |
udd | +0.014 |
won | +0.012 |
aris | +0.012 |
Neg logit contributions | |
Charlotte | -0.013 |
Becky | -0.013 |
ricia | -0.013 |
pillow | -0.012 |
iflower | -0.012 |
Token | never |
Token ID | 1239 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
ount | +0.035 |
udd | +0.033 |
ll | +0.031 |
aris | +0.031 |
inconvenience | +0.030 |
Neg logit contributions | |
Charlotte | -0.034 |
Becky | -0.033 |
ricia | -0.031 |
pillow | -0.031 |
Ruby | -0.031 |
Token | worried |
Token ID | 7960 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
ount | +0.073 |
arl | +0.068 |
aris | +0.063 |
udd | +0.062 |
ll | +0.062 |
Neg logit contributions | |
Charlotte | -0.041 |
Becky | -0.041 |
frantically | -0.038 |
thumb | -0.038 |
Ruby | -0.038 |
Token | when |
Token ID | 618 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
ount | +0.045 |
udd | +0.044 |
ll | +0.043 |
aris | +0.038 |
won | +0.038 |
Neg logit contributions | |
Charlotte | -0.069 |
Becky | -0.069 |
ricia | -0.067 |
pillow | -0.065 |
iflower | -0.065 |
Token | it |
Token ID | 340 |
Feature activation | +9.65e-03 |
Pos logit contributions | |
ll | +0.011 |
ount | +0.011 |
udd | +0.011 |
won | +0.010 |
aris | +0.009 |
Neg logit contributions | |
Charlotte | -0.012 |
ricia | -0.012 |
Becky | -0.011 |
pillow | -0.011 |
iflower | -0.011 |
Token | r |
Token ID | 374 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
ount | +0.020 |
ll | +0.019 |
udd | +0.019 |
aris | +0.018 |
ari | +0.017 |
Neg logit contributions | |
Becky | -0.011 |
Charlotte | -0.011 |
ricia | -0.011 |
Ruby | -0.010 |
pillow | -0.010 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
pay | +0.087 |
ount | +0.087 |
des | +0.083 |
won | +0.082 |
ari | +0.079 |
Neg logit contributions | |
ricia | -0.156 |
Charlotte | -0.153 |
sey | -0.151 |
Becky | -0.150 |
issa | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e-03 |
Pos logit contributions | |
ount | +0.025 |
ll | +0.024 |
udd | +0.024 |
aris | +0.022 |
won | +0.021 |
Neg logit contributions | |
Charlotte | -0.022 |
Becky | -0.022 |
ricia | -0.021 |
pillow | -0.021 |
Ruby | -0.020 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ll | +0.005 |
ount | +0.005 |
udd | +0.005 |
aris | +0.004 |
lay | +0.004 |
Neg logit contributions | |
Charlotte | -0.006 |
Becky | -0.006 |
Ruby | -0.005 |
ricia | -0.005 |
Bonnie | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
udd | +0.044 |
ount | +0.043 |
ll | +0.042 |
pay | +0.037 |
aris | +0.037 |
Neg logit contributions | |
Charlotte | -0.053 |
Becky | -0.052 |
Ruby | -0.050 |
ricia | -0.049 |
pillow | -0.049 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ount | +0.018 |
ll | +0.018 |
udd | +0.017 |
aris | +0.014 |
won | +0.014 |
Neg logit contributions | |
Charlotte | -0.048 |
Becky | -0.047 |
ricia | -0.046 |
pillow | -0.045 |
Ruby | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
ll | +0.035 |
udd | +0.033 |
ount | +0.032 |
ari | +0.031 |
aris | +0.030 |
Neg logit contributions | |
Ruby | -0.011 |
Becky | -0.011 |
its | -0.011 |
pillow | -0.010 |
Rocky | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
ount | +0.014 |
udd | +0.013 |
ll | +0.013 |
aris | +0.012 |
ari | +0.012 |
Neg logit contributions | |
Becky | -0.011 |
Charlotte | -0.011 |
Ruby | -0.011 |
ricia | -0.011 |
pillow | -0.011 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ount | +0.002 |
aris | +0.002 |
ll | +0.002 |
udd | +0.002 |
parties | +0.002 |
Neg logit contributions | |
ricia | -0.001 |
iflower | -0.001 |
His | -0.001 |
Ruby | -0.001 |
idi | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
ount | +0.018 |
ll | +0.018 |
udd | +0.018 |
aris | +0.016 |
won | +0.015 |
Neg logit contributions | |
Charlotte | -0.023 |
Becky | -0.022 |
ricia | -0.022 |
pillow | -0.021 |
Ruby | -0.021 |
Token | water |
Token ID | 1660 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
ll | +0.040 |
ount | +0.040 |
udd | +0.040 |
aris | +0.037 |
ari | +0.037 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.019 |
pillow | -0.019 |
Ruby | -0.018 |
ricia | -0.017 |
Token | spr |
Token ID | 7500 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
ount | +0.076 |
ll | +0.075 |
udd | +0.075 |
aris | +0.068 |
ari | +0.067 |
Neg logit contributions | |
Charlotte | -0.073 |
Becky | -0.072 |
ricia | -0.070 |
pillow | -0.069 |
creature | -0.068 |
Token | ays |
Token ID | 592 |
Feature activation | +3.76e-03 |
Pos logit contributions | |
ount | +0.146 |
ll | +0.145 |
udd | +0.142 |
ari | +0.135 |
aris | +0.134 |
Neg logit contributions | |
Charlotte | -0.104 |
ricia | -0.104 |
Becky | -0.103 |
iflower | -0.097 |
creature | -0.096 |
Token | out |
Token ID | 503 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
ll | +0.007 |
ount | +0.007 |
udd | +0.007 |
aris | +0.006 |
ari | +0.006 |
Neg logit contributions | |
Becky | -0.005 |
Charlotte | -0.005 |
pillow | -0.005 |
creature | -0.005 |
Ruby | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
Becky | +0.044 |
Charlotte | +0.043 |
pillow | +0.041 |
ricia | +0.041 |
Ruby | +0.040 |
Neg logit contributions | |
ount | -0.050 |
ll | -0.050 |
udd | -0.049 |
aris | -0.044 |
ari | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ount | +0.023 |
ll | +0.022 |
udd | +0.022 |
won | +0.020 |
aris | +0.020 |
Neg logit contributions | |
Charlotte | -0.017 |
Becky | -0.016 |
ricia | -0.016 |
pillow | -0.015 |
iflower | -0.015 |
Token | hose |
Token ID | 31489 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
ount | +0.020 |
ll | +0.019 |
udd | +0.019 |
aris | +0.017 |
won | +0.017 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.018 |
ricia | -0.018 |
Ruby | -0.017 |
pillow | -0.017 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
ount | +0.002 |
ll | +0.002 |
udd | +0.002 |
aris | +0.002 |
ari | +0.002 |
Neg logit contributions | |
Charlotte | -0.003 |
Becky | -0.003 |
ricia | -0.003 |
pillow | -0.003 |
Ruby | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -4.35e-03 |
Pos logit contributions | |
Charlotte | +0.012 |
Becky | +0.012 |
ricia | +0.012 |
pillow | +0.011 |
Ruby | +0.011 |
Neg logit contributions | |
ount | -0.012 |
udd | -0.012 |
ll | -0.012 |
aris | -0.010 |
won | -0.010 |
Token | even |
Token ID | 772 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Charlotte | +0.006 |
Becky | +0.006 |
Ruby | +0.005 |
pillow | +0.005 |
ricia | +0.005 |
Neg logit contributions | |
ount | -0.008 |
ll | -0.008 |
udd | -0.008 |
aris | -0.007 |
ari | -0.007 |
Token | when |
Token ID | 618 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
ount | +0.028 |
udd | +0.027 |
ll | +0.027 |
won | +0.024 |
pay | +0.022 |
Neg logit contributions | |
Charlotte | -0.056 |
Becky | -0.056 |
ricia | -0.055 |
pillow | -0.054 |
iflower | -0.053 |
Token | it |
Token ID | 340 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ll | +0.005 |
udd | +0.004 |
ount | +0.004 |
won | +0.004 |
lay | +0.004 |
Neg logit contributions | |
ricia | -0.004 |
Becky | -0.004 |
Charlotte | -0.004 |
rily | -0.004 |
pillow | -0.004 |
Token | r |
Token ID | 374 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
ount | +0.024 |
ll | +0.022 |
udd | +0.022 |
aris | +0.022 |
ari | +0.021 |
Neg logit contributions | |
Becky | -0.013 |
Charlotte | -0.013 |
ricia | -0.012 |
Ruby | -0.012 |
creature | -0.011 |
Token | ained |
Token ID | 1328 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
pay | +0.102 |
des | +0.093 |
won | +0.091 |
ount | +0.091 |
're | +0.090 |
Neg logit contributions | |
ricia | -0.136 |
sey | -0.133 |
bly | -0.132 |
iflower | -0.131 |
cable | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
ount | +0.015 |
udd | +0.014 |
ll | +0.014 |
aris | +0.013 |
won | +0.013 |
Neg logit contributions | |
Charlotte | -0.015 |
Becky | -0.015 |
ricia | -0.014 |
pillow | -0.014 |
Ruby | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Charlotte | +0.010 |
Becky | +0.009 |
Ruby | +0.009 |
ricia | +0.009 |
Bonnie | +0.009 |
Neg logit contributions | |
ount | -0.009 |
ll | -0.009 |
udd | -0.008 |
aris | -0.008 |
ari | -0.008 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ount | +0.030 |
udd | +0.030 |
ll | +0.029 |
aris | +0.026 |
ari | +0.025 |
Neg logit contributions | |
Charlotte | -0.036 |
Becky | -0.035 |
Ruby | -0.034 |
pillow | -0.033 |
ricia | -0.033 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ount | +0.011 |
udd | +0.011 |
ll | +0.011 |
aris | +0.009 |
won | +0.009 |
Neg logit contributions | |
Charlotte | -0.027 |
Becky | -0.027 |
ricia | -0.026 |
pillow | -0.026 |
Ruby | -0.026 |
Token | things |
Token ID | 1243 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
ount | +0.013 |
ll | +0.012 |
udd | +0.012 |
aris | +0.011 |
ari | +0.011 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
ricia | -0.009 |
pillow | -0.009 |
creature | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Charlotte | +0.009 |
Becky | +0.009 |
ricia | +0.008 |
pillow | +0.008 |
Ruby | +0.008 |
Neg logit contributions | |
ount | -0.007 |
udd | -0.007 |
ll | -0.007 |
aris | -0.006 |
ari | -0.006 |
Token | examine |
Token ID | 10716 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ount | +0.022 |
ll | +0.021 |
udd | +0.021 |
aris | +0.018 |
won | +0.018 |
Neg logit contributions | |
Charlotte | -0.034 |
Becky | -0.034 |
ricia | -0.033 |
pillow | -0.032 |
Ruby | -0.032 |
Token | when |
Token ID | 618 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
Charlotte | +0.023 |
Becky | +0.022 |
ricia | +0.022 |
iflower | +0.021 |
pillow | +0.021 |
Neg logit contributions | |
ount | -0.020 |
udd | -0.020 |
ll | -0.018 |
won | -0.018 |
aris | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +9.28e-03 |
Pos logit contributions | |
ricia | +0.004 |
Charlotte | +0.004 |
Becky | +0.004 |
pillow | +0.004 |
iflower | +0.003 |
Neg logit contributions | |
ount | -0.004 |
ll | -0.004 |
udd | -0.004 |
won | -0.004 |
aris | -0.004 |
Token | r |
Token ID | 374 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
ount | +0.018 |
ll | +0.017 |
udd | +0.017 |
arl | +0.017 |
aris | +0.016 |
Neg logit contributions | |
Becky | -0.011 |
Charlotte | -0.011 |
creature | -0.010 |
pillow | -0.010 |
Ruby | -0.010 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
pay | +0.106 |
inconvenience | +0.099 |
des | +0.098 |
ari | +0.097 |
won | +0.096 |
Neg logit contributions | |
sey | -0.130 |
ricia | -0.126 |
iflower | -0.125 |
lers | -0.123 |
bly | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
ount | +0.018 |
ll | +0.018 |
udd | +0.018 |
aris | +0.016 |
won | +0.016 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.019 |
ricia | -0.018 |
pillow | -0.018 |
Ruby | -0.017 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.004 |
Ruby | +0.004 |
pillow | +0.004 |
ricia | +0.004 |
Neg logit contributions | |
ount | -0.004 |
ll | -0.004 |
udd | -0.003 |
aris | -0.003 |
inconvenience | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ount | +0.033 |
udd | +0.032 |
ll | +0.031 |
aris | +0.028 |
ari | +0.027 |
Neg logit contributions | |
Charlotte | -0.039 |
Becky | -0.038 |
Ruby | -0.037 |
pillow | -0.037 |
ricia | -0.037 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ount | +0.011 |
udd | +0.010 |
ll | +0.010 |
aris | +0.009 |
won | +0.008 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.024 |
ricia | -0.024 |
pillow | -0.023 |
Ruby | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Charlotte | +0.000 |
Becky | +0.000 |
ricia | +0.000 |
pillow | +0.000 |
Ruby | +0.000 |
Neg logit contributions | |
ount | -0.000 |
ll | -0.000 |
udd | -0.000 |
aris | -0.000 |
won | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
Charlotte | +0.021 |
ricia | +0.021 |
Becky | +0.020 |
Ruby | +0.019 |
iflower | +0.018 |
Neg logit contributions | |
ount | -0.031 |
udd | -0.031 |
ll | -0.031 |
won | -0.030 |
aris | -0.029 |
Token | blanket |
Token ID | 18447 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
ount | +0.010 |
udd | +0.010 |
ll | +0.010 |
aris | +0.009 |
won | +0.009 |
Neg logit contributions | |
Charlotte | -0.007 |
Becky | -0.007 |
ricia | -0.006 |
Ruby | -0.006 |
pillow | -0.006 |
Token | when |
Token ID | 618 |
Feature activation | +5.25e-03 |
Pos logit contributions | |
ount | +0.007 |
udd | +0.006 |
ll | +0.006 |
aris | +0.006 |
lay | +0.006 |
Neg logit contributions | |
Charlotte | -0.006 |
Becky | -0.006 |
pillow | -0.006 |
Ruby | -0.005 |
ricia | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ll | +0.009 |
ount | +0.009 |
udd | +0.009 |
won | +0.008 |
aris | +0.008 |
Neg logit contributions | |
Charlotte | -0.007 |
ricia | -0.007 |
Becky | -0.007 |
pillow | -0.007 |
Ruby | -0.007 |
Token | r |
Token ID | 374 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
ount | +0.024 |
udd | +0.022 |
ll | +0.022 |
aris | +0.021 |
ari | +0.021 |
Neg logit contributions | |
Becky | -0.019 |
Charlotte | -0.018 |
Ruby | -0.018 |
ricia | -0.018 |
pillow | -0.018 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
pay | +0.094 |
ount | +0.090 |
aren | +0.088 |
won | +0.088 |
des | +0.088 |
Neg logit contributions | |
ricia | -0.138 |
sey | -0.136 |
iflower | -0.134 |
bly | -0.132 |
cable | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-04 |
Pos logit contributions | |
ount | +0.020 |
ll | +0.020 |
udd | +0.020 |
aris | +0.018 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.020 |
ricia | -0.019 |
pillow | -0.019 |
Ruby | -0.018 |
Token | And |
Token ID | 843 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
Becky | +0.000 |
Charlotte | +0.000 |
Ruby | +0.000 |
pillow | +0.000 |
cable | +0.000 |
Neg logit contributions | |
ount | -0.000 |
ll | -0.000 |
udd | -0.000 |
inconvenience | -0.000 |
lay | -0.000 |
Token | as |
Token ID | 355 |
Feature activation | -3.87e-03 |
Pos logit contributions | |
ount | +0.025 |
udd | +0.024 |
ll | +0.023 |
arl | +0.022 |
aris | +0.022 |
Neg logit contributions | |
Becky | -0.015 |
Charlotte | -0.015 |
Ruby | -0.014 |
creature | -0.014 |
pillow | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
pillow | +0.005 |
ricia | +0.005 |
Ruby | +0.005 |
Neg logit contributions | |
ount | -0.008 |
udd | -0.007 |
ll | -0.007 |
aris | -0.007 |
ari | -0.007 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ount | +0.022 |
udd | +0.021 |
ll | +0.021 |
aris | +0.019 |
ari | +0.019 |
Neg logit contributions | |
Charlotte | -0.017 |
Becky | -0.016 |
creature | -0.016 |
ricia | -0.015 |
Ruby | -0.015 |
Token | their |
Token ID | 511 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ll | +0.020 |
udd | +0.020 |
ount | +0.020 |
won | +0.019 |
done | +0.018 |
Neg logit contributions | |
Charlotte | -0.022 |
ricia | -0.022 |
Becky | -0.021 |
issa | -0.021 |
iflower | -0.019 |
Token | popcorn |
Token ID | 38914 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
ll | +0.017 |
udd | +0.016 |
ount | +0.015 |
won | +0.015 |
done | +0.014 |
Neg logit contributions | |
Charlotte | -0.024 |
ricia | -0.023 |
Becky | -0.023 |
issa | -0.022 |
Bonnie | -0.021 |
Token | while |
Token ID | 981 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
ount | +0.008 |
ll | +0.008 |
udd | +0.008 |
won | +0.007 |
aris | +0.007 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
ricia | -0.009 |
Ruby | -0.008 |
pillow | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ricia | +0.041 |
Charlotte | +0.039 |
Becky | +0.039 |
creature | +0.037 |
pillow | +0.037 |
Neg logit contributions | |
ll | -0.037 |
ount | -0.036 |
udd | -0.034 |
won | -0.033 |
pay | -0.032 |
Token | r |
Token ID | 374 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
ount | +0.033 |
ll | +0.032 |
udd | +0.032 |
aris | +0.029 |
won | +0.028 |
Neg logit contributions | |
Charlotte | -0.030 |
Becky | -0.030 |
ricia | -0.029 |
pillow | -0.028 |
Ruby | -0.028 |
Token | ained |
Token ID | 1328 |
Feature activation | +8.25e-03 |
Pos logit contributions | |
ount | +0.084 |
ari | +0.084 |
won | +0.084 |
aris | +0.083 |
pay | +0.081 |
Neg logit contributions | |
iflower | -0.149 |
ricia | -0.149 |
bly | -0.146 |
rily | -0.145 |
led | -0.143 |
Token | outside |
Token ID | 2354 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
ount | +0.012 |
udd | +0.012 |
ll | +0.012 |
won | +0.010 |
aris | +0.010 |
Neg logit contributions | |
Charlotte | -0.014 |
Becky | -0.014 |
ricia | -0.014 |
iflower | -0.013 |
pillow | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-03 |
Pos logit contributions | |
ount | +0.007 |
ll | +0.006 |
udd | +0.006 |
aris | +0.006 |
ari | +0.006 |
Neg logit contributions | |
Charlotte | -0.007 |
Becky | -0.007 |
ricia | -0.006 |
pillow | -0.006 |
Ruby | -0.006 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.002 |
ricia | +0.002 |
Ruby | +0.002 |
pillow | +0.002 |
Neg logit contributions | |
ount | -0.002 |
ll | -0.002 |
udd | -0.002 |
aris | -0.002 |
ari | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Becky | +0.017 |
Charlotte | +0.017 |
ricia | +0.016 |
creature | +0.016 |
iflower | +0.016 |
Neg logit contributions | |
udd | -0.018 |
ll | -0.018 |
ount | -0.017 |
won | -0.016 |
aris | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | +5.25e-03 |
Pos logit contributions | |
ll | +0.012 |
udd | +0.012 |
ount | +0.012 |
lay | +0.011 |
OM | +0.010 |
Neg logit contributions | |
Charlotte | -0.010 |
Becky | -0.010 |
Ruby | -0.009 |
Bonnie | -0.009 |
ricia | -0.009 |
Token | would |
Token ID | 561 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ount | +0.008 |
udd | +0.007 |
ll | +0.007 |
aris | +0.007 |
ari | +0.006 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
ricia | -0.009 |
pillow | -0.008 |
Ruby | -0.008 |
Token | celebrate |
Token ID | 10648 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
Charlotte | +0.021 |
Becky | +0.020 |
pillow | +0.020 |
Ruby | +0.019 |
veil | +0.019 |
Neg logit contributions | |
ount | -0.019 |
udd | -0.019 |
ll | -0.018 |
aris | -0.017 |
ari | -0.016 |
Token | when |
Token ID | 618 |
Feature activation | -8.74e-05 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
ricia | +0.003 |
pillow | +0.003 |
iflower | +0.002 |
Neg logit contributions | |
ount | -0.003 |
udd | -0.003 |
ll | -0.003 |
won | -0.003 |
aris | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
Charlotte | +0.000 |
ricia | +0.000 |
Becky | +0.000 |
iflower | +0.000 |
pillow | +0.000 |
Neg logit contributions | |
ount | -0.000 |
ll | -0.000 |
udd | -0.000 |
won | -0.000 |
aris | -0.000 |
Token | r |
Token ID | 374 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
ount | +0.014 |
udd | +0.014 |
ll | +0.014 |
arl | +0.013 |
aris | +0.013 |
Neg logit contributions | |
Becky | -0.009 |
Charlotte | -0.009 |
ricia | -0.009 |
creature | -0.008 |
Ruby | -0.008 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
pay | +0.107 |
des | +0.098 |
won | +0.092 |
inconvenience | +0.091 |
aren | +0.090 |
Neg logit contributions | |
sey | -0.133 |
bly | -0.131 |
ricia | -0.130 |
led | -0.127 |
ling | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.020 |
udd | +0.020 |
aris | +0.018 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.019 |
ricia | -0.018 |
Ruby | -0.018 |
pillow | -0.018 |
Token | because |
Token ID | 780 |
Feature activation | +9.25e-03 |
Pos logit contributions | |
ount | +0.025 |
ll | +0.025 |
udd | +0.024 |
aris | +0.023 |
ari | +0.022 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.019 |
Ruby | -0.018 |
pillow | -0.018 |
creature | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
ount | +0.015 |
ll | +0.015 |
udd | +0.015 |
won | +0.014 |
aris | +0.014 |
Neg logit contributions | |
ricia | -0.014 |
Charlotte | -0.013 |
Becky | -0.013 |
iflower | -0.013 |
pillow | -0.012 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
ount | +0.003 |
udd | +0.003 |
ll | +0.003 |
aris | +0.003 |
ari | +0.003 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
ricia | -0.004 |
pillow | -0.004 |
Ruby | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
Charlotte | +0.039 |
Becky | +0.038 |
ricia | +0.038 |
veil | +0.036 |
Bonnie | +0.036 |
Neg logit contributions | |
ll | -0.027 |
udd | -0.026 |
ount | -0.024 |
won | -0.023 |
aris | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | +6.19e-05 |
Pos logit contributions | |
Charlotte | +0.008 |
Becky | +0.008 |
ricia | +0.008 |
Bonnie | +0.007 |
therapist | +0.007 |
Neg logit contributions | |
udd | -0.010 |
ll | -0.010 |
ount | -0.010 |
won | -0.010 |
pay | -0.009 |
Token | stick |
Token ID | 4859 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ount | +0.000 |
ll | +0.000 |
udd | +0.000 |
aris | +0.000 |
ari | +0.000 |
Neg logit contributions | |
Charlotte | -0.000 |
Becky | -0.000 |
ricia | -0.000 |
pillow | -0.000 |
Ruby | -0.000 |
Token | when |
Token ID | 618 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
Charlotte | +0.022 |
Becky | +0.022 |
ricia | +0.022 |
pillow | +0.021 |
Ruby | +0.021 |
Neg logit contributions | |
ount | -0.021 |
ll | -0.020 |
udd | -0.020 |
aris | -0.018 |
won | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +9.06e-03 |
Pos logit contributions | |
ll | +0.009 |
ount | +0.009 |
udd | +0.009 |
won | +0.008 |
aris | +0.008 |
Neg logit contributions | |
Charlotte | -0.008 |
ricia | -0.008 |
Becky | -0.008 |
pillow | -0.007 |
Ruby | -0.007 |
Token | r |
Token ID | 374 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
ount | +0.017 |
ll | +0.016 |
udd | +0.016 |
aris | +0.016 |
ari | +0.015 |
Neg logit contributions | |
Becky | -0.011 |
Charlotte | -0.011 |
Ruby | -0.011 |
pillow | -0.011 |
ricia | -0.011 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
pay | +0.095 |
ount | +0.093 |
ari | +0.089 |
des | +0.088 |
won | +0.084 |
Neg logit contributions | |
ricia | -0.137 |
sey | -0.134 |
iflower | -0.134 |
lers | -0.133 |
cable | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-04 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.020 |
udd | +0.020 |
aris | +0.019 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.018 |
ricia | -0.017 |
pillow | -0.017 |
Ruby | -0.017 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ount | +0.001 |
ll | +0.001 |
udd | +0.001 |
lay | +0.001 |
aris | +0.001 |
Neg logit contributions | |
Becky | -0.001 |
Charlotte | -0.001 |
pillow | -0.001 |
Ruby | -0.001 |
ricia | -0.000 |
Token | would |
Token ID | 561 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
Charlotte | +0.020 |
Becky | +0.020 |
ricia | +0.018 |
Bonnie | +0.018 |
Ruby | +0.018 |
Neg logit contributions | |
ll | -0.018 |
udd | -0.018 |
won | -0.016 |
ount | -0.016 |
lay | -0.014 |
Token | put |
Token ID | 1234 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
Charlotte | +0.033 |
Becky | +0.033 |
pillow | +0.032 |
Ruby | +0.031 |
ricia | +0.031 |
Neg logit contributions | |
ount | -0.031 |
udd | -0.030 |
ll | -0.029 |
aris | -0.028 |
ari | -0.027 |
Token | next |
Token ID | 1306 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ount | +0.003 |
udd | +0.003 |
ll | +0.003 |
aris | +0.003 |
won | +0.002 |
Neg logit contributions | |
Charlotte | -0.002 |
Becky | -0.002 |
turkey | -0.002 |
ricia | -0.002 |
pillow | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
ount | +0.060 |
udd | +0.056 |
ll | +0.055 |
aris | +0.051 |
won | +0.049 |
Neg logit contributions | |
Charlotte | -0.056 |
Becky | -0.055 |
ricia | -0.054 |
pillow | -0.053 |
creature | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e-03 |
Pos logit contributions | |
Charlotte | +0.016 |
Becky | +0.016 |
Ruby | +0.015 |
pillow | +0.015 |
ricia | +0.015 |
Neg logit contributions | |
ount | -0.016 |
ll | -0.016 |
udd | -0.015 |
aris | -0.014 |
ari | -0.013 |
Token | when |
Token ID | 618 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
ricia | +0.003 |
iflower | +0.003 |
Charlotte | +0.003 |
Becky | +0.003 |
pillow | +0.003 |
Neg logit contributions | |
ount | -0.003 |
ll | -0.003 |
won | -0.003 |
udd | -0.003 |
pay | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
ricia | +0.008 |
iflower | +0.008 |
Charlotte | +0.008 |
rily | +0.008 |
Becky | +0.007 |
Neg logit contributions | |
won | -0.008 |
ll | -0.008 |
ount | -0.008 |
udd | -0.008 |
done | -0.008 |
Token | r |
Token ID | 374 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
ount | +0.009 |
ll | +0.008 |
udd | +0.008 |
aris | +0.008 |
won | +0.007 |
Neg logit contributions | |
Charlotte | -0.007 |
Becky | -0.007 |
ricia | -0.007 |
pillow | -0.006 |
Ruby | -0.006 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ount | +0.085 |
pay | +0.082 |
won | +0.081 |
des | +0.077 |
udd | +0.076 |
Neg logit contributions | |
ricia | -0.151 |
iflower | -0.146 |
Charlotte | -0.144 |
Becky | -0.143 |
cable | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | +7.58e-04 |
Pos logit contributions | |
ount | +0.020 |
udd | +0.019 |
ll | +0.019 |
won | +0.017 |
aris | +0.017 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.024 |
ricia | -0.024 |
iflower | -0.023 |
pillow | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-03 |
Pos logit contributions | |
won | +0.001 |
ount | +0.001 |
udd | +0.001 |
ll | +0.001 |
pay | +0.001 |
Neg logit contributions | |
ricia | -0.001 |
iflower | -0.001 |
Charlotte | -0.001 |
Becky | -0.001 |
pillow | -0.001 |
Token | lady |
Token ID | 10846 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ount | +0.003 |
ll | +0.003 |
udd | +0.003 |
aris | +0.003 |
ari | +0.002 |
Neg logit contributions | |
Charlotte | -0.002 |
veil | -0.002 |
pillow | -0.002 |
turkey | -0.002 |
ricia | -0.002 |
Token | used |
Token ID | 973 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
ount | +0.027 |
ll | +0.025 |
udd | +0.025 |
aris | +0.023 |
ari | +0.022 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.024 |
ricia | -0.023 |
pillow | -0.023 |
Ruby | -0.022 |
Token | while |
Token ID | 981 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
Becky | +0.000 |
pillow | +0.000 |
Charlotte | +0.000 |
creature | +0.000 |
veil | +0.000 |
Neg logit contributions | |
ount | -0.001 |
udd | -0.001 |
ll | -0.001 |
aris | -0.001 |
ari | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +9.16e-03 |
Pos logit contributions | |
Charlotte | +0.040 |
Becky | +0.039 |
ricia | +0.038 |
pillow | +0.037 |
Ruby | +0.036 |
Neg logit contributions | |
ount | -0.043 |
ll | -0.042 |
udd | -0.042 |
aris | -0.038 |
won | -0.037 |
Token | lightning |
Token ID | 14357 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ount | +0.015 |
ll | +0.014 |
udd | +0.014 |
aris | +0.013 |
ari | +0.013 |
Neg logit contributions | |
Charlotte | -0.014 |
Becky | -0.014 |
ricia | -0.014 |
pillow | -0.014 |
creature | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
ount | +0.038 |
ll | +0.037 |
udd | +0.037 |
aris | +0.034 |
ari | +0.033 |
Neg logit contributions | |
Charlotte | -0.030 |
Becky | -0.030 |
ricia | -0.029 |
pillow | -0.029 |
creature | -0.028 |
Token | thunder |
Token ID | 18355 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
ount | +0.010 |
udd | +0.010 |
ll | +0.010 |
won | +0.009 |
aris | +0.009 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
ricia | -0.009 |
pillow | -0.008 |
iflower | -0.008 |
Token | r |
Token ID | 374 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
ll | +0.067 |
ount | +0.067 |
udd | +0.064 |
aris | +0.061 |
ari | +0.060 |
Neg logit contributions | |
Charlotte | -0.055 |
Becky | -0.054 |
ricia | -0.052 |
pillow | -0.052 |
creature | -0.052 |
Token | umbled |
Token ID | 11137 |
Feature activation | +3.53e-03 |
Pos logit contributions | |
pay | +0.128 |
ari | +0.124 |
ount | +0.121 |
won | +0.121 |
des | +0.121 |
Neg logit contributions | |
sey | -0.107 |
led | -0.106 |
ricia | -0.104 |
bly | -0.101 |
frantically | -0.098 |
Token | outside |
Token ID | 2354 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
ount | +0.006 |
ll | +0.006 |
udd | +0.006 |
aris | +0.006 |
ari | +0.006 |
Neg logit contributions | |
Charlotte | -0.005 |
Becky | -0.005 |
ricia | -0.005 |
pillow | -0.005 |
Ruby | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
ount | +0.006 |
ll | +0.006 |
udd | +0.006 |
aris | +0.005 |
won | +0.005 |
Neg logit contributions | |
Charlotte | -0.006 |
Becky | -0.006 |
ricia | -0.006 |
pillow | -0.006 |
Ruby | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
ount | +0.003 |
ll | +0.003 |
udd | +0.003 |
ari | +0.003 |
aris | +0.003 |
Neg logit contributions | |
Charlotte | -0.003 |
Becky | -0.003 |
Ruby | -0.003 |
ricia | -0.003 |
Bonnie | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
ount | +0.040 |
udd | +0.040 |
ll | +0.039 |
aris | +0.034 |
ari | +0.033 |
Neg logit contributions | |
Charlotte | -0.052 |
Becky | -0.051 |
Ruby | -0.049 |
ricia | -0.048 |
pillow | -0.048 |
Token | keep |
Token ID | 1394 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ount | +0.021 |
udd | +0.021 |
ll | +0.020 |
aris | +0.019 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.022 |
Becky | -0.021 |
pillow | -0.021 |
Ruby | -0.020 |
veil | -0.020 |
Token | them |
Token ID | 606 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ricia | +0.047 |
Charlotte | +0.046 |
Becky | +0.046 |
pillow | +0.043 |
Ruby | +0.043 |
Neg logit contributions | |
ll | -0.054 |
udd | -0.054 |
ount | -0.054 |
won | -0.051 |
pay | -0.047 |
Token | dry |
Token ID | 5894 |
Feature activation | -5.06e-03 |
Pos logit contributions | |
Charlotte | +0.033 |
Becky | +0.033 |
ricia | +0.031 |
pillow | +0.031 |
Ruby | +0.030 |
Neg logit contributions | |
ount | -0.036 |
ll | -0.035 |
udd | -0.035 |
aris | -0.031 |
ari | -0.031 |
Token | when |
Token ID | 618 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
Charlotte | +0.008 |
Becky | +0.008 |
ricia | +0.008 |
pillow | +0.008 |
Ruby | +0.008 |
Neg logit contributions | |
ount | -0.008 |
udd | -0.008 |
ll | -0.008 |
aris | -0.007 |
won | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
ricia | +0.010 |
Charlotte | +0.010 |
Becky | +0.010 |
pillow | +0.009 |
Ruby | +0.009 |
Neg logit contributions | |
ll | -0.009 |
ount | -0.008 |
won | -0.008 |
udd | -0.008 |
done | -0.007 |
Token | r |
Token ID | 374 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
ount | +0.015 |
udd | +0.014 |
ll | +0.014 |
aris | +0.014 |
arl | +0.013 |
Neg logit contributions | |
Becky | -0.012 |
pillow | -0.011 |
Charlotte | -0.011 |
Ruby | -0.011 |
ricia | -0.011 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
pay | +0.094 |
des | +0.093 |
ount | +0.091 |
won | +0.088 |
ari | +0.088 |
Neg logit contributions | |
crib | -0.134 |
sey | -0.133 |
ricia | -0.128 |
cable | -0.128 |
iflower | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | +7.54e-03 |
Pos logit contributions | |
ount | +0.018 |
ll | +0.017 |
udd | +0.017 |
aris | +0.015 |
won | +0.015 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.019 |
ricia | -0.019 |
pillow | -0.018 |
Ruby | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
ount | +0.014 |
udd | +0.013 |
ll | +0.013 |
aris | +0.012 |
ari | +0.012 |
Neg logit contributions | |
Charlotte | -0.011 |
Becky | -0.011 |
pillow | -0.010 |
Ruby | -0.010 |
ricia | -0.010 |
Token | protect |
Token ID | 1805 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.021 |
udd | +0.021 |
aris | +0.019 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.025 |
Becky | -0.024 |
ricia | -0.023 |
pillow | -0.023 |
Ruby | -0.023 |
Token | them |
Token ID | 606 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
ricia | +0.014 |
Charlotte | +0.013 |
Becky | +0.013 |
iflower | +0.013 |
veil | +0.013 |
Neg logit contributions | |
ount | -0.013 |
won | -0.012 |
ll | -0.012 |
udd | -0.012 |
pay | -0.011 |
Token | together |
Token ID | 1978 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
Charlotte | +0.011 |
Becky | +0.010 |
Ruby | +0.010 |
pillow | +0.010 |
ricia | +0.010 |
Neg logit contributions | |
ount | -0.011 |
ll | -0.011 |
udd | -0.011 |
aris | -0.010 |
ari | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ount | +0.021 |
udd | +0.020 |
ll | +0.020 |
aris | +0.019 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.015 |
Becky | -0.015 |
Ruby | -0.014 |
pillow | -0.014 |
Bonnie | -0.013 |
Token | even |
Token ID | 772 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ount | +0.020 |
ll | +0.019 |
udd | +0.019 |
aris | +0.018 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.016 |
Becky | -0.016 |
Ruby | -0.015 |
pillow | -0.015 |
ricia | -0.014 |
Token | though |
Token ID | 996 |
Feature activation | -1.13e-03 |
Pos logit contributions | |
ount | +0.041 |
udd | +0.040 |
ll | +0.039 |
won | +0.035 |
aris | +0.035 |
Neg logit contributions | |
Charlotte | -0.056 |
Becky | -0.055 |
ricia | -0.054 |
pillow | -0.053 |
iflower | -0.052 |
Token | it |
Token ID | 340 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
ricia | +0.002 |
Becky | +0.002 |
iflower | +0.002 |
Charlotte | +0.002 |
rily | +0.002 |
Neg logit contributions | |
udd | -0.002 |
won | -0.002 |
ount | -0.002 |
ll | -0.002 |
done | -0.001 |
Token | r |
Token ID | 374 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
ll | +0.009 |
udd | +0.009 |
ount | +0.009 |
won | +0.009 |
aris | +0.008 |
Neg logit contributions | |
Charlotte | -0.008 |
Becky | -0.008 |
ricia | -0.008 |
pillow | -0.007 |
veil | -0.007 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
pay | +0.085 |
ount | +0.082 |
won | +0.076 |
ari | +0.074 |
des | +0.073 |
Neg logit contributions | |
ricia | -0.153 |
iflower | -0.149 |
Charlotte | -0.146 |
bly | -0.144 |
Becky | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
ount | +0.018 |
udd | +0.018 |
ll | +0.018 |
won | +0.016 |
aris | +0.016 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.018 |
ricia | -0.018 |
pillow | -0.017 |
iflower | -0.017 |
Token | The |
Token ID | 383 |
Feature activation | +7.75e-03 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
Ruby | +0.003 |
ricia | +0.003 |
pillow | +0.003 |
Neg logit contributions | |
ll | -0.003 |
ount | -0.003 |
udd | -0.002 |
aris | -0.002 |
ari | -0.002 |
Token | end |
Token ID | 886 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
ount | +0.014 |
ll | +0.014 |
udd | +0.014 |
aris | +0.013 |
won | +0.012 |
Neg logit contributions | |
Charlotte | -0.011 |
Becky | -0.010 |
ricia | -0.010 |
pillow | -0.010 |
Ruby | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
ount | +0.010 |
ll | +0.009 |
udd | +0.009 |
aris | +0.008 |
ari | +0.008 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
ricia | -0.008 |
pillow | -0.008 |
Ruby | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Charlotte | +0.010 |
Becky | +0.009 |
ricia | +0.009 |
iflower | +0.009 |
veil | +0.009 |
Neg logit contributions | |
ount | -0.010 |
udd | -0.010 |
won | -0.010 |
ll | -0.010 |
aris | -0.009 |
Token | car |
Token ID | 1097 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
ll | +0.024 |
ount | +0.023 |
udd | +0.023 |
aris | +0.022 |
lay | +0.020 |
Neg logit contributions | |
pillow | -0.013 |
creature | -0.013 |
cable | -0.012 |
wand | -0.012 |
radio | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
pillow | +0.004 |
cable | +0.004 |
Becky | +0.003 |
deeply | +0.003 |
frantically | +0.003 |
Neg logit contributions | |
ount | -0.008 |
ll | -0.008 |
udd | -0.008 |
aris | -0.007 |
lay | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
ount | +0.043 |
ll | +0.043 |
udd | +0.043 |
aris | +0.039 |
ari | +0.038 |
Neg logit contributions | |
Charlotte | -0.028 |
Becky | -0.027 |
pillow | -0.027 |
Ruby | -0.025 |
ricia | -0.025 |
Token | fire |
Token ID | 2046 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
ll | +0.020 |
ount | +0.020 |
udd | +0.019 |
aris | +0.019 |
ari | +0.017 |
Neg logit contributions | |
pillow | -0.012 |
creature | -0.012 |
cable | -0.011 |
wand | -0.011 |
crib | -0.011 |
Token | hyd |
Token ID | 7409 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
ount | +0.055 |
udd | +0.054 |
ll | +0.053 |
aris | +0.053 |
des | +0.052 |
Neg logit contributions | |
creature | -0.027 |
cable | -0.027 |
pillow | -0.027 |
flame | -0.026 |
wand | -0.025 |
Token | rant |
Token ID | 5250 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
ll | +0.187 |
unch | +0.186 |
aris | +0.182 |
lay | +0.181 |
ari | +0.177 |
Neg logit contributions | |
led | -0.053 |
le | -0.050 |
ricia | -0.050 |
ling | -0.048 |
ches | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ll | +0.007 |
ount | +0.007 |
udd | +0.007 |
ari | +0.007 |
aris | +0.007 |
Neg logit contributions | |
pillow | -0.005 |
Becky | -0.004 |
Charlotte | -0.004 |
creature | -0.004 |
crib | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ll | +0.026 |
ount | +0.024 |
udd | +0.023 |
ari | +0.022 |
lay | +0.021 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.018 |
Ruby | -0.017 |
Elsa | -0.016 |
pillow | -0.016 |
Token | take |
Token ID | 1011 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
ount | +0.022 |
udd | +0.021 |
aris | +0.021 |
ll | +0.021 |
ari | +0.019 |
Neg logit contributions | |
pillow | -0.022 |
Becky | -0.022 |
Charlotte | -0.021 |
veil | -0.021 |
wand | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
Charlotte | +0.010 |
Becky | +0.009 |
ricia | +0.009 |
pillow | +0.009 |
Ruby | +0.009 |
Neg logit contributions | |
ount | -0.015 |
ll | -0.015 |
udd | -0.015 |
aris | -0.014 |
ari | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | -9.97e-03 |
Pos logit contributions | |
ount | +0.005 |
ll | +0.005 |
udd | +0.005 |
aris | +0.004 |
won | +0.004 |
Neg logit contributions | |
Charlotte | -0.005 |
Becky | -0.005 |
ricia | -0.005 |
pillow | -0.005 |
Ruby | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
Charlotte | +0.013 |
ricia | +0.013 |
Becky | +0.013 |
pillow | +0.012 |
iflower | +0.012 |
Neg logit contributions | |
ll | -0.018 |
ount | -0.018 |
udd | -0.018 |
won | -0.016 |
aris | -0.016 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
Charlotte | +0.018 |
Becky | +0.017 |
ricia | +0.017 |
pillow | +0.017 |
Ruby | +0.016 |
Neg logit contributions | |
ll | -0.015 |
udd | -0.014 |
won | -0.014 |
ount | -0.013 |
paid | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
ount | +0.004 |
ll | +0.003 |
udd | +0.003 |
aris | +0.003 |
won | +0.003 |
Neg logit contributions | |
Charlotte | -0.006 |
Becky | -0.006 |
ricia | -0.006 |
pillow | -0.006 |
Ruby | -0.006 |
Token | take |
Token ID | 1011 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
ount | +0.006 |
udd | +0.006 |
ll | +0.006 |
won | +0.005 |
pay | +0.005 |
Neg logit contributions | |
Charlotte | -0.011 |
ricia | -0.011 |
Becky | -0.011 |
Ruby | -0.010 |
iflower | -0.010 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
Charlotte | +0.034 |
Becky | +0.034 |
ricia | +0.033 |
pillow | +0.032 |
iflower | +0.032 |
Neg logit contributions | |
ount | -0.038 |
udd | -0.037 |
ll | -0.036 |
aris | -0.034 |
won | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -4.20e-03 |
Pos logit contributions | |
ricia | +0.187 |
creature | +0.178 |
growth | +0.178 |
Charlotte | +0.175 |
unia | +0.174 |
Neg logit contributions | |
ll | -0.114 |
udd | -0.100 |
ount | -0.085 |
won | -0.081 |
pay | -0.080 |
Token | She |
Token ID | 1375 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
Ruby | +0.005 |
Bonnie | +0.005 |
pillow | +0.005 |
Neg logit contributions | |
ll | -0.009 |
ount | -0.008 |
udd | -0.008 |
inconvenience | -0.007 |
done | -0.007 |
Token | especially |
Token ID | 2592 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Charlotte | +0.021 |
Becky | +0.021 |
creature | +0.020 |
rily | +0.020 |
ricia | +0.020 |
Neg logit contributions | |
ll | -0.012 |
udd | -0.011 |
won | -0.011 |
paid | -0.010 |
bought | -0.009 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
udd | +0.030 |
won | +0.029 |
ount | +0.028 |
ll | +0.028 |
lay | +0.026 |
Neg logit contributions | |
Becky | -0.034 |
Charlotte | -0.034 |
ricia | -0.033 |
pillow | -0.032 |
creature | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
ount | +0.014 |
ll | +0.014 |
udd | +0.014 |
aris | +0.012 |
won | +0.012 |
Neg logit contributions | |
Charlotte | -0.027 |
Becky | -0.027 |
ricia | -0.026 |
pillow | -0.026 |
Ruby | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Charlotte | +0.017 |
Becky | +0.016 |
Ruby | +0.015 |
ricia | +0.015 |
pillow | +0.015 |
Neg logit contributions | |
ount | -0.018 |
ll | -0.018 |
udd | -0.017 |
aris | -0.016 |
won | -0.015 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
Becky | +0.020 |
Charlotte | +0.020 |
ricia | +0.019 |
Ruby | +0.019 |
iflower | +0.019 |
Neg logit contributions | |
ll | -0.016 |
udd | -0.016 |
won | -0.015 |
ount | -0.014 |
paid | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +5.47e-03 |
Pos logit contributions | |
Becky | +0.043 |
ricia | +0.043 |
Charlotte | +0.043 |
iflower | +0.042 |
rily | +0.042 |
Neg logit contributions | |
ll | -0.014 |
ount | -0.013 |
won | -0.013 |
udd | -0.013 |
aris | -0.011 |
Token | take |
Token ID | 1011 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
ount | +0.006 |
ll | +0.005 |
udd | +0.005 |
pay | +0.005 |
won | +0.005 |
Neg logit contributions | |
ricia | -0.011 |
Becky | -0.011 |
Charlotte | -0.011 |
iflower | -0.011 |
Ruby | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
Becky | +0.037 |
ricia | +0.036 |
iflower | +0.035 |
Charlotte | +0.035 |
rily | +0.033 |
Neg logit contributions | |
won | -0.047 |
udd | -0.047 |
ount | -0.047 |
ll | -0.044 |
pay | -0.044 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
Charlotte | +0.054 |
pillow | +0.053 |
Becky | +0.051 |
veil | +0.050 |
Ruby | +0.049 |
Neg logit contributions | |
ount | -0.055 |
udd | -0.051 |
ll | -0.050 |
aris | -0.046 |
won | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ricia | +0.163 |
growth | +0.152 |
Becky | +0.151 |
Charlotte | +0.150 |
creature | +0.149 |
Neg logit contributions | |
ll | -0.117 |
udd | -0.104 |
won | -0.099 |
ount | -0.096 |
come | -0.094 |
Token | Each |
Token ID | 5501 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
Charlotte | +0.021 |
Becky | +0.021 |
Ruby | +0.020 |
Bonnie | +0.019 |
pillow | +0.018 |
Neg logit contributions | |
ount | -0.023 |
udd | -0.022 |
ll | -0.022 |
ari | -0.019 |
inconvenience | -0.019 |
Token | day |
Token ID | 1110 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
Becky | +0.011 |
ricia | +0.011 |
iflower | +0.011 |
Charlotte | +0.011 |
Beck | +0.011 |
Neg logit contributions | |
won | -0.005 |
udd | -0.004 |
pay | -0.004 |
come | -0.004 |
ll | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
Charlotte | +0.058 |
Becky | +0.057 |
ricia | +0.056 |
pillow | +0.054 |
Ruby | +0.053 |
Neg logit contributions | |
ount | -0.067 |
udd | -0.065 |
ll | -0.065 |
aris | -0.059 |
won | -0.058 |
Token | would |
Token ID | 561 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
Charlotte | +0.020 |
Becky | +0.020 |
ricia | +0.019 |
Ruby | +0.019 |
iflower | +0.018 |
Neg logit contributions | |
ll | -0.012 |
udd | -0.012 |
won | -0.011 |
ount | -0.011 |
ari | -0.010 |
Token | rock |
Token ID | 3881 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Charlotte | +0.016 |
Becky | +0.016 |
ricia | +0.015 |
pillow | +0.015 |
Ruby | +0.014 |
Neg logit contributions | |
ount | -0.025 |
ll | -0.024 |
udd | -0.024 |
aris | -0.022 |
ari | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | -9.14e-04 |
Pos logit contributions | |
Charlotte | +0.022 |
Becky | +0.022 |
pillow | +0.021 |
ricia | +0.021 |
creature | +0.021 |
Neg logit contributions | |
ount | -0.025 |
ll | -0.025 |
udd | -0.025 |
aris | -0.022 |
won | -0.022 |
Token | he |
Token ID | 339 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Charlotte | +0.001 |
Becky | +0.001 |
ricia | +0.001 |
pillow | +0.001 |
Ruby | +0.001 |
Neg logit contributions | |
ount | -0.001 |
ll | -0.001 |
udd | -0.001 |
won | -0.001 |
aris | -0.001 |
Token | could |
Token ID | 714 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Charlotte | +0.042 |
Becky | +0.041 |
ricia | +0.040 |
Ruby | +0.039 |
pillow | +0.039 |
Neg logit contributions | |
ll | -0.031 |
udd | -0.030 |
won | -0.029 |
ount | -0.029 |
aris | -0.025 |
Token | take |
Token ID | 1011 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
Charlotte | +0.042 |
ricia | +0.042 |
Becky | +0.041 |
Ruby | +0.039 |
Bonnie | +0.039 |
Neg logit contributions | |
ount | -0.026 |
ll | -0.026 |
udd | -0.024 |
pay | -0.024 |
won | -0.023 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
Charlotte | +0.025 |
Becky | +0.024 |
ricia | +0.023 |
pillow | +0.022 |
Ruby | +0.022 |
Neg logit contributions | |
ount | -0.039 |
ll | -0.038 |
udd | -0.038 |
aris | -0.035 |
ari | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -6.02e-03 |
Pos logit contributions | |
ricia | +0.152 |
Charlotte | +0.147 |
Becky | +0.141 |
unia | +0.138 |
turkey | +0.136 |
Neg logit contributions | |
ll | -0.122 |
udd | -0.114 |
ount | -0.111 |
won | -0.107 |
pay | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | -8.37e-04 |
Pos logit contributions | |
Charlotte | +0.011 |
Becky | +0.011 |
ricia | +0.010 |
pillow | +0.010 |
Ruby | +0.010 |
Neg logit contributions | |
ount | -0.008 |
udd | -0.008 |
ll | -0.008 |
aris | -0.007 |
won | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -8.23e-03 |
Pos logit contributions | |
Charlotte | +0.002 |
Becky | +0.002 |
ricia | +0.002 |
pillow | +0.002 |
Ruby | +0.002 |
Neg logit contributions | |
ount | -0.001 |
ll | -0.001 |
udd | -0.001 |
aris | -0.001 |
won | -0.001 |
Token | One |
Token ID | 3198 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Charlotte | +0.014 |
Becky | +0.013 |
ricia | +0.013 |
pillow | +0.013 |
Ruby | +0.012 |
Neg logit contributions | |
ount | -0.013 |
ll | -0.013 |
udd | -0.012 |
won | -0.011 |
aris | -0.011 |
Token | night |
Token ID | 1755 |
Feature activation | -4.84e-03 |
Pos logit contributions | |
ount | +0.035 |
ll | +0.034 |
udd | +0.034 |
aris | +0.030 |
won | +0.029 |
Neg logit contributions | |
Charlotte | -0.050 |
Becky | -0.049 |
ricia | -0.048 |
pillow | -0.047 |
Ruby | -0.047 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Charlotte | +0.010 |
Becky | +0.010 |
ricia | +0.010 |
pillow | +0.010 |
Ruby | +0.010 |
Neg logit contributions | |
ount | -0.009 |
ll | -0.009 |
udd | -0.009 |
aris | -0.008 |
won | -0.007 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
Charlotte | +0.024 |
Becky | +0.024 |
iflower | +0.023 |
creature | +0.023 |
ricia | +0.022 |
Neg logit contributions | |
udd | -0.023 |
ll | -0.022 |
won | -0.022 |
ount | -0.021 |
aris | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
ount | +0.016 |
udd | +0.016 |
ll | +0.016 |
aris | +0.014 |
won | +0.014 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.018 |
ricia | -0.018 |
iflower | -0.017 |
pillow | -0.017 |
Token | take |
Token ID | 1011 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
pay | +0.008 |
ount | +0.008 |
come | +0.008 |
udd | +0.008 |
won | +0.007 |
Neg logit contributions | |
ricia | -0.015 |
Charlotte | -0.015 |
iflower | -0.015 |
Becky | -0.015 |
creature | -0.014 |
Token | Anna |
Token ID | 11735 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
Becky | +0.023 |
Charlotte | +0.022 |
ricia | +0.022 |
iflower | +0.022 |
frantically | +0.021 |
Neg logit contributions | |
ount | -0.031 |
udd | -0.030 |
ll | -0.028 |
won | -0.028 |
aris | -0.028 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
Becky | +0.056 |
Charlotte | +0.055 |
ricia | +0.055 |
iflower | +0.052 |
creature | +0.051 |
Neg logit contributions | |
ount | -0.065 |
ll | -0.064 |
udd | -0.064 |
won | -0.058 |
aris | -0.058 |
Token | she |
Token ID | 673 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
ricia | +0.175 |
growth | +0.166 |
unia | +0.166 |
creature | +0.164 |
Charlotte | +0.163 |
Neg logit contributions | |
ll | -0.108 |
udd | -0.093 |
ount | -0.089 |
come | -0.085 |
won | -0.080 |
Token | went |
Token ID | 1816 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ount | +0.006 |
ll | +0.006 |
udd | +0.005 |
aris | +0.005 |
arl | +0.005 |
Neg logit contributions | |
Charlotte | -0.005 |
Becky | -0.005 |
pillow | -0.005 |
ricia | -0.005 |
creature | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e-04 |
Pos logit contributions | |
ount | +0.033 |
ll | +0.032 |
udd | +0.032 |
aris | +0.029 |
won | +0.028 |
Neg logit contributions | |
Charlotte | -0.030 |
Becky | -0.029 |
ricia | -0.028 |
pillow | -0.028 |
Ruby | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
ount | +0.000 |
ll | +0.000 |
udd | +0.000 |
aris | +0.000 |
ari | +0.000 |
Neg logit contributions | |
Charlotte | -0.000 |
Becky | -0.000 |
Ruby | -0.000 |
ricia | -0.000 |
pillow | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Charlotte | +0.012 |
Becky | +0.012 |
ricia | +0.012 |
pillow | +0.012 |
Ruby | +0.011 |
Neg logit contributions | |
ount | -0.007 |
ll | -0.007 |
udd | -0.007 |
aris | -0.006 |
won | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -1.88e-03 |
Pos logit contributions | |
Becky | +0.008 |
Charlotte | +0.008 |
Ruby | +0.007 |
Alexa | +0.007 |
Louise | +0.007 |
Neg logit contributions | |
ll | -0.012 |
udd | -0.012 |
ount | -0.011 |
lay | -0.011 |
arl | -0.010 |
Token | used |
Token ID | 973 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
ricia | +0.003 |
pillow | +0.003 |
iflower | +0.003 |
Neg logit contributions | |
ll | -0.003 |
udd | -0.003 |
ount | -0.003 |
won | -0.003 |
ari | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ricia | +0.041 |
Charlotte | +0.040 |
Becky | +0.038 |
iflower | +0.037 |
unia | +0.036 |
Neg logit contributions | |
ount | -0.052 |
udd | -0.051 |
ll | -0.051 |
won | -0.051 |
aris | -0.048 |
Token | take |
Token ID | 1011 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ount | +0.022 |
ll | +0.021 |
udd | +0.021 |
aris | +0.019 |
won | +0.019 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.024 |
ricia | -0.023 |
pillow | -0.022 |
Ruby | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
Charlotte | +0.023 |
Becky | +0.023 |
ricia | +0.022 |
pillow | +0.022 |
iflower | +0.021 |
Neg logit contributions | |
ount | -0.026 |
udd | -0.026 |
ll | -0.025 |
aris | -0.024 |
won | -0.024 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
Charlotte | +0.037 |
Becky | +0.037 |
pillow | +0.036 |
Ruby | +0.034 |
creature | +0.034 |
Neg logit contributions | |
ount | -0.045 |
udd | -0.043 |
ll | -0.042 |
aris | -0.037 |
OM | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
ricia | +0.135 |
Charlotte | +0.133 |
Becky | +0.131 |
pillow | +0.127 |
creature | +0.125 |
Neg logit contributions | |
ll | -0.132 |
udd | -0.128 |
ount | -0.126 |
won | -0.116 |
aris | -0.112 |
Token | went |
Token ID | 1816 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ount | +0.008 |
ll | +0.008 |
udd | +0.008 |
aris | +0.007 |
arl | +0.007 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
ricia | -0.009 |
pillow | -0.009 |
creature | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
ount | +0.028 |
ll | +0.028 |
udd | +0.028 |
aris | +0.025 |
won | +0.024 |
Neg logit contributions | |
Charlotte | -0.027 |
Becky | -0.026 |
ricia | -0.025 |
pillow | -0.025 |
creature | -0.025 |
Token | sail |
Token ID | 14936 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ount | +0.007 |
ll | +0.007 |
udd | +0.007 |
won | +0.007 |
aris | +0.006 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
ricia | -0.009 |
pillow | -0.009 |
iflower | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
ount | +0.023 |
ll | +0.022 |
udd | +0.022 |
aris | +0.020 |
won | +0.020 |
Neg logit contributions | |
Charlotte | -0.017 |
Becky | -0.016 |
ricia | -0.016 |
pillow | -0.015 |
Ruby | -0.015 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
Becky | +0.016 |
ricia | +0.016 |
rily | +0.015 |
Charlotte | +0.015 |
led | +0.015 |
Neg logit contributions | |
won | -0.015 |
udd | -0.014 |
ll | -0.014 |
pay | -0.013 |
come | -0.013 |
Token | wallet |
Token ID | 13008 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
ricia | +0.010 |
Becky | +0.010 |
Charlotte | +0.009 |
Beck | +0.009 |
Ruby | +0.009 |
Neg logit contributions | |
udd | -0.011 |
won | -0.011 |
come | -0.011 |
ll | -0.010 |
done | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | -3.79e-03 |
Pos logit contributions | |
Becky | +0.006 |
Charlotte | +0.006 |
ricia | +0.006 |
Ruby | +0.006 |
Bonnie | +0.005 |
Neg logit contributions | |
ll | -0.006 |
udd | -0.006 |
ount | -0.006 |
ari | -0.006 |
won | -0.005 |
Token | he |
Token ID | 339 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
pillow | +0.005 |
Ruby | +0.005 |
Neg logit contributions | |
ount | -0.007 |
ll | -0.006 |
udd | -0.006 |
won | -0.006 |
aris | -0.006 |
Token | carried |
Token ID | 5281 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
Charlotte | +0.037 |
Becky | +0.037 |
ricia | +0.035 |
Ruby | +0.035 |
pillow | +0.034 |
Neg logit contributions | |
ll | -0.030 |
udd | -0.029 |
won | -0.029 |
ount | -0.027 |
paid | -0.025 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
Charlotte | +0.044 |
Becky | +0.044 |
ricia | +0.043 |
pillow | +0.041 |
iflower | +0.040 |
Neg logit contributions | |
ount | -0.059 |
ll | -0.058 |
udd | -0.058 |
aris | -0.054 |
won | -0.054 |
Token | with |
Token ID | 351 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ricia | +0.156 |
Charlotte | +0.153 |
Becky | +0.148 |
unia | +0.142 |
pillow | +0.141 |
Neg logit contributions | |
ll | -0.115 |
udd | -0.103 |
ount | -0.102 |
won | -0.097 |
aris | -0.093 |
Token | him |
Token ID | 683 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
Charlotte | +0.042 |
Becky | +0.041 |
ricia | +0.041 |
Ruby | +0.038 |
pillow | +0.038 |
Neg logit contributions | |
ount | -0.052 |
udd | -0.051 |
ll | -0.051 |
aris | -0.047 |
won | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
Charlotte | +0.020 |
Becky | +0.019 |
pillow | +0.018 |
ricia | +0.018 |
Ruby | +0.018 |
Neg logit contributions | |
ount | -0.021 |
udd | -0.020 |
ll | -0.020 |
aris | -0.018 |
ari | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -3.45e-03 |
Pos logit contributions | |
Becky | +0.009 |
Charlotte | +0.008 |
ricia | +0.008 |
Ruby | +0.008 |
pillow | +0.008 |
Neg logit contributions | |
udd | -0.010 |
ll | -0.010 |
ount | -0.010 |
ari | -0.008 |
aris | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Becky | +0.006 |
Charlotte | +0.006 |
ricia | +0.005 |
Ruby | +0.005 |
idi | +0.005 |
Neg logit contributions | |
ount | -0.005 |
udd | -0.005 |
ll | -0.005 |
aris | -0.004 |
ari | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | -4.64e-03 |
Pos logit contributions | |
Becky | +0.007 |
ricia | +0.007 |
Charlotte | +0.007 |
Bonnie | +0.007 |
frantically | +0.007 |
Neg logit contributions | |
udd | -0.006 |
ll | -0.006 |
ount | -0.006 |
ari | -0.006 |
won | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
Charlotte | +0.006 |
ricia | +0.006 |
Becky | +0.006 |
frantically | +0.006 |
iflower | +0.006 |
Neg logit contributions | |
ll | -0.008 |
ount | -0.008 |
udd | -0.008 |
won | -0.007 |
aris | -0.007 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
Charlotte | +0.018 |
Becky | +0.018 |
ricia | +0.017 |
Ruby | +0.017 |
turkey | +0.017 |
Neg logit contributions | |
ll | -0.016 |
udd | -0.015 |
won | -0.015 |
ount | -0.014 |
paid | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +3.51e-03 |
Pos logit contributions | |
ount | +0.005 |
ll | +0.004 |
udd | +0.004 |
aris | +0.004 |
won | +0.004 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
ricia | -0.004 |
pillow | -0.004 |
Ruby | -0.004 |
Token | carry |
Token ID | 3283 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
ount | +0.005 |
ll | +0.005 |
udd | +0.005 |
aris | +0.004 |
won | +0.004 |
Neg logit contributions | |
Charlotte | -0.006 |
Becky | -0.006 |
ricia | -0.006 |
Ruby | -0.006 |
pillow | -0.006 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
Becky | +0.074 |
ricia | +0.073 |
Charlotte | +0.073 |
comet | +0.069 |
iflower | +0.069 |
Neg logit contributions | |
ount | -0.055 |
udd | -0.055 |
ll | -0.053 |
won | -0.049 |
aris | -0.048 |
Token | she |
Token ID | 673 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
ricia | +0.178 |
creature | +0.171 |
growth | +0.168 |
unia | +0.167 |
Charlotte | +0.166 |
Neg logit contributions | |
ll | -0.089 |
udd | -0.078 |
won | -0.065 |
ount | -0.064 |
aris | -0.063 |
Token | went |
Token ID | 1816 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Charlotte | +0.004 |
pillow | +0.004 |
Becky | +0.004 |
creature | +0.004 |
ricia | +0.004 |
Neg logit contributions | |
ount | -0.005 |
ll | -0.005 |
udd | -0.005 |
arl | -0.004 |
aris | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.020 |
udd | +0.020 |
aris | +0.018 |
won | +0.018 |
Neg logit contributions | |
Charlotte | -0.022 |
Becky | -0.022 |
ricia | -0.021 |
pillow | -0.021 |
Ruby | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
ricia | +0.003 |
Ruby | +0.003 |
pillow | +0.003 |
Neg logit contributions | |
ount | -0.003 |
ll | -0.003 |
udd | -0.003 |
aris | -0.003 |
ari | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
udd | +0.016 |
ll | +0.016 |
ount | +0.014 |
ari | +0.013 |
won | +0.013 |
Neg logit contributions | |
Becky | -0.038 |
Charlotte | -0.038 |
ricia | -0.037 |
rily | -0.036 |
frantically | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
Becky | +0.002 |
Charlotte | +0.002 |
pillow | +0.002 |
Ruby | +0.002 |
cable | +0.002 |
Neg logit contributions | |
ll | -0.004 |
ount | -0.004 |
udd | -0.004 |
ari | -0.003 |
lay | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Charlotte | +0.018 |
Becky | +0.018 |
ricia | +0.017 |
Ruby | +0.016 |
Bonnie | +0.016 |
Neg logit contributions | |
ll | -0.015 |
udd | -0.015 |
won | -0.014 |
ount | -0.013 |
paid | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
Becky | +0.042 |
Charlotte | +0.042 |
ricia | +0.041 |
Bonnie | +0.039 |
iflower | +0.039 |
Neg logit contributions | |
ll | -0.014 |
ount | -0.014 |
udd | -0.014 |
won | -0.013 |
aris | -0.012 |
Token | take |
Token ID | 1011 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ount | +0.005 |
ll | +0.004 |
udd | +0.004 |
aris | +0.004 |
won | +0.004 |
Neg logit contributions | |
Charlotte | -0.006 |
Becky | -0.006 |
ricia | -0.006 |
pillow | -0.006 |
Ruby | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
Becky | +0.030 |
Charlotte | +0.030 |
ricia | +0.029 |
iflower | +0.027 |
pillow | +0.027 |
Neg logit contributions | |
ount | -0.051 |
udd | -0.051 |
ll | -0.050 |
won | -0.048 |
aris | -0.047 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
pillow | +0.049 |
Charlotte | +0.048 |
veil | +0.045 |
Becky | +0.045 |
Ruby | +0.044 |
Neg logit contributions | |
ount | -0.060 |
udd | -0.054 |
ll | -0.053 |
aris | -0.049 |
lay | -0.047 |
Token | she |
Token ID | 673 |
Feature activation | -6.90e-04 |
Pos logit contributions | |
ricia | +0.154 |
Becky | +0.148 |
creature | +0.146 |
Charlotte | +0.146 |
growth | +0.144 |
Neg logit contributions | |
ll | -0.115 |
udd | -0.106 |
ount | -0.098 |
won | -0.096 |
done | -0.089 |
Token | went |
Token ID | 1816 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Charlotte | +0.001 |
pillow | +0.001 |
Becky | +0.001 |
creature | +0.001 |
ricia | +0.001 |
Neg logit contributions | |
ount | -0.001 |
ll | -0.001 |
udd | -0.001 |
arl | -0.001 |
aris | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.021 |
udd | +0.021 |
aris | +0.019 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.020 |
pillow | -0.019 |
ricia | -0.019 |
Ruby | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -6.67e-03 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
Ruby | +0.005 |
pillow | +0.005 |
ricia | +0.005 |
Neg logit contributions | |
ount | -0.008 |
ll | -0.007 |
udd | -0.007 |
arl | -0.006 |
inconvenience | -0.006 |
Token | hopped |
Token ID | 45230 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
Becky | +0.013 |
Charlotte | +0.013 |
iflower | +0.012 |
ricia | +0.012 |
creature | +0.012 |
Neg logit contributions | |
ll | -0.008 |
udd | -0.008 |
won | -0.007 |
ount | -0.007 |
lay | -0.007 |
Token | most |
Token ID | 749 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.004 |
pillow | +0.004 |
ricia | +0.004 |
Ruby | +0.004 |
Neg logit contributions | |
ount | -0.007 |
udd | -0.007 |
ll | -0.007 |
aris | -0.007 |
ari | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
udd | +0.015 |
ount | +0.014 |
ll | +0.014 |
aris | +0.013 |
won | +0.013 |
Neg logit contributions | |
Charlotte | -0.017 |
Becky | -0.017 |
ricia | -0.016 |
Ruby | -0.016 |
pillow | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | +4.35e-03 |
Pos logit contributions | |
Charlotte | +0.010 |
Becky | +0.010 |
Ruby | +0.009 |
pillow | +0.009 |
ricia | +0.009 |
Neg logit contributions | |
ll | -0.008 |
ount | -0.008 |
udd | -0.008 |
aris | -0.007 |
ari | -0.007 |
Token | took |
Token ID | 1718 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
ll | +0.006 |
udd | +0.006 |
won | +0.006 |
ount | +0.005 |
paid | +0.005 |
Neg logit contributions | |
Charlotte | -0.008 |
Becky | -0.008 |
iflower | -0.008 |
ricia | -0.008 |
creature | -0.008 |
Token | him |
Token ID | 683 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
iflower | +0.025 |
ricia | +0.025 |
Charlotte | +0.024 |
Becky | +0.023 |
fish | +0.022 |
Neg logit contributions | |
ount | -0.032 |
won | -0.031 |
udd | -0.031 |
aris | -0.029 |
pay | -0.029 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
Charlotte | +0.026 |
Becky | +0.026 |
ricia | +0.025 |
pillow | +0.025 |
Ruby | +0.024 |
Neg logit contributions | |
ount | -0.020 |
udd | -0.020 |
ll | -0.020 |
aris | -0.017 |
won | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ricia | +0.147 |
Charlotte | +0.140 |
unia | +0.138 |
Becky | +0.136 |
creature | +0.134 |
Neg logit contributions | |
ll | -0.122 |
udd | -0.115 |
ount | -0.111 |
won | -0.105 |
come | -0.102 |
Token | her |
Token ID | 607 |
Feature activation | +2.72e-03 |
Pos logit contributions | |
ricia | +0.030 |
iflower | +0.028 |
worm | +0.027 |
Becky | +0.027 |
creature | +0.026 |
Neg logit contributions | |
come | -0.035 |
ount | -0.035 |
udd | -0.034 |
pay | -0.034 |
won | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
ll | +0.005 |
udd | +0.004 |
won | +0.004 |
ount | +0.004 |
aris | +0.004 |
Neg logit contributions | |
ricia | -0.004 |
Charlotte | -0.004 |
Becky | -0.004 |
idi | -0.004 |
iflower | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
ricia | +0.003 |
Ruby | +0.003 |
pillow | +0.003 |
Neg logit contributions | |
ount | -0.002 |
ll | -0.002 |
udd | -0.002 |
aris | -0.002 |
won | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
ll | +0.007 |
udd | +0.007 |
won | +0.007 |
ount | +0.006 |
paid | +0.006 |
Neg logit contributions | |
Charlotte | -0.010 |
Becky | -0.010 |
iflower | -0.010 |
ricia | -0.009 |
creature | -0.009 |
Token | toy |
Token ID | 13373 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
ricia | +0.036 |
Charlotte | +0.036 |
Becky | +0.035 |
Beck | +0.033 |
Ruby | +0.033 |
Neg logit contributions | |
udd | -0.035 |
won | -0.033 |
ount | -0.031 |
come | -0.031 |
ari | -0.030 |
Token | bunny |
Token ID | 44915 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
ricia | +0.083 |
Charlotte | +0.082 |
Becky | +0.081 |
Bonnie | +0.075 |
iflower | +0.075 |
Neg logit contributions | |
ount | -0.061 |
ll | -0.060 |
udd | -0.060 |
ari | -0.057 |
won | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
ricia | +0.067 |
Becky | +0.066 |
Charlotte | +0.064 |
idi | +0.062 |
frantically | +0.060 |
Neg logit contributions | |
ll | -0.033 |
udd | -0.032 |
ount | -0.032 |
won | -0.030 |
ari | -0.028 |
Token | she |
Token ID | 673 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ricia | +0.014 |
frantically | +0.014 |
rily | +0.014 |
Charlotte | +0.014 |
Becky | +0.013 |
Neg logit contributions | |
ll | -0.013 |
won | -0.013 |
udd | -0.013 |
ount | -0.013 |
paid | -0.012 |
Token | carried |
Token ID | 5281 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
Becky | +0.024 |
Charlotte | +0.024 |
ricia | +0.024 |
pillow | +0.023 |
rily | +0.023 |
Neg logit contributions | |
ll | -0.019 |
won | -0.018 |
udd | -0.017 |
ount | -0.016 |
paid | -0.016 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
ricia | +0.054 |
Becky | +0.053 |
iflower | +0.052 |
Charlotte | +0.052 |
comet | +0.051 |
Neg logit contributions | |
ount | -0.049 |
ll | -0.047 |
udd | -0.045 |
won | -0.045 |
aris | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
ricia | +0.179 |
Charlotte | +0.169 |
unia | +0.165 |
creature | +0.165 |
growth | +0.165 |
Neg logit contributions | |
ll | -0.095 |
udd | -0.080 |
ount | -0.071 |
won | -0.070 |
come | -0.070 |
Token | Every |
Token ID | 3887 |
Feature activation | -3.18e-03 |
Pos logit contributions | |
Charlotte | +0.014 |
Becky | +0.013 |
ricia | +0.013 |
pillow | +0.013 |
Ruby | +0.013 |
Neg logit contributions | |
ount | -0.012 |
ll | -0.012 |
udd | -0.012 |
aris | -0.011 |
won | -0.010 |
Token | night |
Token ID | 1755 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
rily | +0.008 |
Becky | +0.008 |
ricia | +0.008 |
bly | +0.008 |
Charlotte | +0.008 |
Neg logit contributions | |
ll | -0.001 |
won | -0.001 |
udd | -0.001 |
come | -0.001 |
done | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
Charlotte | +0.035 |
Becky | +0.035 |
ricia | +0.034 |
pillow | +0.033 |
Ruby | +0.033 |
Neg logit contributions | |
ount | -0.030 |
ll | -0.030 |
udd | -0.029 |
aris | -0.026 |
won | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ricia | +0.022 |
iflower | +0.021 |
frantically | +0.021 |
unia | +0.020 |
creature | +0.020 |
Neg logit contributions | |
won | -0.014 |
come | -0.014 |
ount | -0.014 |
parties | -0.014 |
udd | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
ount | +0.003 |
ll | +0.003 |
udd | +0.003 |
aris | +0.002 |
ari | +0.002 |
Neg logit contributions | |
Charlotte | -0.002 |
Becky | -0.002 |
ricia | -0.002 |
Ruby | -0.002 |
pillow | -0.002 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
Becky | +0.014 |
Charlotte | +0.013 |
iflower | +0.013 |
creature | +0.013 |
rily | +0.013 |
Neg logit contributions | |
udd | -0.012 |
ll | -0.012 |
won | -0.011 |
ount | -0.010 |
lay | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
ll | +0.016 |
udd | +0.016 |
ount | +0.015 |
won | +0.014 |
aris | +0.014 |
Neg logit contributions | |
Becky | -0.031 |
ricia | -0.031 |
iflower | -0.031 |
Charlotte | -0.031 |
creature | -0.030 |
Token | bring |
Token ID | 2222 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ount | +0.010 |
udd | +0.009 |
ll | +0.009 |
pay | +0.009 |
won | +0.009 |
Neg logit contributions | |
Charlotte | -0.018 |
iflower | -0.018 |
Becky | -0.018 |
ricia | -0.018 |
creature | -0.017 |
Token | Anna |
Token ID | 11735 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
iflower | +0.030 |
frantically | +0.027 |
worm | +0.027 |
ricia | +0.027 |
creature | +0.026 |
Neg logit contributions | |
parties | -0.033 |
udd | -0.033 |
won | -0.032 |
ount | -0.032 |
aris | -0.032 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
ricia | +0.074 |
iflower | +0.071 |
Charlotte | +0.070 |
Becky | +0.069 |
frantically | +0.067 |
Neg logit contributions | |
udd | -0.068 |
ount | -0.068 |
ll | -0.067 |
won | -0.065 |
aris | -0.064 |
Token | she |
Token ID | 673 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ricia | +0.147 |
growth | +0.141 |
Charlotte | +0.139 |
creature | +0.139 |
unia | +0.138 |
Neg logit contributions | |
ll | -0.115 |
udd | -0.106 |
won | -0.100 |
ount | -0.100 |
come | -0.094 |
Token | went |
Token ID | 1816 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ount | +0.021 |
ll | +0.021 |
udd | +0.021 |
aris | +0.018 |
arl | +0.018 |
Neg logit contributions | |
Charlotte | -0.021 |
Becky | -0.021 |
pillow | -0.021 |
ricia | -0.020 |
Ruby | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
ount | +0.031 |
ll | +0.030 |
udd | +0.030 |
aris | +0.027 |
won | +0.026 |
Neg logit contributions | |
Charlotte | -0.030 |
Becky | -0.029 |
ricia | -0.028 |
pillow | -0.028 |
Ruby | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
ount | +0.005 |
ll | +0.005 |
udd | +0.005 |
aris | +0.004 |
ari | +0.004 |
Neg logit contributions | |
Charlotte | -0.006 |
Becky | -0.006 |
ricia | -0.006 |
Ruby | -0.006 |
pillow | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.35e-04 |
Pos logit contributions | |
ount | +0.009 |
udd | +0.009 |
ll | +0.009 |
aris | +0.008 |
won | +0.008 |
Neg logit contributions | |
Charlotte | -0.012 |
Becky | -0.012 |
ricia | -0.012 |
Ruby | -0.012 |
pillow | -0.012 |
Token | new |
Token ID | 649 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
udd | +0.009 |
ll | +0.009 |
ount | +0.009 |
won | +0.009 |
aris | +0.008 |
Neg logit contributions | |
Becky | -0.009 |
Charlotte | -0.009 |
ricia | -0.009 |
iflower | -0.009 |
rily | -0.009 |
Token | best |
Token ID | 1266 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
Becky | +0.016 |
ricia | +0.016 |
Charlotte | +0.015 |
iflower | +0.015 |
rily | +0.015 |
Neg logit contributions | |
udd | -0.010 |
won | -0.010 |
ll | -0.009 |
pay | -0.008 |
ari | -0.008 |
Token | friend |
Token ID | 1545 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
udd | +0.003 |
ount | +0.003 |
ll | +0.003 |
aris | +0.003 |
won | +0.003 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
ricia | -0.004 |
Ruby | -0.004 |
iflower | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
Charlotte | +0.042 |
Becky | +0.041 |
ricia | +0.039 |
pillow | +0.039 |
Ruby | +0.039 |
Neg logit contributions | |
ount | -0.043 |
udd | -0.042 |
ll | -0.041 |
aris | -0.037 |
lay | -0.036 |
Token | took |
Token ID | 1718 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
Charlotte | +0.015 |
Becky | +0.015 |
ricia | +0.014 |
pillow | +0.014 |
Ruby | +0.014 |
Neg logit contributions | |
ll | -0.015 |
ount | -0.015 |
udd | -0.015 |
won | -0.013 |
aris | -0.013 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
Charlotte | +0.024 |
Becky | +0.023 |
ricia | +0.023 |
pillow | +0.022 |
Ruby | +0.021 |
Neg logit contributions | |
ount | -0.027 |
ll | -0.027 |
udd | -0.027 |
aris | -0.024 |
won | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
ricia | +0.153 |
Charlotte | +0.146 |
pillow | +0.141 |
Becky | +0.141 |
veil | +0.139 |
Neg logit contributions | |
ll | -0.117 |
udd | -0.103 |
ount | -0.101 |
won | -0.099 |
aris | -0.091 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
Charlotte | +0.012 |
Becky | +0.012 |
ricia | +0.012 |
pillow | +0.011 |
Ruby | +0.011 |
Neg logit contributions | |
ount | -0.013 |
udd | -0.013 |
ll | -0.013 |
aris | -0.011 |
won | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
Charlotte | +0.049 |
ricia | +0.048 |
Becky | +0.048 |
pillow | +0.047 |
Ruby | +0.045 |
Neg logit contributions | |
ll | -0.055 |
ount | -0.054 |
udd | -0.054 |
won | -0.050 |
aris | -0.049 |
Token | went |
Token ID | 1816 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Charlotte | +0.053 |
Becky | +0.053 |
ricia | +0.051 |
Ruby | +0.050 |
pillow | +0.050 |
Neg logit contributions | |
ll | -0.038 |
udd | -0.038 |
ount | -0.038 |
won | -0.034 |
aris | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
ount | +0.039 |
ll | +0.038 |
udd | +0.038 |
aris | +0.034 |
won | +0.034 |
Neg logit contributions | |
Charlotte | -0.048 |
Becky | -0.048 |
ricia | -0.047 |
pillow | -0.046 |
Ruby | -0.045 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.74e-04 |
Pos logit contributions | |
ll | +0.002 |
udd | +0.002 |
ount | +0.002 |
won | +0.002 |
come | +0.002 |
Neg logit contributions | |
ricia | -0.003 |
creature | -0.003 |
iflower | -0.002 |
Becky | -0.002 |
frantically | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
ricia | +0.001 |
Becky | +0.001 |
Charlotte | +0.001 |
iflower | +0.000 |
rily | +0.000 |
Neg logit contributions | |
ll | -0.000 |
udd | -0.000 |
ount | -0.000 |
won | -0.000 |
ari | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
ount | +0.004 |
udd | +0.004 |
ll | +0.004 |
aris | +0.004 |
won | +0.004 |
Neg logit contributions | |
Charlotte | -0.005 |
ricia | -0.005 |
Becky | -0.005 |
iflower | -0.005 |
creature | -0.005 |
Token | took |
Token ID | 1718 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
won | +0.008 |
udd | +0.008 |
ll | +0.007 |
paid | +0.007 |
bought | +0.006 |
Neg logit contributions | |
Becky | -0.011 |
rily | -0.011 |
creature | -0.011 |
Charlotte | -0.011 |
ricia | -0.011 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
iflower | +0.026 |
ricia | +0.025 |
fish | +0.024 |
worm | +0.023 |
Becky | +0.023 |
Neg logit contributions | |
udd | -0.031 |
won | -0.030 |
ount | -0.030 |
pay | -0.029 |
aris | -0.029 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
Charlotte | +0.033 |
Becky | +0.033 |
ricia | +0.032 |
pillow | +0.031 |
Ruby | +0.030 |
Neg logit contributions | |
ount | -0.034 |
ll | -0.033 |
udd | -0.033 |
aris | -0.030 |
won | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ricia | +0.141 |
Charlotte | +0.136 |
unia | +0.134 |
creature | +0.133 |
Becky | +0.133 |
Neg logit contributions | |
ll | -0.127 |
udd | -0.116 |
ount | -0.113 |
won | -0.102 |
come | -0.100 |
Token | her |
Token ID | 607 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
ricia | +0.027 |
worm | +0.026 |
iflower | +0.026 |
creature | +0.025 |
Becky | +0.024 |
Neg logit contributions | |
come | -0.033 |
udd | -0.033 |
ount | -0.032 |
pay | -0.032 |
parties | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-04 |
Pos logit contributions | |
udd | +0.010 |
ount | +0.010 |
ll | +0.010 |
won | +0.009 |
aris | +0.009 |
Neg logit contributions | |
ricia | -0.008 |
Charlotte | -0.008 |
Becky | -0.007 |
iflower | -0.007 |
idi | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
Charlotte | +0.001 |
Becky | +0.001 |
ricia | +0.001 |
iflower | +0.001 |
creature | +0.001 |
Neg logit contributions | |
ount | -0.001 |
udd | -0.001 |
ll | -0.001 |
aris | -0.001 |
won | -0.001 |
Token | played |
Token ID | 2826 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
udd | +0.007 |
ll | +0.007 |
won | +0.007 |
paid | +0.006 |
ount | +0.006 |
Neg logit contributions | |
Becky | -0.011 |
Charlotte | -0.011 |
ricia | -0.010 |
iflower | -0.010 |
creature | -0.010 |
Token | smile |
Token ID | 8212 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
ricia | +0.028 |
Becky | +0.027 |
Charlotte | +0.027 |
frantically | +0.026 |
iflower | +0.026 |
Neg logit contributions | |
udd | -0.034 |
won | -0.033 |
ount | -0.033 |
ll | -0.032 |
arl | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
Charlotte | +0.006 |
Becky | +0.006 |
ricia | +0.006 |
pillow | +0.005 |
Ruby | +0.005 |
Neg logit contributions | |
ount | -0.007 |
ll | -0.006 |
udd | -0.006 |
aris | -0.006 |
won | -0.006 |
Token | Sara |
Token ID | 24799 |
Feature activation | -6.23e-03 |
Pos logit contributions | |
Charlotte | +0.008 |
Becky | +0.008 |
Ruby | +0.008 |
Bonnie | +0.007 |
Elsa | +0.007 |
Neg logit contributions | |
ll | -0.009 |
udd | -0.008 |
ount | -0.008 |
ari | -0.007 |
aris | -0.007 |
Token | took |
Token ID | 1718 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Charlotte | +0.009 |
Becky | +0.009 |
ricia | +0.009 |
pillow | +0.008 |
creature | +0.008 |
Neg logit contributions | |
udd | -0.011 |
ll | -0.011 |
ount | -0.011 |
won | -0.010 |
aris | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
iflower | +0.035 |
ricia | +0.032 |
fish | +0.031 |
Becky | +0.030 |
frantically | +0.030 |
Neg logit contributions | |
ount | -0.036 |
udd | -0.035 |
won | -0.034 |
aris | -0.033 |
pay | -0.032 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
Charlotte | +0.029 |
Becky | +0.029 |
ricia | +0.028 |
pillow | +0.027 |
Ruby | +0.026 |
Neg logit contributions | |
ount | -0.033 |
ll | -0.033 |
udd | -0.033 |
aris | -0.030 |
won | -0.029 |
Token | she |
Token ID | 673 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
Charlotte | +0.125 |
ricia | +0.125 |
Becky | +0.123 |
pillow | +0.118 |
iflower | +0.116 |
Neg logit contributions | |
ll | -0.137 |
ount | -0.131 |
udd | -0.130 |
won | -0.119 |
aris | -0.113 |
Token | went |
Token ID | 1816 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ount | +0.009 |
ll | +0.009 |
udd | +0.009 |
aris | +0.008 |
arl | +0.007 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
pillow | -0.008 |
ricia | -0.008 |
creature | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
ount | +0.024 |
ll | +0.024 |
udd | +0.024 |
aris | +0.021 |
won | +0.021 |
Neg logit contributions | |
Charlotte | -0.022 |
Becky | -0.022 |
ricia | -0.021 |
pillow | -0.021 |
Ruby | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
Ruby | +0.005 |
Bonnie | +0.005 |
Elsa | +0.005 |
Neg logit contributions | |
ll | -0.005 |
udd | -0.005 |
ount | -0.005 |
ari | -0.004 |
aris | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -8.67e-03 |
Pos logit contributions | |
Charlotte | +0.008 |
Becky | +0.007 |
ricia | +0.007 |
Ruby | +0.007 |
pillow | +0.007 |
Neg logit contributions | |
ount | -0.005 |
udd | -0.005 |
ll | -0.005 |
aris | -0.005 |
won | -0.004 |
Token | always |
Token ID | 1464 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Becky | +0.026 |
ricia | +0.026 |
rily | +0.025 |
iflower | +0.025 |
creature | +0.025 |
Neg logit contributions | |
won | -0.017 |
udd | -0.016 |
ll | -0.016 |
paid | -0.014 |
ount | -0.014 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ount | +0.022 |
udd | +0.021 |
ll | +0.021 |
aris | +0.019 |
ari | +0.019 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.020 |
ricia | -0.019 |
pillow | -0.019 |
Ruby | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +3.61e-03 |
Pos logit contributions | |
ricia | +0.045 |
iflower | +0.045 |
Becky | +0.045 |
rily | +0.044 |
Charlotte | +0.044 |
Neg logit contributions | |
ount | -0.013 |
udd | -0.013 |
won | -0.013 |
ll | -0.012 |
aris | -0.011 |
Token | take |
Token ID | 1011 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
ount | +0.004 |
ll | +0.004 |
udd | +0.003 |
won | +0.003 |
pay | +0.003 |
Neg logit contributions | |
Becky | -0.008 |
Charlotte | -0.008 |
ricia | -0.008 |
iflower | -0.007 |
pillow | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
iflower | +0.041 |
ricia | +0.041 |
Becky | +0.041 |
fish | +0.040 |
comet | +0.039 |
Neg logit contributions | |
won | -0.027 |
udd | -0.027 |
ount | -0.026 |
pay | -0.025 |
aris | -0.024 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
Becky | +0.017 |
ricia | +0.016 |
Charlotte | +0.016 |
iflower | +0.016 |
frantically | +0.015 |
Neg logit contributions | |
ll | -0.023 |
ount | -0.023 |
udd | -0.023 |
won | -0.021 |
aris | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
ricia | +0.144 |
Becky | +0.136 |
creature | +0.136 |
Charlotte | +0.135 |
growth | +0.133 |
Neg logit contributions | |
ll | -0.117 |
udd | -0.110 |
ount | -0.105 |
won | -0.099 |
come | -0.093 |
Token | |
Token ID | 220 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
Charlotte | +0.012 |
Becky | +0.011 |
Bonnie | +0.011 |
Ruby | +0.011 |
ricia | +0.011 |
Neg logit contributions | |
ount | -0.012 |
ll | -0.011 |
udd | -0.011 |
ari | -0.010 |
aris | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
Charlotte | +0.010 |
Becky | +0.010 |
ricia | +0.010 |
Ruby | +0.010 |
pillow | +0.010 |
Neg logit contributions | |
ount | -0.007 |
udd | -0.007 |
ll | -0.007 |
aris | -0.006 |
won | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.003 |
ricia | +0.003 |
Ruby | +0.003 |
pillow | +0.003 |
Neg logit contributions | |
ount | -0.003 |
udd | -0.002 |
ll | -0.002 |
aris | -0.002 |
won | -0.002 |
Token | One |
Token ID | 3198 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Charlotte | +0.013 |
Becky | +0.013 |
ricia | +0.013 |
pillow | +0.012 |
Ruby | +0.012 |
Neg logit contributions | |
ount | -0.012 |
ll | -0.011 |
udd | -0.011 |
aris | -0.010 |
won | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
udd | +0.000 |
ll | +0.000 |
ount | +0.000 |
won | +0.000 |
aris | +0.000 |
Neg logit contributions | |
Becky | -0.000 |
ricia | -0.000 |
Charlotte | -0.000 |
Ruby | -0.000 |
creature | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Charlotte | +0.007 |
Becky | +0.007 |
pillow | +0.006 |
Ruby | +0.006 |
ricia | +0.006 |
Neg logit contributions | |
ll | -0.010 |
ount | -0.009 |
udd | -0.009 |
ari | -0.008 |
aris | -0.008 |
Token | could |
Token ID | 714 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
Charlotte | +0.029 |
Becky | +0.029 |
ricia | +0.029 |
iflower | +0.028 |
Ruby | +0.028 |
Neg logit contributions | |
ll | -0.019 |
udd | -0.018 |
won | -0.018 |
ount | -0.017 |
paid | -0.016 |
Token | take |
Token ID | 1011 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
ricia | +0.066 |
Charlotte | +0.063 |
iflower | +0.062 |
Becky | +0.062 |
creature | +0.060 |
Neg logit contributions | |
pay | -0.029 |
come | -0.027 |
ount | -0.027 |
ll | -0.026 |
won | -0.024 |
Token | pictures |
Token ID | 5986 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
ricia | +0.029 |
Charlotte | +0.029 |
Becky | +0.028 |
iflower | +0.028 |
pillow | +0.027 |
Neg logit contributions | |
ount | -0.038 |
won | -0.037 |
udd | -0.037 |
aris | -0.035 |
pay | -0.035 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
ount | +0.010 |
udd | +0.010 |
ll | +0.010 |
aris | +0.009 |
lay | +0.009 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
pillow | -0.009 |
Ruby | -0.009 |
ricia | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ricia | +0.148 |
Charlotte | +0.140 |
Becky | +0.137 |
unia | +0.136 |
veil | +0.133 |
Neg logit contributions | |
ll | -0.107 |
ount | -0.104 |
udd | -0.102 |
won | -0.100 |
come | -0.094 |
Token | went |
Token ID | 1816 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Charlotte | +0.017 |
Becky | +0.017 |
ricia | +0.016 |
pillow | +0.016 |
Ruby | +0.015 |
Neg logit contributions | |
ount | -0.016 |
udd | -0.015 |
ll | -0.015 |
aris | -0.013 |
won | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -8.53e-04 |
Pos logit contributions | |
ount | +0.032 |
ll | +0.031 |
udd | +0.031 |
aris | +0.027 |
won | +0.027 |
Neg logit contributions | |
Charlotte | -0.031 |
Becky | -0.030 |
ricia | -0.029 |
pillow | -0.028 |
Ruby | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
Charlotte | +0.001 |
Becky | +0.001 |
pillow | +0.001 |
Ruby | +0.001 |
ricia | +0.001 |
Neg logit contributions | |
ll | -0.001 |
ount | -0.001 |
udd | -0.001 |
aris | -0.001 |
ari | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -7.57e-03 |
Pos logit contributions | |
ount | +0.002 |
udd | +0.002 |
ll | +0.002 |
aris | +0.002 |
won | +0.002 |
Neg logit contributions | |
Charlotte | -0.002 |
Becky | -0.002 |
ricia | -0.002 |
Ruby | -0.002 |
pillow | -0.002 |
Token | smile |
Token ID | 8212 |
Feature activation | -3.26e-03 |
Pos logit contributions | |
ricia | +0.027 |
Becky | +0.026 |
Charlotte | +0.026 |
iflower | +0.025 |
frantically | +0.024 |
Neg logit contributions | |
udd | -0.033 |
won | -0.032 |
ount | -0.031 |
ll | -0.030 |
come | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
pillow | +0.005 |
Ruby | +0.005 |
Neg logit contributions | |
ount | -0.005 |
udd | -0.005 |
ll | -0.005 |
aris | -0.005 |
won | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
Ruby | +0.005 |
pillow | +0.005 |
Neg logit contributions | |
ount | -0.005 |
ll | -0.005 |
udd | -0.004 |
aris | -0.004 |
ari | -0.004 |
Token | took |
Token ID | 1718 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Charlotte | +0.019 |
Becky | +0.019 |
iflower | +0.018 |
pillow | +0.018 |
ricia | +0.018 |
Neg logit contributions | |
udd | -0.019 |
ll | -0.019 |
ount | -0.018 |
won | -0.018 |
aris | -0.016 |
Token | Anna |
Token ID | 11735 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
iflower | +0.038 |
fish | +0.034 |
ricia | +0.033 |
worm | +0.033 |
lf | +0.032 |
Neg logit contributions | |
won | -0.033 |
come | -0.030 |
ount | -0.030 |
aris | -0.030 |
parties | -0.029 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
ricia | +0.048 |
Becky | +0.048 |
Charlotte | +0.047 |
iflower | +0.046 |
creature | +0.044 |
Neg logit contributions | |
ll | -0.049 |
ount | -0.049 |
udd | -0.048 |
won | -0.044 |
aris | -0.044 |
Token | she |
Token ID | 673 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
Charlotte | +0.123 |
ricia | +0.123 |
Becky | +0.121 |
pillow | +0.116 |
iflower | +0.115 |
Neg logit contributions | |
ll | -0.134 |
ount | -0.130 |
udd | -0.129 |
won | -0.118 |
aris | -0.113 |
Token | went |
Token ID | 1816 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ount | +0.014 |
ll | +0.013 |
udd | +0.013 |
aris | +0.012 |
arl | +0.011 |
Neg logit contributions | |
Charlotte | -0.013 |
Becky | -0.013 |
pillow | -0.012 |
ricia | -0.012 |
creature | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
ount | +0.027 |
ll | +0.026 |
udd | +0.026 |
aris | +0.024 |
won | +0.023 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.023 |
ricia | -0.022 |
pillow | -0.022 |
Ruby | -0.022 |
Token | She |
Token ID | 1375 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
Charlotte | +0.002 |
Becky | +0.002 |
ricia | +0.002 |
pillow | +0.002 |
iflower | +0.002 |
Neg logit contributions | |
ount | -0.002 |
udd | -0.002 |
ll | -0.002 |
aris | -0.001 |
won | -0.001 |
Token | talked |
Token ID | 6619 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
iflower | +0.003 |
creature | +0.003 |
ricia | +0.003 |
Neg logit contributions | |
udd | -0.002 |
ll | -0.002 |
won | -0.002 |
ount | -0.002 |
paid | -0.002 |
Token | fairy |
Token ID | 25607 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
le | +0.018 |
led | +0.018 |
rily | +0.017 |
ricia | +0.017 |
growth | +0.017 |
Neg logit contributions | |
udd | -0.014 |
won | -0.013 |
ll | -0.013 |
party | -0.012 |
ari | -0.012 |
Token | doll |
Token ID | 3654 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
Becky | +0.015 |
Charlotte | +0.015 |
ricia | +0.015 |
iflower | +0.014 |
frantically | +0.014 |
Neg logit contributions | |
udd | -0.017 |
ount | -0.016 |
ll | -0.016 |
ari | -0.015 |
aris | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | +2.95e-03 |
Pos logit contributions | |
Becky | +0.015 |
Charlotte | +0.015 |
ricia | +0.015 |
iflower | +0.014 |
pillow | +0.014 |
Neg logit contributions | |
ount | -0.015 |
udd | -0.015 |
ll | -0.015 |
ari | -0.013 |
aris | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | -8.00e-03 |
Pos logit contributions | |
ll | +0.005 |
ount | +0.005 |
udd | +0.005 |
won | +0.004 |
aris | +0.004 |
Neg logit contributions | |
ricia | -0.004 |
Charlotte | -0.004 |
frantically | -0.004 |
rily | -0.004 |
iflower | -0.004 |
Token | carried |
Token ID | 5281 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
Charlotte | +0.014 |
Becky | +0.013 |
pillow | +0.013 |
ricia | +0.013 |
rily | +0.013 |
Neg logit contributions | |
ll | -0.012 |
udd | -0.012 |
ount | -0.011 |
won | -0.011 |
ari | -0.010 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
Charlotte | +0.042 |
ricia | +0.042 |
Becky | +0.042 |
iflower | +0.041 |
pillow | +0.041 |
Neg logit contributions | |
ount | -0.052 |
ll | -0.050 |
udd | -0.050 |
aris | -0.047 |
won | -0.046 |
Token | she |
Token ID | 673 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
ricia | +0.148 |
Charlotte | +0.140 |
creature | +0.139 |
unia | +0.137 |
growth | +0.136 |
Neg logit contributions | |
ll | -0.112 |
udd | -0.101 |
ount | -0.094 |
won | -0.090 |
aris | -0.086 |
Token | went |
Token ID | 1816 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
ll | +0.004 |
ount | +0.004 |
udd | +0.004 |
arl | +0.004 |
inconvenience | +0.004 |
Neg logit contributions | |
Charlotte | -0.003 |
Becky | -0.003 |
pillow | -0.003 |
creature | -0.003 |
Ruby | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-03 |
Pos logit contributions | |
ount | +0.026 |
ll | +0.026 |
udd | +0.025 |
aris | +0.022 |
won | +0.022 |
Neg logit contributions | |
Charlotte | -0.023 |
Becky | -0.022 |
Ruby | -0.021 |
pillow | -0.021 |
ricia | -0.021 |
Token | One |
Token ID | 1881 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.004 |
Ruby | +0.003 |
pillow | +0.003 |
ricia | +0.003 |
Neg logit contributions | |
ll | -0.003 |
ount | -0.003 |
udd | -0.003 |
aris | -0.003 |
won | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
udd | +0.018 |
ll | +0.017 |
ount | +0.016 |
ari | +0.015 |
won | +0.013 |
Neg logit contributions | |
Charlotte | -0.049 |
Becky | -0.049 |
ricia | -0.048 |
rily | -0.048 |
frantically | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-04 |
Pos logit contributions | |
ount | +0.025 |
ll | +0.024 |
udd | +0.024 |
aris | +0.022 |
ari | +0.022 |
Neg logit contributions | |
Charlotte | -0.023 |
Becky | -0.022 |
pillow | -0.021 |
ricia | -0.021 |
creature | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
cable | +0.000 |
pillow | +0.000 |
Charlotte | +0.000 |
Becky | +0.000 |
Ruby | +0.000 |
Neg logit contributions | |
ount | -0.001 |
ll | -0.001 |
udd | -0.001 |
ari | -0.001 |
aris | -0.001 |
Token | would |
Token ID | 561 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Becky | +0.027 |
Charlotte | +0.026 |
creature | +0.026 |
device | +0.026 |
rily | +0.025 |
Neg logit contributions | |
ll | -0.016 |
udd | -0.016 |
won | -0.015 |
paid | -0.013 |
lay | -0.012 |
Token | take |
Token ID | 1011 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ricia | +0.044 |
Charlotte | +0.043 |
Becky | +0.043 |
creature | +0.041 |
iflower | +0.040 |
Neg logit contributions | |
ll | -0.031 |
ount | -0.031 |
udd | -0.030 |
won | -0.028 |
pay | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ricia | +0.034 |
Charlotte | +0.032 |
Becky | +0.032 |
iflower | +0.030 |
unia | +0.029 |
Neg logit contributions | |
won | -0.037 |
udd | -0.036 |
ount | -0.034 |
pay | -0.034 |
come | -0.033 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
Charlotte | +0.033 |
pillow | +0.033 |
Becky | +0.033 |
Ruby | +0.031 |
veil | +0.031 |
Neg logit contributions | |
ount | -0.051 |
udd | -0.047 |
ll | -0.046 |
aris | -0.042 |
inconvenience | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ricia | +0.140 |
Charlotte | +0.136 |
Becky | +0.134 |
unia | +0.130 |
creature | +0.129 |
Neg logit contributions | |
ll | -0.125 |
udd | -0.117 |
ount | -0.112 |
won | -0.106 |
done | -0.099 |
Token | him |
Token ID | 683 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
Charlotte | +0.018 |
Becky | +0.018 |
ricia | +0.017 |
Ruby | +0.016 |
pillow | +0.016 |
Neg logit contributions | |
ount | -0.026 |
udd | -0.026 |
ll | -0.026 |
won | -0.024 |
aris | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +3.54e-04 |
Pos logit contributions | |
Charlotte | +0.008 |
Becky | +0.007 |
pillow | +0.007 |
ricia | +0.007 |
Ruby | +0.007 |
Neg logit contributions | |
ount | -0.008 |
udd | -0.008 |
ll | -0.008 |
aris | -0.007 |
ari | -0.007 |
Token | One |
Token ID | 1881 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ount | +0.001 |
ll | +0.001 |
udd | +0.001 |
aris | +0.001 |
ari | +0.001 |
Neg logit contributions | |
Charlotte | -0.000 |
Becky | -0.000 |
cable | -0.000 |
pillow | -0.000 |
Ruby | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
udd | +0.021 |
ll | +0.021 |
ount | +0.020 |
won | +0.018 |
ari | +0.017 |
Neg logit contributions | |
Becky | -0.047 |
Charlotte | -0.047 |
ricia | -0.046 |
rily | -0.045 |
Ruby | -0.045 |
Token | this |
Token ID | 428 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Charlotte | +0.000 |
Becky | +0.000 |
ricia | +0.000 |
pillow | +0.000 |
Ruby | +0.000 |
Neg logit contributions | |
ount | -0.000 |
ll | -0.000 |
udd | -0.000 |
aris | -0.000 |
won | -0.000 |
Token | doll |
Token ID | 3654 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
iflower | +0.040 |
ricia | +0.040 |
Becky | +0.040 |
Charlotte | +0.039 |
frantically | +0.038 |
Neg logit contributions | |
udd | -0.055 |
ount | -0.055 |
won | -0.054 |
ll | -0.053 |
ari | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Charlotte | +0.030 |
Becky | +0.030 |
ricia | +0.030 |
frantically | +0.027 |
iflower | +0.027 |
Neg logit contributions | |
udd | -0.038 |
ll | -0.038 |
ount | -0.037 |
won | -0.035 |
ari | -0.034 |
Token | took |
Token ID | 1718 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ricia | +0.022 |
Becky | +0.022 |
Charlotte | +0.021 |
creature | +0.021 |
iflower | +0.021 |
Neg logit contributions | |
won | -0.014 |
udd | -0.014 |
ll | -0.013 |
ount | -0.013 |
pay | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -7.44e-03 |
Pos logit contributions | |
ricia | +0.032 |
iflower | +0.031 |
Becky | +0.031 |
Charlotte | +0.031 |
fish | +0.029 |
Neg logit contributions | |
udd | -0.040 |
ount | -0.040 |
won | -0.040 |
pay | -0.038 |
aris | -0.037 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
ricia | +0.011 |
Becky | +0.010 |
Charlotte | +0.010 |
iflower | +0.010 |
Bonnie | +0.010 |
Neg logit contributions | |
ount | -0.012 |
ll | -0.012 |
udd | -0.012 |
won | -0.012 |
aris | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | +2.43e-03 |
Pos logit contributions | |
ricia | +0.130 |
Charlotte | +0.124 |
Becky | +0.123 |
creature | +0.122 |
unia | +0.120 |
Neg logit contributions | |
ll | -0.127 |
udd | -0.120 |
ount | -0.116 |
won | -0.110 |
aris | -0.104 |
Token | went |
Token ID | 1816 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ll | +0.004 |
ount | +0.004 |
udd | +0.004 |
aris | +0.003 |
arl | +0.003 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
pillow | -0.004 |
ricia | -0.004 |
creature | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
ount | +0.020 |
ll | +0.020 |
udd | +0.020 |
aris | +0.018 |
won | +0.017 |
Neg logit contributions | |
Charlotte | -0.020 |
Becky | -0.020 |
ricia | -0.019 |
pillow | -0.019 |
Ruby | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
Charlotte | +0.007 |
Becky | +0.007 |
Ruby | +0.006 |
pillow | +0.006 |
ricia | +0.006 |
Neg logit contributions | |
ount | -0.007 |
ll | -0.007 |
udd | -0.007 |
aris | -0.006 |
ari | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
ount | +0.001 |
ll | +0.001 |
udd | +0.001 |
aris | +0.001 |
won | +0.001 |
Neg logit contributions | |
Charlotte | -0.002 |
Becky | -0.002 |
ricia | -0.002 |
pillow | -0.002 |
Ruby | -0.002 |
Token | new |
Token ID | 649 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Charlotte | +0.018 |
Becky | +0.018 |
ricia | +0.018 |
iflower | +0.017 |
growth | +0.017 |
Neg logit contributions | |
ount | -0.017 |
udd | -0.016 |
come | -0.016 |
won | -0.015 |
ll | -0.015 |
Token | : |
Token ID | 25 |
Feature activation | +4.20e-04 |
Pos logit contributions | |
Charlotte | +0.027 |
Becky | +0.027 |
ricia | +0.026 |
pillow | +0.025 |
Ruby | +0.025 |
Neg logit contributions | |
ount | -0.023 |
ll | -0.023 |
udd | -0.023 |
won | -0.021 |
aris | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
ount | +0.001 |
udd | +0.001 |
ll | +0.001 |
won | +0.001 |
aris | +0.001 |
Neg logit contributions | |
Charlotte | -0.001 |
ricia | -0.001 |
Becky | -0.001 |
iflower | -0.001 |
pillow | -0.001 |
Token | flood |
Token ID | 6947 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Charlotte | +0.023 |
Becky | +0.023 |
ricia | +0.022 |
rily | +0.021 |
frantically | +0.021 |
Neg logit contributions | |
ount | -0.028 |
udd | -0.028 |
won | -0.027 |
ll | -0.027 |
ari | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ount | +0.040 |
ll | +0.038 |
udd | +0.038 |
won | +0.035 |
aris | +0.034 |
Neg logit contributions | |
Charlotte | -0.038 |
Becky | -0.038 |
ricia | -0.037 |
pillow | -0.035 |
Ruby | -0.035 |
Token | rain |
Token ID | 6290 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
ount | +0.014 |
udd | +0.013 |
won | +0.012 |
ll | +0.012 |
aris | +0.012 |
Neg logit contributions | |
Charlotte | -0.018 |
ricia | -0.018 |
Becky | -0.017 |
iflower | -0.017 |
Ruby | -0.016 |
Token | bows |
Token ID | 25435 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
ll | +0.076 |
ount | +0.076 |
udd | +0.072 |
aris | +0.069 |
ari | +0.067 |
Neg logit contributions | |
Charlotte | -0.065 |
ricia | -0.063 |
creature | -0.063 |
Becky | -0.063 |
pillow | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ount | +0.003 |
udd | +0.003 |
ll | +0.003 |
won | +0.003 |
aris | +0.003 |
Neg logit contributions | |
Charlotte | -0.003 |
Becky | -0.003 |
ricia | -0.003 |
pillow | -0.003 |
Ruby | -0.003 |
Token | It |
Token ID | 632 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ricia | +0.018 |
Charlotte | +0.017 |
iflower | +0.017 |
Becky | +0.017 |
pillow | +0.017 |
Neg logit contributions | |
ount | -0.016 |
udd | -0.015 |
ll | -0.014 |
aris | -0.013 |
won | -0.013 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Charlotte | +0.026 |
iflower | +0.025 |
Becky | +0.025 |
pillow | +0.025 |
ricia | +0.024 |
Neg logit contributions | |
won | -0.022 |
ount | -0.022 |
ll | -0.021 |
udd | -0.021 |
come | -0.019 |
Token | like |
Token ID | 588 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
Charlotte | +0.022 |
ricia | +0.021 |
Becky | +0.021 |
iflower | +0.021 |
pillow | +0.020 |
Neg logit contributions | |
ount | -0.016 |
udd | -0.016 |
ll | -0.014 |
won | -0.014 |
aris | -0.013 |
Token | arrive |
Token ID | 9240 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
udd | +0.053 |
ll | +0.051 |
ount | +0.048 |
aris | +0.048 |
ari | +0.043 |
Neg logit contributions | |
pillow | -0.044 |
veil | -0.043 |
Charlotte | -0.042 |
ear | -0.041 |
comet | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
ount | +0.047 |
ll | +0.045 |
udd | +0.045 |
aris | +0.040 |
ari | +0.040 |
Neg logit contributions | |
Charlotte | -0.042 |
Becky | -0.041 |
ricia | -0.039 |
pillow | -0.039 |
Ruby | -0.038 |
Token | When |
Token ID | 1649 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
ll | +0.002 |
ount | +0.002 |
udd | +0.002 |
aris | +0.002 |
ari | +0.002 |
Neg logit contributions | |
Charlotte | -0.002 |
Becky | -0.002 |
ricia | -0.002 |
Ruby | -0.002 |
pillow | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
Charlotte | +0.012 |
Becky | +0.012 |
ricia | +0.012 |
pillow | +0.011 |
Ruby | +0.011 |
Neg logit contributions | |
ount | -0.019 |
ll | -0.019 |
udd | -0.019 |
aris | -0.017 |
won | -0.017 |
Token | finally |
Token ID | 3443 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
ount | +0.007 |
udd | +0.007 |
ll | +0.007 |
aris | +0.007 |
arl | +0.007 |
Neg logit contributions | |
Becky | -0.003 |
Charlotte | -0.003 |
idi | -0.003 |
Ruby | -0.003 |
ricia | -0.003 |
Token | came |
Token ID | 1625 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
udd | +0.008 |
ount | +0.008 |
ll | +0.008 |
aris | +0.008 |
ocular | +0.007 |
Neg logit contributions | |
Becky | -0.008 |
Charlotte | -0.008 |
idi | -0.008 |
Ruby | -0.007 |
veil | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
ount | +0.093 |
udd | +0.092 |
ll | +0.092 |
aris | +0.080 |
ari | +0.080 |
Neg logit contributions | |
Charlotte | -0.068 |
Becky | -0.068 |
Ruby | -0.062 |
creature | -0.060 |
pillow | -0.058 |
Token | she |
Token ID | 673 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
ount | +0.006 |
won | +0.006 |
udd | +0.006 |
ll | +0.006 |
pay | +0.005 |
Neg logit contributions | |
ricia | -0.006 |
iflower | -0.006 |
Becky | -0.006 |
Charlotte | -0.006 |
creature | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
ricia | +0.003 |
pillow | +0.003 |
Ruby | +0.003 |
Neg logit contributions | |
ount | -0.003 |
ll | -0.003 |
udd | -0.003 |
won | -0.003 |
aris | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
iflower | +0.016 |
ricia | +0.015 |
Charlotte | +0.015 |
Becky | +0.015 |
wand | +0.014 |
Neg logit contributions | |
ount | -0.026 |
udd | -0.026 |
won | -0.026 |
ll | -0.026 |
lay | -0.025 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
pillow | +0.004 |
ricia | +0.004 |
Ruby | +0.004 |
Neg logit contributions | |
ount | -0.009 |
ll | -0.008 |
udd | -0.008 |
aris | -0.008 |
won | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
Becky | +0.037 |
Charlotte | +0.037 |
iflower | +0.036 |
ricia | +0.035 |
Ruby | +0.035 |
Neg logit contributions | |
ll | -0.017 |
udd | -0.017 |
won | -0.016 |
paid | -0.015 |
ount | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ricia | +0.008 |
Charlotte | +0.008 |
Becky | +0.008 |
iflower | +0.008 |
pillow | +0.007 |
Neg logit contributions | |
ll | -0.006 |
ount | -0.006 |
udd | -0.006 |
won | -0.005 |
aris | -0.005 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
ount | +0.017 |
ll | +0.017 |
udd | +0.016 |
won | +0.015 |
aris | +0.015 |
Neg logit contributions | |
ricia | -0.017 |
Charlotte | -0.017 |
Becky | -0.016 |
iflower | -0.016 |
pillow | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ount | +0.008 |
udd | +0.008 |
ll | +0.008 |
won | +0.007 |
aris | +0.007 |
Neg logit contributions | |
Charlotte | -0.008 |
Becky | -0.008 |
ricia | -0.007 |
pillow | -0.007 |
Ruby | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
ll | +0.013 |
ount | +0.013 |
won | +0.013 |
udd | +0.012 |
pay | +0.011 |
Neg logit contributions | |
iflower | -0.021 |
ricia | -0.020 |
rily | -0.020 |
Charlotte | -0.019 |
frantically | -0.019 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.004 |
ricia | +0.004 |
iflower | +0.004 |
Ruby | +0.004 |
Neg logit contributions | |
ll | -0.005 |
udd | -0.005 |
ount | -0.005 |
aris | -0.005 |
won | -0.004 |
Token | my |
Token ID | 1820 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ount | +0.074 |
udd | +0.068 |
aris | +0.067 |
OM | +0.066 |
ll | +0.065 |
Neg logit contributions | |
Charlotte | -0.061 |
Becky | -0.057 |
pillow | -0.057 |
bunny | -0.055 |
veil | -0.054 |
Token | went |
Token ID | 1816 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
ount | +0.025 |
udd | +0.023 |
ll | +0.023 |
aris | +0.022 |
OM | +0.022 |
Neg logit contributions | |
Charlotte | -0.022 |
pillow | -0.021 |
Becky | -0.021 |
veil | -0.020 |
bunny | -0.020 |
Token | outside |
Token ID | 2354 |
Feature activation | -9.53e-04 |
Pos logit contributions | |
ount | +0.032 |
ll | +0.031 |
udd | +0.030 |
aris | +0.026 |
won | +0.026 |
Neg logit contributions | |
Charlotte | -0.051 |
Becky | -0.050 |
ricia | -0.049 |
pillow | -0.048 |
iflower | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Charlotte | +0.002 |
Becky | +0.002 |
ricia | +0.002 |
pillow | +0.002 |
Ruby | +0.002 |
Neg logit contributions | |
ount | -0.001 |
udd | -0.001 |
ll | -0.001 |
aris | -0.001 |
ari | -0.001 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
ount | +0.012 |
ll | +0.011 |
udd | +0.011 |
pay | +0.010 |
won | +0.010 |
Neg logit contributions | |
ricia | -0.040 |
Charlotte | -0.039 |
iflower | -0.039 |
Becky | -0.039 |
rily | -0.038 |
Token | each |
Token ID | 1123 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
udd | +0.001 |
ount | +0.001 |
ll | +0.001 |
won | +0.001 |
aris | +0.001 |
Neg logit contributions | |
iflower | -0.001 |
Charlotte | -0.001 |
Becky | -0.001 |
ricia | -0.001 |
issa | -0.001 |
Token | other |
Token ID | 584 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
iflower | +0.067 |
Charlotte | +0.065 |
bly | +0.064 |
Becky | +0.063 |
rily | +0.061 |
Neg logit contributions | |
won | -0.054 |
ount | -0.053 |
udd | -0.053 |
ll | -0.053 |
come | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
Charlotte | +0.037 |
Becky | +0.036 |
ricia | +0.036 |
iflower | +0.034 |
pillow | +0.034 |
Neg logit contributions | |
ount | -0.030 |
ll | -0.030 |
udd | -0.030 |
aris | -0.026 |
won | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ll | +0.008 |
ount | +0.008 |
udd | +0.008 |
aris | +0.007 |
ari | +0.007 |
Neg logit contributions | |
Charlotte | -0.010 |
Becky | -0.010 |
Ruby | -0.009 |
ricia | -0.009 |
pillow | -0.009 |
Token | did |
Token ID | 750 |
Feature activation | +5.40e-04 |
Pos logit contributions | |
ount | +0.016 |
ll | +0.015 |
udd | +0.015 |
aris | +0.014 |
ari | +0.013 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.018 |
ricia | -0.017 |
pillow | -0.017 |
Ruby | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ount | +0.001 |
ll | +0.001 |
udd | +0.001 |
aris | +0.001 |
ari | +0.001 |
Neg logit contributions | |
Charlotte | -0.001 |
Becky | -0.001 |
ricia | -0.001 |
pillow | -0.001 |
Ruby | -0.001 |
Token | know |
Token ID | 760 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
ll | +0.054 |
ount | +0.054 |
udd | +0.053 |
aris | +0.047 |
ari | +0.045 |
Neg logit contributions | |
Becky | -0.084 |
Charlotte | -0.084 |
pillow | -0.080 |
ricia | -0.080 |
Ruby | -0.079 |
Token | that |
Token ID | 326 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ount | +0.042 |
udd | +0.041 |
ll | +0.041 |
aris | +0.037 |
won | +0.037 |
Neg logit contributions | |
Charlotte | -0.041 |
Becky | -0.040 |
ricia | -0.040 |
pillow | -0.038 |
iflower | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
ount | +0.025 |
udd | +0.023 |
ll | +0.023 |
won | +0.023 |
aris | +0.022 |
Neg logit contributions | |
Charlotte | -0.021 |
ricia | -0.020 |
Becky | -0.020 |
iflower | -0.019 |
Bonnie | -0.018 |
Token | star |
Token ID | 3491 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ll | +0.015 |
udd | +0.015 |
ount | +0.015 |
won | +0.014 |
ari | +0.014 |
Neg logit contributions | |
Charlotte | -0.010 |
Becky | -0.009 |
ricia | -0.009 |
Ruby | -0.008 |
Bonnie | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
Charlotte | +0.032 |
Becky | +0.030 |
ricia | +0.030 |
Bonnie | +0.029 |
Ruby | +0.028 |
Neg logit contributions | |
ll | -0.032 |
ount | -0.031 |
udd | -0.031 |
won | -0.030 |
ari | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
Becky | +0.013 |
Charlotte | +0.013 |
ricia | +0.012 |
pillow | +0.012 |
Ruby | +0.012 |
Neg logit contributions | |
ount | -0.012 |
ll | -0.012 |
udd | -0.012 |
aris | -0.011 |
lay | -0.010 |
Token | would |
Token ID | 561 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
Charlotte | +0.025 |
Becky | +0.025 |
ricia | +0.024 |
Ruby | +0.023 |
pillow | +0.023 |
Neg logit contributions | |
ll | -0.015 |
udd | -0.014 |
ount | -0.014 |
won | -0.013 |
aris | -0.011 |
Token | walk |
Token ID | 2513 |
Feature activation | +9.23e-03 |
Pos logit contributions | |
Charlotte | +0.026 |
Becky | +0.026 |
pillow | +0.025 |
ricia | +0.024 |
Ruby | +0.024 |
Neg logit contributions | |
ount | -0.023 |
udd | -0.022 |
ll | -0.022 |
aris | -0.020 |
ari | -0.019 |
Token | through |
Token ID | 832 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ll | +0.012 |
udd | +0.011 |
ount | +0.011 |
won | +0.010 |
aris | +0.010 |
Neg logit contributions | |
Charlotte | -0.017 |
ricia | -0.017 |
Becky | -0.017 |
iflower | -0.017 |
issa | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ricia | +0.024 |
Charlotte | +0.024 |
Becky | +0.022 |
iflower | +0.022 |
Ruby | +0.021 |
Neg logit contributions | |
ount | -0.024 |
udd | -0.024 |
ll | -0.023 |
won | -0.022 |
aris | -0.022 |
Token | wheat |
Token ID | 17135 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
udd | +0.021 |
ll | +0.021 |
ount | +0.020 |
aris | +0.019 |
ari | +0.019 |
Neg logit contributions | |
Charlotte | -0.024 |
ricia | -0.024 |
Becky | -0.024 |
Ruby | -0.022 |
Bonnie | -0.022 |
Token | fields |
Token ID | 7032 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
ount | +0.079 |
udd | +0.075 |
ll | +0.075 |
aris | +0.068 |
won | +0.067 |
Neg logit contributions | |
Charlotte | -0.060 |
Becky | -0.059 |
pillow | -0.056 |
ricia | -0.056 |
Ruby | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
ount | +0.080 |
udd | +0.075 |
ll | +0.074 |
aris | +0.067 |
lay | +0.067 |
Neg logit contributions | |
Becky | -0.057 |
Charlotte | -0.057 |
pillow | -0.054 |
Ruby | -0.053 |
frantically | -0.053 |
Token | adm |
Token ID | 6178 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
ount | +0.009 |
udd | +0.009 |
ll | +0.009 |
aris | +0.008 |
ari | +0.008 |
Neg logit contributions | |
Charlotte | -0.008 |
Becky | -0.008 |
ricia | -0.008 |
pillow | -0.008 |
Ruby | -0.008 |
Token | iring |
Token ID | 3428 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
ount | +0.048 |
ll | +0.047 |
udd | +0.046 |
won | +0.041 |
aris | +0.041 |
Neg logit contributions | |
Charlotte | -0.063 |
Becky | -0.063 |
ricia | -0.062 |
iflower | -0.060 |
pillow | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
Charlotte | +0.003 |
ricia | +0.003 |
Becky | +0.003 |
pillow | +0.003 |
Ruby | +0.003 |
Neg logit contributions | |
ount | -0.005 |
udd | -0.005 |
ll | -0.005 |
won | -0.004 |
aris | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
Charlotte | +0.008 |
Becky | +0.008 |
Ruby | +0.008 |
pillow | +0.008 |
Elsa | +0.007 |
Neg logit contributions | |
ll | -0.011 |
udd | -0.010 |
ount | -0.010 |
won | -0.009 |
ari | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
Charlotte | +0.025 |
ricia | +0.023 |
Becky | +0.023 |
iflower | +0.023 |
rily | +0.022 |
Neg logit contributions | |
ll | -0.022 |
won | -0.021 |
ount | -0.021 |
udd | -0.021 |
come | -0.018 |
Token | scary |
Token ID | 14343 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Charlotte | +0.031 |
ricia | +0.031 |
Becky | +0.030 |
iflower | +0.029 |
rily | +0.028 |
Neg logit contributions | |
ount | -0.033 |
udd | -0.032 |
ll | -0.032 |
won | -0.030 |
done | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
Charlotte | +0.015 |
Becky | +0.014 |
pillow | +0.014 |
ricia | +0.014 |
creature | +0.014 |
Neg logit contributions | |
ount | -0.018 |
ll | -0.017 |
udd | -0.017 |
aris | -0.015 |
ari | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
Charlotte | +0.009 |
Becky | +0.009 |
Ruby | +0.009 |
pillow | +0.008 |
Elsa | +0.008 |
Neg logit contributions | |
ll | -0.012 |
ount | -0.011 |
udd | -0.011 |
aris | -0.010 |
ari | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Charlotte | +0.012 |
Becky | +0.012 |
iflower | +0.012 |
ricia | +0.012 |
rily | +0.012 |
Neg logit contributions | |
ll | -0.007 |
won | -0.007 |
udd | -0.007 |
ount | -0.006 |
lay | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
udd | +0.034 |
ount | +0.033 |
ll | +0.031 |
won | +0.030 |
aris | +0.030 |
Neg logit contributions | |
Charlotte | -0.027 |
ricia | -0.027 |
Becky | -0.026 |
iflower | -0.026 |
rily | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | -1.17e-03 |
Pos logit contributions | |
Charlotte | +0.020 |
Becky | +0.020 |
ricia | +0.019 |
Ruby | +0.018 |
Bonnie | +0.018 |
Neg logit contributions | |
udd | -0.029 |
ll | -0.029 |
ount | -0.029 |
won | -0.027 |
aris | -0.026 |
Token | monster |
Token ID | 9234 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ricia | +0.002 |
Charlotte | +0.002 |
Becky | +0.002 |
rily | +0.002 |
iflower | +0.002 |
Neg logit contributions | |
udd | -0.002 |
ount | -0.002 |
ll | -0.002 |
won | -0.002 |
ari | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
Charlotte | +0.051 |
Becky | +0.050 |
ricia | +0.050 |
Bonnie | +0.046 |
iflower | +0.046 |
Neg logit contributions | |
ount | -0.048 |
ll | -0.047 |
udd | -0.045 |
won | -0.043 |
aris | -0.041 |
Token | But |
Token ID | 887 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
Charlotte | +0.024 |
Becky | +0.023 |
Ruby | +0.022 |
pillow | +0.022 |
Elsa | +0.021 |
Neg logit contributions | |
ll | -0.034 |
ount | -0.032 |
udd | -0.032 |
aris | -0.029 |
ari | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
Charlotte | +0.047 |
Becky | +0.046 |
ricia | +0.045 |
pillow | +0.043 |
iflower | +0.043 |
Neg logit contributions | |
ount | -0.044 |
ll | -0.043 |
udd | -0.043 |
won | -0.039 |
aris | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Becky | +0.005 |
Charlotte | +0.005 |
Ruby | +0.005 |
frantically | +0.004 |
deeply | +0.004 |
Neg logit contributions | |
ll | -0.009 |
ount | -0.009 |
udd | -0.009 |
lay | -0.008 |
arl | -0.008 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.36e-03 |
Pos logit contributions | |
Charlotte | +0.020 |
Becky | +0.020 |
ricia | +0.019 |
pillow | +0.018 |
Ruby | +0.018 |
Neg logit contributions | |
ount | -0.017 |
ll | -0.017 |
udd | -0.017 |
won | -0.015 |
aris | -0.015 |
Token | back |
Token ID | 736 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
ount | +0.006 |
udd | +0.006 |
ll | +0.006 |
aris | +0.005 |
ari | +0.005 |
Neg logit contributions | |
Charlotte | -0.005 |
Becky | -0.005 |
ricia | -0.005 |
pillow | -0.004 |
Ruby | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
Charlotte | +0.011 |
Becky | +0.011 |
ricia | +0.011 |
pillow | +0.010 |
Ruby | +0.010 |
Neg logit contributions | |
ount | -0.008 |
ll | -0.008 |
udd | -0.008 |
aris | -0.007 |
won | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
ount | +0.006 |
ll | +0.006 |
udd | +0.006 |
aris | +0.005 |
won | +0.005 |
Neg logit contributions | |
Charlotte | -0.003 |
Becky | -0.003 |
ricia | -0.003 |
pillow | -0.003 |
Ruby | -0.003 |
Token | house |
Token ID | 2156 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ll | +0.003 |
udd | +0.003 |
ount | +0.003 |
ari | +0.002 |
won | +0.002 |
Neg logit contributions | |
Charlotte | -0.003 |
ricia | -0.003 |
Becky | -0.003 |
Bonnie | -0.003 |
bly | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
ount | +0.069 |
udd | +0.066 |
ll | +0.065 |
aris | +0.060 |
ari | +0.058 |
Neg logit contributions | |
Charlotte | -0.043 |
Becky | -0.042 |
pillow | -0.041 |
frantically | -0.040 |
creature | -0.040 |
Token | fet |
Token ID | 11351 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
Charlotte | +0.014 |
Becky | +0.013 |
Ruby | +0.013 |
pillow | +0.013 |
creature | +0.012 |
Neg logit contributions | |
ount | -0.015 |
udd | -0.015 |
ll | -0.014 |
aris | -0.013 |
arl | -0.013 |
Token | ched |
Token ID | 1740 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
ount | +0.004 |
udd | +0.004 |
ll | +0.004 |
won | +0.004 |
aris | +0.004 |
Neg logit contributions | |
Charlotte | -0.002 |
Becky | -0.002 |
ricia | -0.002 |
iflower | -0.002 |
pillow | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
Charlotte | +0.042 |
ricia | +0.041 |
Becky | +0.040 |
iflower | +0.040 |
veil | +0.039 |
Neg logit contributions | |
won | -0.042 |
ount | -0.042 |
udd | -0.041 |
ll | -0.039 |
pay | -0.039 |
Token | love |
Token ID | 1842 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
ount | +0.017 |
aris | +0.016 |
udd | +0.015 |
ll | +0.015 |
ari | +0.015 |
Neg logit contributions | |
Charlotte | -0.017 |
pillow | -0.017 |
veil | -0.017 |
Becky | -0.016 |
wand | -0.016 |
Token | you |
Token ID | 345 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
ount | +0.011 |
udd | +0.010 |
ll | +0.010 |
aris | +0.009 |
ari | +0.009 |
Neg logit contributions | |
Charlotte | -0.011 |
Becky | -0.011 |
ricia | -0.010 |
pillow | -0.010 |
Ruby | -0.010 |
Token | ." |
Token ID | 526 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ount | +0.003 |
udd | +0.002 |
ll | +0.002 |
aris | +0.002 |
lay | +0.002 |
Neg logit contributions | |
Charlotte | -0.003 |
Becky | -0.003 |
pillow | -0.003 |
Ruby | -0.002 |
ricia | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
ount | +0.018 |
ll | +0.017 |
udd | +0.017 |
aris | +0.015 |
won | +0.015 |
Neg logit contributions | |
Charlotte | -0.022 |
Becky | -0.022 |
Ruby | -0.021 |
ricia | -0.021 |
pillow | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -7.59e-04 |
Pos logit contributions | |
ount | +0.008 |
ll | +0.008 |
udd | +0.008 |
aris | +0.007 |
won | +0.007 |
Neg logit contributions | |
Charlotte | -0.011 |
Becky | -0.011 |
ricia | -0.010 |
pillow | -0.010 |
creature | -0.010 |
Token | They |
Token ID | 2990 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
Becky | +0.001 |
Charlotte | +0.001 |
ricia | +0.001 |
pillow | +0.001 |
creature | +0.001 |
Neg logit contributions | |
ll | -0.001 |
ount | -0.001 |
udd | -0.001 |
lay | -0.001 |
ari | -0.001 |
Token | eat |
Token ID | 4483 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
ount | +0.023 |
udd | +0.022 |
ll | +0.021 |
aris | +0.020 |
lay | +0.019 |
Neg logit contributions | |
Charlotte | -0.023 |
pillow | -0.023 |
Becky | -0.023 |
veil | -0.022 |
Ruby | -0.021 |
Token | their |
Token ID | 511 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
ount | +0.015 |
udd | +0.015 |
ll | +0.015 |
aris | +0.013 |
won | +0.013 |
Neg logit contributions | |
Charlotte | -0.013 |
ricia | -0.013 |
Becky | -0.012 |
iflower | -0.012 |
creature | -0.012 |
Token | lunch |
Token ID | 9965 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ll | +0.024 |
udd | +0.024 |
ount | +0.023 |
aris | +0.022 |
won | +0.022 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.018 |
ricia | -0.018 |
Bonnie | -0.017 |
Ruby | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ount | +0.037 |
udd | +0.034 |
ll | +0.033 |
lay | +0.031 |
aris | +0.031 |
Neg logit contributions | |
pillow | -0.021 |
Charlotte | -0.021 |
Becky | -0.021 |
Ruby | -0.020 |
veil | -0.019 |
Token | then |
Token ID | 788 |
Feature activation | -7.97e-04 |
Pos logit contributions | |
ll | +0.025 |
ount | +0.025 |
udd | +0.024 |
won | +0.023 |
pay | +0.022 |
Neg logit contributions | |
ricia | -0.040 |
Charlotte | -0.040 |
Becky | -0.039 |
iflower | -0.038 |
creature | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
Charlotte | +0.014 |
Becky | +0.014 |
ricia | +0.014 |
pillow | +0.013 |
iflower | +0.013 |
Neg logit contributions | |
ount | -0.015 |
udd | -0.015 |
ll | -0.015 |
aris | -0.013 |
won | -0.013 |
Token | gave |
Token ID | 2921 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
ount | +0.012 |
ll | +0.012 |
udd | +0.012 |
aris | +0.011 |
ari | +0.010 |
Neg logit contributions | |
Charlotte | -0.011 |
Becky | -0.011 |
ricia | -0.010 |
pillow | -0.010 |
Ruby | -0.010 |
Token | each |
Token ID | 1123 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
iflower | +0.008 |
ricia | +0.008 |
Becky | +0.008 |
Charlotte | +0.008 |
veil | +0.008 |
Neg logit contributions | |
udd | -0.009 |
ll | -0.009 |
ount | -0.008 |
won | -0.008 |
aris | -0.008 |
Token | other |
Token ID | 584 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
iflower | +0.060 |
rily | +0.059 |
Charlotte | +0.057 |
Becky | +0.056 |
ricia | +0.056 |
Neg logit contributions | |
won | -0.050 |
pay | -0.045 |
're | -0.045 |
come | -0.044 |
ll | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
Charlotte | +0.034 |
Becky | +0.034 |
ricia | +0.033 |
pillow | +0.031 |
iflower | +0.031 |
Neg logit contributions | |
ount | -0.053 |
udd | -0.052 |
ll | -0.052 |
aris | -0.048 |
won | -0.048 |
Token | big |
Token ID | 1263 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.004 |
ricia | +0.004 |
iflower | +0.004 |
Ruby | +0.004 |
Neg logit contributions | |
udd | -0.005 |
ount | -0.005 |
ll | -0.005 |
won | -0.005 |
aris | -0.005 |
Token | hug |
Token ID | 16225 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
udd | +0.022 |
ount | +0.021 |
ll | +0.021 |
won | +0.019 |
aris | +0.019 |
Neg logit contributions | |
Charlotte | -0.027 |
Becky | -0.027 |
ricia | -0.026 |
iflower | -0.025 |
Ruby | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
ount | +0.009 |
ll | +0.009 |
udd | +0.009 |
lay | +0.008 |
aris | +0.008 |
Neg logit contributions | |
Charlotte | -0.007 |
Becky | -0.007 |
pillow | -0.006 |
creature | -0.006 |
Ruby | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
ount | +0.016 |
ll | +0.015 |
udd | +0.015 |
aris | +0.014 |
ari | +0.014 |
Neg logit contributions | |
Charlotte | -0.013 |
Becky | -0.013 |
ricia | -0.012 |
pillow | -0.012 |
Ruby | -0.012 |
Token | went |
Token ID | 1816 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
udd | +0.006 |
ll | +0.006 |
ount | +0.006 |
won | +0.006 |
aris | +0.005 |
Neg logit contributions | |
Becky | -0.007 |
Charlotte | -0.007 |
ricia | -0.007 |
iflower | -0.007 |
pillow | -0.007 |
Token | off |
Token ID | 572 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
ount | +0.049 |
ll | +0.047 |
udd | +0.047 |
aris | +0.043 |
won | +0.042 |
Neg logit contributions | |
Charlotte | -0.045 |
Becky | -0.045 |
ricia | -0.043 |
pillow | -0.042 |
Ruby | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
ount | +0.089 |
ll | +0.089 |
udd | +0.087 |
aris | +0.081 |
lay | +0.080 |
Neg logit contributions | |
pillow | -0.043 |
Charlotte | -0.043 |
Becky | -0.043 |
creature | -0.043 |
frantically | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +8.44e-03 |
Pos logit contributions | |
ount | +0.004 |
udd | +0.004 |
ll | +0.004 |
won | +0.003 |
aris | +0.003 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
ricia | -0.004 |
pillow | -0.004 |
iflower | -0.004 |
Token | conductor |
Token ID | 39206 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
ll | +0.017 |
ount | +0.017 |
udd | +0.016 |
aris | +0.015 |
lay | +0.015 |
Neg logit contributions | |
creature | -0.010 |
Charlotte | -0.010 |
pillow | -0.010 |
radio | -0.010 |
Becky | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
ount | +0.014 |
udd | +0.013 |
ll | +0.013 |
aris | +0.012 |
arl | +0.012 |
Neg logit contributions | |
Charlotte | -0.010 |
Becky | -0.010 |
pillow | -0.010 |
ricia | -0.010 |
creature | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ount | +0.037 |
ll | +0.036 |
udd | +0.036 |
won | +0.033 |
aris | +0.032 |
Neg logit contributions | |
Charlotte | -0.037 |
Becky | -0.036 |
ricia | -0.036 |
pillow | -0.034 |
Ruby | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ount | +0.022 |
udd | +0.022 |
ll | +0.021 |
aris | +0.020 |
ari | +0.019 |
Neg logit contributions | |
Charlotte | -0.017 |
Becky | -0.016 |
Ruby | -0.015 |
ricia | -0.015 |
pillow | -0.015 |
Token | This |
Token ID | 1212 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
ount | +0.018 |
udd | +0.017 |
ll | +0.017 |
aris | +0.015 |
ari | +0.014 |
Neg logit contributions | |
Charlotte | -0.019 |
ricia | -0.018 |
Becky | -0.018 |
creature | -0.017 |
Ruby | -0.017 |
Token | is |
Token ID | 318 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
Charlotte | +0.012 |
ricia | +0.012 |
Becky | +0.012 |
pillow | +0.012 |
creature | +0.012 |
Neg logit contributions | |
ount | -0.019 |
ll | -0.019 |
udd | -0.018 |
aris | -0.017 |
lay | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
ount | +0.007 |
udd | +0.007 |
ll | +0.007 |
aris | +0.007 |
ari | +0.007 |
Neg logit contributions | |
Charlotte | -0.004 |
Becky | -0.004 |
ricia | -0.004 |
Ruby | -0.004 |
pillow | -0.004 |
Token | end |
Token ID | 886 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
ll | +0.008 |
ount | +0.008 |
udd | +0.008 |
aris | +0.008 |
unch | +0.007 |
Neg logit contributions | |
radio | -0.005 |
creature | -0.005 |
Charlotte | -0.005 |
pillow | -0.005 |
cable | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Becky | +0.017 |
Charlotte | +0.017 |
ricia | +0.016 |
pillow | +0.016 |
Ruby | +0.015 |
Neg logit contributions | |
ount | -0.017 |
udd | -0.017 |
ll | -0.017 |
aris | -0.015 |
lay | -0.015 |
Token | children |
Token ID | 1751 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
ount | +0.040 |
ll | +0.040 |
udd | +0.039 |
lay | +0.036 |
aris | +0.036 |
Neg logit contributions | |
Charlotte | -0.022 |
Becky | -0.022 |
pillow | -0.022 |
turkey | -0.021 |
creature | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -5.21e-05 |
Pos logit contributions | |
Charlotte | +0.013 |
Becky | +0.013 |
pillow | +0.012 |
Ruby | +0.012 |
ricia | +0.012 |
Neg logit contributions | |
ount | -0.015 |
udd | -0.014 |
ll | -0.014 |
aris | -0.013 |
OM | -0.013 |
Token | One |
Token ID | 1881 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
Charlotte | +0.000 |
Becky | +0.000 |
Ruby | +0.000 |
Bonnie | +0.000 |
ricia | +0.000 |
Neg logit contributions | |
ll | -0.000 |
udd | -0.000 |
ount | -0.000 |
done | -0.000 |
ari | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ll | +0.021 |
udd | +0.021 |
ount | +0.020 |
won | +0.018 |
ari | +0.018 |
Neg logit contributions | |
Charlotte | -0.046 |
Becky | -0.045 |
ricia | -0.044 |
frantically | -0.043 |
rily | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-04 |
Pos logit contributions | |
Charlotte | +0.045 |
ricia | +0.045 |
Becky | +0.044 |
iflower | +0.043 |
pillow | +0.043 |
Neg logit contributions | |
ount | -0.028 |
udd | -0.027 |
ll | -0.027 |
won | -0.024 |
aris | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
ount | +0.001 |
udd | +0.000 |
won | +0.000 |
ll | +0.000 |
pay | +0.000 |
Neg logit contributions | |
ricia | -0.001 |
iflower | -0.001 |
Charlotte | -0.001 |
Becky | -0.001 |
pillow | -0.000 |
Token | old |
Token ID | 1468 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
Charlotte | +0.006 |
Becky | +0.006 |
ricia | +0.006 |
pillow | +0.006 |
creature | +0.005 |
Neg logit contributions | |
ount | -0.009 |
ll | -0.009 |
udd | -0.009 |
aris | -0.009 |
won | -0.008 |
Token | nurse |
Token ID | 15849 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
Charlotte | +0.019 |
Becky | +0.019 |
ricia | +0.018 |
pillow | +0.017 |
iflower | +0.017 |
Neg logit contributions | |
ount | -0.021 |
udd | -0.021 |
ll | -0.021 |
won | -0.019 |
aris | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
ount | +0.020 |
ll | +0.019 |
udd | +0.019 |
aris | +0.017 |
won | +0.017 |
Neg logit contributions | |
Charlotte | -0.024 |
Becky | -0.024 |
ricia | -0.023 |
pillow | -0.023 |
Ruby | -0.022 |
Token | an |
Token ID | 281 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
Charlotte | +0.004 |
Becky | +0.004 |
ricia | +0.004 |
pillow | +0.004 |
Ruby | +0.003 |
Neg logit contributions | |
ount | -0.005 |
ll | -0.005 |
udd | -0.005 |
aris | -0.004 |
ari | -0.004 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
udd | +0.002 |
ount | +0.002 |
ll | +0.002 |
pay | +0.002 |
done | +0.002 |
Neg logit contributions | |
Becky | -0.003 |
Charlotte | -0.003 |
ricia | -0.003 |
Ruby | -0.003 |
Ruby | -0.003 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
Charlotte | +0.039 |
Becky | +0.039 |
ricia | +0.037 |
pillow | +0.036 |
Ruby | +0.035 |
Neg logit contributions | |
ount | -0.059 |
ll | -0.058 |
udd | -0.057 |
won | -0.053 |
aris | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -9.24e-03 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
pillow | +0.005 |
Ruby | +0.005 |
Neg logit contributions | |
ount | -0.005 |
ll | -0.004 |
udd | -0.004 |
aris | -0.004 |
won | -0.004 |
Token | but |
Token ID | 475 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
Becky | +0.016 |
Charlotte | +0.016 |
ricia | +0.016 |
iflower | +0.015 |
pillow | +0.015 |
Neg logit contributions | |
ount | -0.013 |
ll | -0.012 |
udd | -0.012 |
won | -0.012 |
aris | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
ricia | +0.031 |
Charlotte | +0.029 |
iflower | +0.029 |
veil | +0.028 |
pillow | +0.028 |
Neg logit contributions | |
won | -0.026 |
ll | -0.025 |
ount | -0.023 |
done | -0.021 |
come | -0.021 |
Token | bear |
Token ID | 6842 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
Charlotte | +0.007 |
ricia | +0.007 |
Becky | +0.007 |
iflower | +0.007 |
rily | +0.006 |
Neg logit contributions | |
udd | -0.011 |
ount | -0.011 |
ll | -0.011 |
won | -0.010 |
ari | -0.010 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
Charlotte | +0.014 |
Becky | +0.014 |
ricia | +0.013 |
pillow | +0.013 |
Ruby | +0.013 |
Neg logit contributions | |
ll | -0.014 |
udd | -0.013 |
ount | -0.013 |
won | -0.013 |
ari | -0.012 |
Token | 't |
Token ID | 470 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
Becky | +0.028 |
ricia | +0.027 |
Charlotte | +0.027 |
veil | +0.027 |
pillow | +0.026 |
Neg logit contributions | |
ount | -0.014 |
ll | -0.014 |
pay | -0.013 |
won | -0.012 |
come | -0.012 |
Token | seem |
Token ID | 1283 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
udd | +0.011 |
ount | +0.011 |
ll | +0.010 |
aris | +0.010 |
ari | +0.010 |
Neg logit contributions | |
Charlotte | -0.012 |
Becky | -0.012 |
creature | -0.012 |
Ruby | -0.012 |
pillow | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ount | +0.031 |
udd | +0.030 |
ll | +0.030 |
aris | +0.026 |
ari | +0.026 |
Neg logit contributions | |
Charlotte | -0.039 |
Becky | -0.038 |
ricia | -0.037 |
creature | -0.036 |
pillow | -0.036 |
Token | notice |
Token ID | 4003 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
udd | +0.057 |
ount | +0.054 |
ll | +0.052 |
aris | +0.052 |
ari | +0.050 |
Neg logit contributions | |
Charlotte | -0.048 |
Becky | -0.046 |
creature | -0.045 |
Ruby | -0.045 |
pillow | -0.044 |
Token | Bob |
Token ID | 5811 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ount | +0.049 |
ll | +0.048 |
udd | +0.048 |
aris | +0.044 |
ari | +0.043 |
Neg logit contributions | |
Charlotte | -0.040 |
Becky | -0.040 |
ricia | -0.039 |
pillow | -0.037 |
Ruby | -0.037 |
Token | little |
Token ID | 1310 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
Charlotte | +0.009 |
Becky | +0.009 |
ricia | +0.009 |
Ruby | +0.008 |
pillow | +0.008 |
Neg logit contributions | |
udd | -0.013 |
ount | -0.013 |
ll | -0.013 |
ari | -0.011 |
won | -0.011 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ricia | +0.013 |
Charlotte | +0.012 |
Becky | +0.012 |
frantically | +0.012 |
idi | +0.012 |
Neg logit contributions | |
udd | -0.013 |
ll | -0.013 |
ount | -0.012 |
ari | -0.012 |
aris | -0.011 |
Token | named |
Token ID | 3706 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
Charlotte | +0.021 |
Becky | +0.020 |
ricia | +0.020 |
iflower | +0.019 |
pillow | +0.019 |
Neg logit contributions | |
udd | -0.016 |
ll | -0.016 |
ount | -0.016 |
ari | -0.014 |
won | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
ount | +0.069 |
udd | +0.068 |
ll | +0.067 |
aris | +0.062 |
ari | +0.060 |
Neg logit contributions | |
Becky | -0.055 |
Charlotte | -0.054 |
Ruby | -0.052 |
pillow | -0.049 |
Bonnie | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
Charlotte | +0.003 |
Becky | +0.003 |
ricia | +0.003 |
Ruby | +0.003 |
pillow | +0.003 |
Neg logit contributions | |
udd | -0.002 |
ll | -0.002 |
ount | -0.002 |
won | -0.002 |
aris | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -2.95e-03 |
Pos logit contributions | |
ount | +0.012 |
ll | +0.012 |
udd | +0.012 |
aris | +0.011 |
ari | +0.011 |
Neg logit contributions | |
Becky | -0.011 |
Charlotte | -0.011 |
Ruby | -0.011 |
pillow | -0.011 |
ricia | -0.010 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.40e-03 |
Pos logit contributions | |
rily | +0.005 |
Becky | +0.005 |
Charlotte | +0.005 |
ricia | +0.005 |
creature | +0.005 |
Neg logit contributions | |
ll | -0.004 |
udd | -0.004 |
won | -0.004 |
done | -0.004 |
ount | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -2.46e-05 |
Pos logit contributions | |
ount | +0.008 |
udd | +0.008 |
ll | +0.008 |
ari | +0.007 |
aris | +0.007 |
Neg logit contributions | |
Charlotte | -0.009 |
Becky | -0.009 |
pillow | -0.009 |
turkey | -0.009 |
veil | -0.009 |
Token | play |
Token ID | 711 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
Charlotte | +0.000 |
Becky | +0.000 |
ricia | +0.000 |
creature | +0.000 |
Ruby | +0.000 |
Neg logit contributions | |
ount | -0.000 |
ll | -0.000 |
udd | -0.000 |
aris | -0.000 |
won | -0.000 |
Token | outside |
Token ID | 2354 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
ricia | +0.034 |
Charlotte | +0.033 |
Becky | +0.033 |
creature | +0.030 |
iflower | +0.030 |
Neg logit contributions | |
udd | -0.037 |
ount | -0.037 |
ll | -0.036 |
aris | -0.033 |
won | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
ricia | +0.047 |
Charlotte | +0.043 |
iflower | +0.041 |
Becky | +0.041 |
rily | +0.040 |
Neg logit contributions | |
ll | -0.027 |
udd | -0.025 |
ount | -0.023 |
come | -0.023 |
m | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
Charlotte | +0.001 |
Becky | +0.001 |
ricia | +0.001 |
Ruby | +0.001 |
pillow | +0.001 |
Neg logit contributions | |
udd | -0.001 |
ll | -0.001 |
ount | -0.001 |
won | -0.001 |
aris | -0.000 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
ricia | +0.018 |
Becky | +0.017 |
Charlotte | +0.017 |
iflower | +0.017 |
creature | +0.017 |
Neg logit contributions | |
ount | -0.015 |
udd | -0.015 |
ll | -0.015 |
won | -0.014 |
done | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ricia | +0.040 |
Charlotte | +0.036 |
Becky | +0.034 |
issa | +0.034 |
iflower | +0.034 |
Neg logit contributions | |
udd | -0.026 |
won | -0.025 |
ll | -0.024 |
ount | -0.023 |
come | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
ricia | +0.033 |
Charlotte | +0.030 |
iflower | +0.030 |
wand | +0.030 |
Becky | +0.029 |
Neg logit contributions | |
ount | -0.027 |
ll | -0.026 |
udd | -0.025 |
pay | -0.025 |
lay | -0.025 |
Token | backyard |
Token ID | 24296 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ricia | +0.004 |
Charlotte | +0.004 |
Becky | +0.004 |
Ruby | +0.004 |
rily | +0.004 |
Neg logit contributions | |
udd | -0.002 |
ount | -0.002 |
ll | -0.002 |
won | -0.002 |
aris | -0.002 |
Token | when |
Token ID | 618 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ount | +0.028 |
ll | +0.027 |
udd | +0.027 |
aris | +0.024 |
ari | +0.024 |
Neg logit contributions | |
Charlotte | -0.026 |
Becky | -0.026 |
pillow | -0.025 |
ricia | -0.025 |
creature | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
ricia | +0.023 |
ches | +0.022 |
iflower | +0.022 |
rily | +0.022 |
Charlotte | +0.021 |
Neg logit contributions | |
Su | -0.013 |
ll | -0.013 |
ount | -0.013 |
won | -0.013 |
lay | -0.012 |
Token | started |
Token ID | 2067 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ount | +0.003 |
udd | +0.003 |
ll | +0.003 |
won | +0.002 |
aris | +0.002 |
Neg logit contributions | |
Charlotte | -0.002 |
Becky | -0.002 |
ricia | -0.002 |
pillow | -0.002 |
Ruby | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ount | +0.014 |
ll | +0.013 |
udd | +0.013 |
ari | +0.011 |
aris | +0.011 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.019 |
ricia | -0.018 |
pillow | -0.018 |
Ruby | -0.018 |
Token | rain |
Token ID | 6290 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
ount | +0.034 |
ll | +0.033 |
udd | +0.033 |
aris | +0.029 |
ari | +0.028 |
Neg logit contributions | |
Charlotte | -0.041 |
Becky | -0.041 |
ricia | -0.039 |
pillow | -0.039 |
Ruby | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -3.86e-03 |
Pos logit contributions | |
ount | +0.091 |
ll | +0.090 |
aris | +0.084 |
udd | +0.083 |
ari | +0.082 |
Neg logit contributions | |
Charlotte | -0.061 |
pillow | -0.060 |
Becky | -0.059 |
ricia | -0.058 |
cable | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
Charlotte | +0.001 |
Becky | +0.001 |
ricia | +0.001 |
pillow | +0.001 |
Ruby | +0.001 |
Neg logit contributions | |
ount | -0.002 |
ll | -0.002 |
udd | -0.002 |
aris | -0.002 |
won | -0.002 |
Token | rushed |
Token ID | 13999 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
Charlotte | +0.016 |
ricia | +0.016 |
Becky | +0.015 |
iflower | +0.015 |
pillow | +0.015 |
Neg logit contributions | |
ount | -0.014 |
udd | -0.014 |
won | -0.014 |
ll | -0.014 |
pay | -0.012 |
Token | over |
Token ID | 625 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
pillow | +0.005 |
iflower | +0.004 |
Neg logit contributions | |
ount | -0.005 |
ll | -0.005 |
udd | -0.005 |
won | -0.004 |
aris | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
Charlotte | +0.028 |
Becky | +0.028 |
ricia | +0.027 |
pillow | +0.026 |
Ruby | +0.026 |
Neg logit contributions | |
ount | -0.018 |
udd | -0.018 |
ll | -0.018 |
aris | -0.015 |
ari | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
ricia | +0.005 |
Charlotte | +0.005 |
Becky | +0.005 |
iflower | +0.005 |
pillow | +0.005 |
Neg logit contributions | |
ount | -0.004 |
ll | -0.004 |
won | -0.004 |
udd | -0.004 |
pay | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
pillow | +0.005 |
Ruby | +0.005 |
Neg logit contributions | |
ount | -0.005 |
ll | -0.005 |
udd | -0.005 |
aris | -0.004 |
won | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
Charlotte | +0.017 |
Becky | +0.017 |
ricia | +0.016 |
pillow | +0.016 |
Ruby | +0.016 |
Neg logit contributions | |
ll | -0.019 |
ount | -0.019 |
udd | -0.019 |
aris | -0.017 |
ari | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
Charlotte | +0.032 |
Becky | +0.032 |
ricia | +0.030 |
pillow | +0.030 |
iflower | +0.030 |
Neg logit contributions | |
ll | -0.025 |
won | -0.024 |
udd | -0.023 |
ount | -0.021 |
paid | -0.020 |
Token | so |
Token ID | 523 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
Charlotte | +0.037 |
Becky | +0.037 |
ricia | +0.035 |
pillow | +0.035 |
Ruby | +0.034 |
Neg logit contributions | |
ount | -0.035 |
ll | -0.034 |
udd | -0.034 |
aris | -0.030 |
ari | -0.030 |
Token | thrilled |
Token ID | 20536 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
Becky | +0.032 |
Charlotte | +0.031 |
frantically | +0.029 |
Bonnie | +0.029 |
Ruby | +0.028 |
Neg logit contributions | |
ount | -0.063 |
udd | -0.060 |
ari | -0.060 |
ll | -0.059 |
aris | -0.058 |
Token | he |
Token ID | 339 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ount | +0.023 |
udd | +0.022 |
ll | +0.022 |
aris | +0.020 |
ari | +0.020 |
Neg logit contributions | |
Charlotte | -0.021 |
Becky | -0.021 |
ricia | -0.020 |
creature | -0.020 |
pillow | -0.019 |
Token | sw |
Token ID | 1509 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Charlotte | +0.005 |
Becky | +0.005 |
ricia | +0.005 |
Ruby | +0.004 |
frantically | +0.004 |
Neg logit contributions | |
ll | -0.005 |
ount | -0.005 |
udd | -0.005 |
won | -0.005 |
ari | -0.005 |
Token | an |
Token ID | 272 |
Feature activation | +7.74e-03 |
Pos logit contributions | |
ount | +0.027 |
ll | +0.027 |
udd | +0.026 |
aris | +0.024 |
won | +0.024 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.017 |
ricia | -0.017 |
pillow | -0.016 |
creature | -0.016 |
Token | kept |
Token ID | 4030 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
ll | +0.013 |
ount | +0.013 |
udd | +0.012 |
won | +0.011 |
aris | +0.011 |
Neg logit contributions | |
Charlotte | -0.012 |
Becky | -0.012 |
ricia | -0.011 |
pillow | -0.011 |
iflower | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ricia | +0.063 |
Charlotte | +0.063 |
Becky | +0.063 |
iflower | +0.060 |
pillow | +0.060 |
Neg logit contributions | |
ount | -0.068 |
ll | -0.067 |
udd | -0.063 |
won | -0.063 |
lay | -0.060 |
Token | matching |
Token ID | 12336 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
Charlotte | +0.015 |
Becky | +0.015 |
ricia | +0.014 |
Ruby | +0.013 |
Bonnie | +0.013 |
Neg logit contributions | |
ll | -0.018 |
udd | -0.018 |
ount | -0.018 |
won | -0.017 |
pay | -0.016 |
Token | toy |
Token ID | 13373 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
ricia | +0.050 |
Charlotte | +0.049 |
Becky | +0.049 |
Anne | +0.044 |
Beck | +0.044 |
Neg logit contributions | |
ount | -0.044 |
won | -0.044 |
udd | -0.044 |
pay | -0.042 |
come | -0.042 |
Token | all |
Token ID | 477 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ricia | +0.088 |
Charlotte | +0.085 |
Becky | +0.083 |
idi | +0.079 |
iflower | +0.079 |
Neg logit contributions | |
ll | -0.071 |
udd | -0.068 |
ount | -0.067 |
won | -0.063 |
aris | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
Charlotte | +0.024 |
Becky | +0.024 |
ricia | +0.024 |
pillow | +0.023 |
iflower | +0.022 |
Neg logit contributions | |
ll | -0.022 |
ount | -0.022 |
udd | -0.021 |
won | -0.019 |
aris | -0.019 |
Token | herself |
Token ID | 5223 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ount | +0.003 |
pay | +0.003 |
ll | +0.003 |
udd | +0.003 |
come | +0.003 |
Neg logit contributions | |
ricia | -0.003 |
Charlotte | -0.003 |
iflower | -0.003 |
Becky | -0.003 |
turkey | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
Charlotte | +0.044 |
Becky | +0.043 |
ricia | +0.043 |
Ruby | +0.040 |
pillow | +0.040 |
Neg logit contributions | |
ount | -0.037 |
ll | -0.037 |
udd | -0.036 |
aris | -0.032 |
won | -0.032 |
Token | even |
Token ID | 772 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Charlotte | +0.009 |
Becky | +0.009 |
ricia | +0.009 |
pillow | +0.008 |
Ruby | +0.008 |
Neg logit contributions | |
ount | -0.009 |
ll | -0.009 |
udd | -0.009 |
won | -0.008 |
aris | -0.008 |
Token | named |
Token ID | 3706 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
Charlotte | +0.023 |
ricia | +0.023 |
Becky | +0.023 |
iflower | +0.022 |
rily | +0.022 |
Neg logit contributions | |
udd | -0.017 |
ount | -0.016 |
ll | -0.016 |
ari | -0.014 |
won | -0.014 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
ount | +0.064 |
ll | +0.063 |
udd | +0.063 |
aris | +0.057 |
ari | +0.056 |
Neg logit contributions | |
Charlotte | -0.057 |
Becky | -0.056 |
ricia | -0.053 |
Ruby | -0.053 |
pillow | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
Charlotte | +0.031 |
Becky | +0.030 |
ricia | +0.030 |
Ruby | +0.029 |
pillow | +0.028 |
Neg logit contributions | |
ll | -0.021 |
udd | -0.021 |
ount | -0.020 |
won | -0.018 |
aris | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
ount | +0.007 |
ll | +0.007 |
udd | +0.007 |
ari | +0.006 |
won | +0.006 |
Neg logit contributions | |
Becky | -0.006 |
Charlotte | -0.006 |
ricia | -0.006 |
Ruby | -0.006 |
pillow | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
rily | +0.011 |
Becky | +0.011 |
Charlotte | +0.010 |
ricia | +0.010 |
turkey | +0.010 |
Neg logit contributions | |
udd | -0.008 |
ll | -0.008 |
won | -0.007 |
done | -0.007 |
ount | -0.006 |
Token | four |
Token ID | 1440 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
ricia | +0.036 |
Charlotte | +0.036 |
Becky | +0.036 |
iflower | +0.034 |
pillow | +0.034 |
Neg logit contributions | |
ount | -0.050 |
udd | -0.048 |
ll | -0.048 |
won | -0.044 |
aris | -0.044 |
Token | years |
Token ID | 812 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
Charlotte | +0.069 |
Becky | +0.069 |
ricia | +0.066 |
Ruby | +0.063 |
Bonnie | +0.062 |
Neg logit contributions | |
udd | -0.083 |
ount | -0.079 |
ll | -0.078 |
aris | -0.071 |
ari | -0.071 |
Token | old |
Token ID | 1468 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
udd | +0.076 |
ount | +0.076 |
ll | +0.075 |
ari | +0.070 |
aris | +0.069 |
Neg logit contributions | |
Charlotte | -0.045 |
Becky | -0.043 |
ricia | -0.043 |
pillow | -0.040 |
Ruby | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
Becky | +0.007 |
Charlotte | +0.007 |
ricia | +0.007 |
iflower | +0.007 |
rily | +0.007 |
Neg logit contributions | |
udd | -0.005 |
ll | -0.005 |
ount | -0.005 |
ari | -0.004 |
won | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
rily | +0.023 |
ricia | +0.022 |
frantically | +0.022 |
le | +0.022 |
growth | +0.022 |
Neg logit contributions | |
ll | -0.018 |
won | -0.018 |
udd | -0.017 |
done | -0.017 |
paid | -0.016 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
ount | +0.018 |
udd | +0.017 |
ll | +0.017 |
ari | +0.015 |
OM | +0.015 |
Neg logit contributions | |
Charlotte | -0.019 |
Becky | -0.019 |
pillow | -0.019 |
turkey | -0.018 |
Ruby | -0.018 |
Token | Every |
Token ID | 3887 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
ll | +0.006 |
ount | +0.006 |
udd | +0.005 |
ari | +0.005 |
aris | +0.005 |
Neg logit contributions | |
Charlotte | -0.005 |
Becky | -0.005 |
Ruby | -0.004 |
pillow | -0.004 |
Bonnie | -0.004 |
Token | morning |
Token ID | 3329 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
won | +0.005 |
udd | +0.005 |
ll | +0.005 |
ount | +0.004 |
pay | +0.004 |
Neg logit contributions | |
Becky | -0.012 |
ricia | -0.012 |
Charlotte | -0.012 |
rily | -0.012 |
iflower | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | -4.77e-03 |
Pos logit contributions | |
Charlotte | +0.019 |
Becky | +0.019 |
pillow | +0.017 |
ricia | +0.017 |
Ruby | +0.017 |
Neg logit contributions | |
ount | -0.019 |
ll | -0.019 |
udd | -0.019 |
aris | -0.017 |
ari | -0.016 |
Token | would |
Token ID | 561 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Charlotte | +0.009 |
Becky | +0.009 |
ricia | +0.009 |
Ruby | +0.009 |
iflower | +0.009 |
Neg logit contributions | |
ll | -0.006 |
udd | -0.006 |
ount | -0.006 |
won | -0.005 |
ari | -0.005 |
Token | put |
Token ID | 1234 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
Charlotte | +0.034 |
Becky | +0.034 |
pillow | +0.032 |
ricia | +0.032 |
Ruby | +0.031 |
Neg logit contributions | |
ount | -0.029 |
udd | -0.028 |
ll | -0.028 |
aris | -0.025 |
ari | -0.024 |
Token | on |
Token ID | 319 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
ricia | +0.015 |
Charlotte | +0.015 |
Becky | +0.014 |
iflower | +0.013 |
frantically | +0.013 |
Neg logit contributions | |
ount | -0.019 |
udd | -0.018 |
won | -0.018 |
ll | -0.017 |
pay | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ricia | +0.052 |
Becky | +0.052 |
Charlotte | +0.051 |
creature | +0.048 |
iflower | +0.048 |
Neg logit contributions | |
udd | -0.112 |
ount | -0.111 |
ll | -0.106 |
won | -0.104 |
aris | -0.103 |
Token | teacher |
Token ID | 4701 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
ricia | +0.019 |
Becky | +0.018 |
Charlotte | +0.018 |
Alexa | +0.017 |
frantically | +0.017 |
Neg logit contributions | |
udd | -0.015 |
won | -0.015 |
ll | -0.015 |
ount | -0.014 |
aris | -0.013 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ricia | +0.004 |
Charlotte | +0.004 |
Becky | +0.004 |
iflower | +0.004 |
creature | +0.004 |
Neg logit contributions | |
ount | -0.005 |
udd | -0.005 |
ll | -0.005 |
aris | -0.005 |
ari | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
ount | +0.025 |
ll | +0.024 |
udd | +0.024 |
aris | +0.022 |
lay | +0.021 |
Neg logit contributions | |
Charlotte | -0.018 |
Becky | -0.017 |
pillow | -0.017 |
Ruby | -0.017 |
ricia | -0.016 |
Token | pick |
Token ID | 2298 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
Charlotte | +0.009 |
Becky | +0.009 |
ricia | +0.009 |
iflower | +0.008 |
creature | +0.008 |
Neg logit contributions | |
ount | -0.010 |
udd | -0.009 |
ll | -0.009 |
won | -0.009 |
aris | -0.009 |
Token | lift |
Token ID | 10303 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
Charlotte | +0.053 |
ricia | +0.052 |
issa | +0.050 |
Becky | +0.049 |
Bonnie | +0.048 |
Neg logit contributions | |
come | -0.028 |
pay | -0.028 |
ll | -0.028 |
ount | -0.027 |
won | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
Charlotte | +0.025 |
Becky | +0.025 |
ricia | +0.024 |
pillow | +0.023 |
iflower | +0.023 |
Neg logit contributions | |
ount | -0.029 |
udd | -0.028 |
ll | -0.028 |
won | -0.026 |
aris | -0.026 |
Token | car |
Token ID | 1097 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
Charlotte | +0.023 |
Becky | +0.022 |
ricia | +0.022 |
Ruby | +0.020 |
Bonnie | +0.020 |
Neg logit contributions | |
ll | -0.037 |
ount | -0.037 |
udd | -0.037 |
won | -0.035 |
aris | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
pillow | +0.015 |
Charlotte | +0.015 |
Becky | +0.015 |
creature | +0.015 |
cable | +0.014 |
Neg logit contributions | |
udd | -0.022 |
ll | -0.022 |
ount | -0.022 |
aris | -0.020 |
lay | -0.019 |
Token | Fel |
Token ID | 13937 |
Feature activation | -9.60e-03 |
Pos logit contributions | |
Charlotte | +0.013 |
Becky | +0.013 |
ricia | +0.012 |
Ruby | +0.012 |
pillow | +0.012 |
Neg logit contributions | |
ount | -0.014 |
ll | -0.014 |
udd | -0.014 |
aris | -0.012 |
won | -0.012 |
Token | icity |
Token ID | 8467 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
pillow | +0.011 |
Becky | +0.011 |
turkey | +0.011 |
Charlotte | +0.010 |
Ruby | +0.010 |
Neg logit contributions | |
ll | -0.018 |
ount | -0.018 |
udd | -0.018 |
ari | -0.017 |
aris | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
Charlotte | +0.078 |
Becky | +0.076 |
ricia | +0.073 |
pillow | +0.073 |
Ruby | +0.072 |
Neg logit contributions | |
ll | -0.073 |
udd | -0.071 |
ount | -0.070 |
won | -0.067 |
aris | -0.062 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Charlotte | +0.002 |
ricia | +0.002 |
Becky | +0.001 |
Ruby | +0.001 |
iflower | +0.001 |
Neg logit contributions | |
udd | -0.002 |
ll | -0.002 |
ount | -0.002 |
aris | -0.002 |
won | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
ount | +0.048 |
inconvenience | +0.041 |
aris | +0.039 |
udd | +0.038 |
arl | +0.037 |
Neg logit contributions | |
Charlotte | -0.063 |
Becky | -0.061 |
ricia | -0.061 |
pillow | -0.059 |
thumb | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
ount | +0.007 |
udd | +0.006 |
ll | +0.006 |
aris | +0.006 |
arl | +0.006 |
Neg logit contributions | |
Charlotte | -0.005 |
Becky | -0.005 |
ricia | -0.005 |
pillow | -0.005 |
frantically | -0.005 |
Token | daddy |
Token ID | 35822 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
Charlotte | +0.011 |
Becky | +0.011 |
ricia | +0.011 |
pillow | +0.010 |
Ruby | +0.010 |
Neg logit contributions | |
ount | -0.018 |
ll | -0.018 |
udd | -0.018 |
aris | -0.016 |
won | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
Charlotte | +0.002 |
Ruby | +0.002 |
Becky | +0.002 |
Bonnie | +0.002 |
cable | +0.002 |
Neg logit contributions | |
ount | -0.004 |
inconvenience | -0.004 |
ari | -0.004 |
ll | -0.004 |
udd | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -8.26e-05 |
Pos logit contributions | |
ount | +0.008 |
udd | +0.007 |
ll | +0.007 |
aris | +0.007 |
ari | +0.006 |
Neg logit contributions | |
Charlotte | -0.008 |
Becky | -0.008 |
ricia | -0.008 |
Ruby | -0.008 |
pillow | -0.008 |
Token | Tim |
Token ID | 14967 |
Feature activation | -8.62e-03 |
Pos logit contributions | |
Charlotte | +0.000 |
ricia | +0.000 |
cable | +0.000 |
frantically | +0.000 |
idi | +0.000 |
Neg logit contributions | |
ount | -0.000 |
ll | -0.000 |
aris | -0.000 |
udd | -0.000 |
ari | -0.000 |
Token | my |
Token ID | 1820 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
Charlotte | +0.019 |
ricia | +0.019 |
Becky | +0.018 |
pillow | +0.018 |
Ruby | +0.018 |
Neg logit contributions | |
ount | -0.010 |
udd | -0.008 |
ll | -0.008 |
aris | -0.007 |
ari | -0.007 |
Token | put |
Token ID | 1234 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
Becky | +0.045 |
Charlotte | +0.044 |
iflower | +0.042 |
ricia | +0.042 |
creature | +0.042 |
Neg logit contributions | |
udd | -0.029 |
ll | -0.028 |
won | -0.027 |
ount | -0.023 |
done | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
Charlotte | +0.011 |
Becky | +0.011 |
ricia | +0.011 |
comet | +0.010 |
creature | +0.010 |
Neg logit contributions | |
udd | -0.011 |
ount | -0.010 |
ll | -0.010 |
won | -0.010 |
done | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ricia | +0.081 |
Becky | +0.078 |
creature | +0.076 |
Charlotte | +0.076 |
worm | +0.075 |
Neg logit contributions | |
udd | -0.101 |
done | -0.094 |
pay | -0.093 |
ount | -0.093 |
won | -0.092 |
Token | favorite |
Token ID | 4004 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
ricia | +0.026 |
Becky | +0.025 |
Charlotte | +0.025 |
rily | +0.023 |
frantically | +0.023 |
Neg logit contributions | |
ll | -0.020 |
udd | -0.020 |
done | -0.019 |
come | -0.019 |
won | -0.018 |
Token | shirt |
Token ID | 10147 |
Feature activation | -7.05e-04 |
Pos logit contributions | |
ricia | +0.041 |
Charlotte | +0.037 |
Becky | +0.037 |
issa | +0.036 |
rily | +0.036 |
Neg logit contributions | |
come | -0.029 |
parties | -0.025 |
party | -0.025 |
udd | -0.024 |
pay | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
Charlotte | +0.001 |
Becky | +0.001 |
ricia | +0.001 |
pillow | +0.001 |
Ruby | +0.001 |
Neg logit contributions | |
ount | -0.001 |
ll | -0.001 |
udd | -0.001 |
aris | -0.001 |
won | -0.001 |
Token | climbed |
Token ID | 19952 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
ricia | +0.004 |
creature | +0.004 |
Becky | +0.004 |
Charlotte | +0.004 |
unia | +0.004 |
Neg logit contributions | |
won | -0.003 |
udd | -0.002 |
ll | -0.002 |
pay | -0.002 |
paid | -0.002 |