Token | of |
Token ID | 286 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
wheel | +0.015 |
sill | +0.015 |
hot | +0.013 |
aback | +0.013 |
icle | +0.012 |
Neg logit contributions | |
ls | -0.042 |
cks | -0.040 |
vows | -0.040 |
irs | -0.037 |
nations | -0.037 |
Token | cheese |
Token ID | 9891 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.006 |
vows | +0.006 |
ves | +0.006 |
irs | +0.005 |
Neg logit contributions | |
sill | -0.006 |
operation | -0.005 |
cleaner | -0.005 |
aback | -0.005 |
wheel | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.006 |
vows | +0.006 |
irs | +0.006 |
nations | +0.006 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
hot | -0.004 |
icle | -0.004 |
bar | -0.004 |
Token | sauce |
Token ID | 10746 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
sill | +0.002 |
wheel | +0.002 |
hot | +0.002 |
cleaner | +0.002 |
icle | +0.002 |
Neg logit contributions | |
ls | -0.003 |
cks | -0.003 |
irs | -0.003 |
vows | -0.003 |
its | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +6.10e-03 |
Pos logit contributions | |
ls | +0.006 |
cks | +0.006 |
irs | +0.006 |
vows | +0.006 |
nations | +0.005 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
hot | -0.004 |
icle | -0.004 |
bar | -0.004 |
Token | topp |
Token ID | 23126 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
ls | +0.013 |
irs | +0.012 |
cks | +0.012 |
vows | +0.012 |
ves | +0.011 |
Neg logit contributions | |
sill | -0.008 |
wheel | -0.007 |
cleaner | -0.007 |
hot | -0.007 |
vest | -0.007 |
Token | ings |
Token ID | 654 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
irs | +0.141 |
ls | +0.140 |
nations | +0.134 |
arrest | +0.127 |
risking | +0.127 |
Neg logit contributions | |
est | -0.132 |
icle | -0.132 |
sill | -0.121 |
bar | -0.115 |
uit | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
ls | +0.039 |
cks | +0.036 |
vows | +0.035 |
irs | +0.033 |
nations | +0.033 |
Neg logit contributions | |
hot | -0.032 |
wheel | -0.029 |
sill | -0.029 |
icle | -0.028 |
uit | -0.027 |
Token | The |
Token ID | 383 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
ls | +0.029 |
cks | +0.027 |
vows | +0.026 |
irs | +0.024 |
ves | +0.024 |
Neg logit contributions | |
wheel | -0.033 |
sill | -0.031 |
hot | -0.030 |
uster | -0.030 |
aback | -0.030 |
Token | people |
Token ID | 661 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ls | +0.018 |
cks | +0.016 |
vows | +0.016 |
irs | +0.015 |
ves | +0.015 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.016 |
hot | -0.015 |
icle | -0.015 |
uster | -0.015 |
Token | who |
Token ID | 508 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ls | +0.080 |
vows | +0.074 |
irs | +0.072 |
cks | +0.072 |
ves | +0.069 |
Neg logit contributions | |
wheel | -0.068 |
hot | -0.064 |
sill | -0.063 |
he | -0.060 |
boat | -0.058 |
Token | monkeys |
Token ID | 26697 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
ls | +0.029 |
irs | +0.028 |
cks | +0.028 |
its | +0.027 |
vows | +0.027 |
Neg logit contributions | |
sill | -0.023 |
wheel | -0.022 |
3 | -0.021 |
bear | -0.020 |
my | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ls | +0.100 |
vows | +0.099 |
irs | +0.098 |
heit | +0.091 |
cks | +0.091 |
Neg logit contributions | |
sill | -0.047 |
wheel | -0.046 |
hot | -0.042 |
bar | -0.040 |
my | -0.038 |
Token | elephants |
Token ID | 25368 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
ls | +0.048 |
irs | +0.047 |
cks | +0.046 |
vows | +0.045 |
its | +0.045 |
Neg logit contributions | |
sill | -0.042 |
wheel | -0.040 |
3 | -0.037 |
vest | -0.036 |
hot | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
ls | +0.106 |
vows | +0.102 |
irs | +0.102 |
cks | +0.097 |
heit | +0.097 |
Neg logit contributions | |
sill | -0.061 |
wheel | -0.060 |
hot | -0.056 |
bar | -0.052 |
my | -0.049 |
Token | gir |
Token ID | 37370 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
ls | +0.042 |
irs | +0.040 |
cks | +0.039 |
vows | +0.038 |
its | +0.038 |
Neg logit contributions | |
sill | -0.038 |
wheel | -0.035 |
vest | -0.032 |
3 | -0.032 |
hot | -0.032 |
Token | aff |
Token ID | 2001 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
vows | +0.078 |
cks | +0.077 |
ls | +0.077 |
spills | +0.075 |
irs | +0.074 |
Neg logit contributions | |
sill | -0.087 |
wheel | -0.086 |
est | -0.084 |
hot | -0.082 |
bar | -0.082 |
Token | es |
Token ID | 274 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
passports | +0.143 |
vows | +0.137 |
spills | +0.134 |
heit | +0.133 |
hides | +0.127 |
Neg logit contributions | |
ah | -0.109 |
bird | -0.104 |
my | -0.104 |
ter | -0.100 |
est | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
ls | +0.061 |
cks | +0.058 |
vows | +0.057 |
irs | +0.057 |
heit | +0.054 |
Neg logit contributions | |
sill | -0.038 |
wheel | -0.037 |
hot | -0.036 |
uit | -0.032 |
est | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
ls | +0.042 |
cks | +0.038 |
vows | +0.037 |
ils | +0.034 |
irs | +0.034 |
Neg logit contributions | |
sill | -0.047 |
wheel | -0.046 |
hot | -0.045 |
icle | -0.043 |
uster | -0.043 |
Token | were |
Token ID | 547 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
ls | +0.063 |
irs | +0.061 |
cks | +0.060 |
vows | +0.056 |
its | +0.055 |
Neg logit contributions | |
wheel | -0.048 |
sill | -0.048 |
my | -0.044 |
hot | -0.043 |
happiest | -0.041 |
Token | very |
Token ID | 845 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
ls | +0.016 |
vows | +0.015 |
irs | +0.015 |
cks | +0.014 |
ves | +0.014 |
Neg logit contributions | |
sill | -0.010 |
wheel | -0.009 |
happiest | -0.008 |
hot | -0.008 |
bar | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
ls | +0.058 |
vows | +0.053 |
cks | +0.052 |
ves | +0.049 |
irs | +0.048 |
Neg logit contributions | |
sill | -0.043 |
wheel | -0.040 |
hot | -0.040 |
aback | -0.039 |
vest | -0.038 |
Token | air |
Token ID | 1633 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
wheel | +0.010 |
hot | +0.009 |
icle | +0.009 |
uster | +0.009 |
sill | +0.009 |
Neg logit contributions | |
ls | -0.011 |
cks | -0.010 |
runs | -0.010 |
vows | -0.010 |
nations | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ls | +0.030 |
cks | +0.027 |
vows | +0.026 |
irs | +0.026 |
ves | +0.025 |
Neg logit contributions | |
sill | -0.026 |
wheel | -0.026 |
hot | -0.024 |
icle | -0.023 |
bar | -0.023 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ls | +0.021 |
cks | +0.019 |
vows | +0.019 |
ves | +0.018 |
irs | +0.018 |
Neg logit contributions | |
wheel | -0.014 |
sill | -0.013 |
hot | -0.013 |
uster | -0.012 |
icle | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
irs | +0.040 |
ls | +0.040 |
cks | +0.040 |
ves | +0.039 |
vows | +0.038 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
aback | -0.016 |
my | -0.016 |
vest | -0.016 |
Token | True |
Token ID | 6407 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
ls | +0.023 |
cks | +0.022 |
vows | +0.021 |
irs | +0.020 |
ves | +0.020 |
Neg logit contributions | |
sill | -0.011 |
wheel | -0.011 |
hot | -0.011 |
aback | -0.011 |
Vest | -0.010 |
Token | think |
Token ID | 892 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ls | +0.175 |
ves | +0.166 |
irs | +0.164 |
cks | +0.158 |
pulp | +0.146 |
Neg logit contributions | |
sill | -0.097 |
hot | -0.095 |
wheel | -0.095 |
expert | -0.093 |
3 | -0.092 |
Token | he |
Token ID | 339 |
Feature activation | -4.45e-03 |
Pos logit contributions | |
cks | +0.048 |
ls | +0.046 |
vows | +0.043 |
irs | +0.043 |
cor | +0.041 |
Neg logit contributions | |
hot | -0.035 |
wheel | -0.035 |
sill | -0.033 |
operation | -0.032 |
vest | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.008 |
hot | +0.008 |
Vest | +0.008 |
vest | +0.008 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.006 |
vows | -0.006 |
irs | -0.006 |
ves | -0.006 |
Token | crazy |
Token ID | 7165 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
ls | +0.019 |
vows | +0.017 |
ves | +0.016 |
cks | +0.016 |
irs | +0.016 |
Neg logit contributions | |
wheel | -0.011 |
sill | -0.011 |
hot | -0.010 |
happiest | -0.010 |
Vest | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.006 |
aback | +0.006 |
est | +0.006 |
Neg logit contributions | |
ls | -0.008 |
cks | -0.007 |
vows | -0.007 |
irs | -0.007 |
ves | -0.007 |
Token | sund |
Token ID | 37437 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ls | +0.014 |
vows | +0.013 |
cks | +0.012 |
cor | +0.012 |
ves | +0.012 |
Neg logit contributions | |
uster | -0.011 |
aback | -0.011 |
wheel | -0.011 |
Vest | -0.011 |
sill | -0.010 |
Token | ae |
Token ID | 3609 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ls | +0.030 |
vows | +0.029 |
ves | +0.029 |
cks | +0.028 |
ils | +0.027 |
Neg logit contributions | |
aback | -0.028 |
wheel | -0.027 |
hot | -0.026 |
sill | -0.026 |
Vest | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
ls | +0.031 |
cks | +0.029 |
vows | +0.028 |
irs | +0.027 |
ves | +0.026 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.024 |
hot | -0.023 |
icle | -0.022 |
uster | -0.022 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ls | +0.050 |
cks | +0.046 |
ves | +0.043 |
vows | +0.043 |
nations | +0.043 |
Neg logit contributions | |
sill | -0.030 |
wheel | -0.029 |
hot | -0.029 |
icle | -0.028 |
bar | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ls | +0.029 |
cks | +0.028 |
vows | +0.027 |
irs | +0.026 |
nations | +0.026 |
Neg logit contributions | |
wheel | -0.009 |
sill | -0.009 |
hot | -0.008 |
icle | -0.007 |
est | -0.007 |
Token | topp |
Token ID | 23126 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
ls | +0.041 |
cks | +0.040 |
nations | +0.037 |
irs | +0.037 |
vows | +0.036 |
Neg logit contributions | |
sill | -0.026 |
wheel | -0.025 |
icle | -0.024 |
est | -0.024 |
cleaner | -0.023 |
Token | ings |
Token ID | 654 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
ls | +0.146 |
irs | +0.141 |
nations | +0.140 |
cks | +0.134 |
countries | +0.127 |
Neg logit contributions | |
icle | -0.126 |
est | -0.121 |
sill | -0.116 |
uit | -0.111 |
bar | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +3.67e-03 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.007 |
vows | +0.006 |
ves | +0.006 |
irs | +0.006 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.007 |
uster | -0.007 |
aback | -0.007 |
hot | -0.007 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.006 |
vows | +0.006 |
irs | +0.006 |
runs | +0.006 |
Neg logit contributions | |
wheel | -0.005 |
sill | -0.005 |
uster | -0.005 |
hot | -0.005 |
Vest | -0.005 |
Token | my |
Token ID | 1820 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
wheel | +0.013 |
uster | +0.013 |
hot | +0.012 |
sill | +0.012 |
aback | +0.010 |
Neg logit contributions | |
ls | -0.032 |
cks | -0.032 |
runs | -0.031 |
ils | -0.030 |
its | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
ls | +0.044 |
cks | +0.041 |
irs | +0.040 |
vows | +0.038 |
nations | +0.037 |
Neg logit contributions | |
wheel | -0.038 |
sill | -0.037 |
hot | -0.035 |
vest | -0.034 |
est | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.013 |
vows | +0.013 |
ves | +0.012 |
nations | +0.012 |
Neg logit contributions | |
wheel | -0.013 |
sill | -0.012 |
uster | -0.012 |
hot | -0.011 |
Vest | -0.011 |
Token | sauce |
Token ID | 10746 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
wheel | +0.027 |
sill | +0.026 |
uster | +0.026 |
hot | +0.025 |
aback | +0.025 |
Neg logit contributions | |
ls | -0.029 |
cks | -0.026 |
vows | -0.026 |
ves | -0.024 |
points | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
ls | +0.018 |
cks | +0.018 |
vows | +0.017 |
irs | +0.017 |
nations | +0.016 |
Neg logit contributions | |
wheel | -0.011 |
sill | -0.011 |
hot | -0.011 |
icle | -0.010 |
bar | -0.010 |
Token | cheese |
Token ID | 9891 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ls | +0.010 |
cks | +0.009 |
vows | +0.009 |
irs | +0.008 |
ves | +0.008 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.007 |
hot | -0.007 |
uster | -0.006 |
aback | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +7.90e-03 |
Pos logit contributions | |
ls | +0.046 |
cks | +0.044 |
vows | +0.042 |
irs | +0.042 |
nations | +0.040 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.025 |
hot | -0.024 |
icle | -0.023 |
bar | -0.022 |
Token | topp |
Token ID | 23126 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
ls | +0.017 |
cks | +0.016 |
vows | +0.015 |
irs | +0.015 |
ves | +0.014 |
Neg logit contributions | |
sill | -0.011 |
wheel | -0.011 |
hot | -0.010 |
icle | -0.010 |
bar | -0.010 |
Token | ings |
Token ID | 654 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ls | +0.132 |
irs | +0.128 |
nations | +0.124 |
boarding | +0.120 |
arrest | +0.118 |
Neg logit contributions | |
icle | -0.132 |
est | -0.131 |
sill | -0.124 |
hot | -0.117 |
uit | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ls | +0.036 |
cks | +0.033 |
vows | +0.032 |
nations | +0.030 |
irs | +0.030 |
Neg logit contributions | |
wheel | -0.032 |
hot | -0.031 |
sill | -0.031 |
icle | -0.029 |
aback | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
ls | +0.017 |
cks | +0.015 |
vows | +0.015 |
irs | +0.014 |
ves | +0.014 |
Neg logit contributions | |
wheel | -0.018 |
sill | -0.017 |
hot | -0.016 |
uster | -0.016 |
aback | -0.016 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
irs | +0.011 |
vows | +0.011 |
nations | +0.011 |
Neg logit contributions | |
wheel | -0.011 |
sill | -0.010 |
hot | -0.010 |
icle | -0.010 |
bar | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
vows | +0.011 |
ves | +0.010 |
nations | +0.010 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.025 |
hot | -0.025 |
aback | -0.024 |
icle | -0.024 |
Token | monkeys |
Token ID | 26697 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
ls | +0.055 |
cks | +0.053 |
its | +0.049 |
irs | +0.049 |
vows | +0.049 |
Neg logit contributions | |
sill | -0.050 |
wheel | -0.048 |
3 | -0.046 |
hot | -0.044 |
vest | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
ls | +0.072 |
vows | +0.071 |
irs | +0.069 |
cks | +0.068 |
heit | +0.065 |
Neg logit contributions | |
sill | -0.033 |
wheel | -0.032 |
hot | -0.030 |
uit | -0.027 |
my | -0.027 |
Token | elephants |
Token ID | 25368 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
ls | +0.034 |
its | +0.033 |
cks | +0.033 |
irs | +0.033 |
vows | +0.031 |
Neg logit contributions | |
sill | -0.026 |
wheel | -0.023 |
3 | -0.022 |
vest | -0.022 |
bear | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ls | +0.097 |
vows | +0.094 |
irs | +0.094 |
cks | +0.093 |
heit | +0.091 |
Neg logit contributions | |
sill | -0.058 |
wheel | -0.055 |
hot | -0.053 |
uit | -0.047 |
bar | -0.047 |
Token | gir |
Token ID | 37370 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
ls | +0.035 |
irs | +0.034 |
cks | +0.034 |
its | +0.033 |
vows | +0.032 |
Neg logit contributions | |
sill | -0.030 |
wheel | -0.027 |
vest | -0.025 |
3 | -0.025 |
happiest | -0.025 |
Token | aff |
Token ID | 2001 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
ls | +0.073 |
cks | +0.072 |
vows | +0.072 |
spills | +0.070 |
passports | +0.069 |
Neg logit contributions | |
sill | -0.086 |
wheel | -0.085 |
est | -0.083 |
hot | -0.079 |
bar | -0.079 |
Token | es |
Token ID | 274 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
passports | +0.138 |
vows | +0.132 |
heit | +0.130 |
spills | +0.129 |
hides | +0.120 |
Neg logit contributions | |
ah | -0.105 |
my | -0.102 |
bird | -0.102 |
est | -0.097 |
ter | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ls | +0.061 |
cks | +0.060 |
vows | +0.057 |
irs | +0.057 |
heit | +0.055 |
Neg logit contributions | |
sill | -0.040 |
wheel | -0.038 |
hot | -0.038 |
uit | -0.034 |
est | -0.034 |
Token | They |
Token ID | 1119 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ls | +0.044 |
cks | +0.040 |
vows | +0.039 |
ils | +0.036 |
ves | +0.035 |
Neg logit contributions | |
sill | -0.048 |
wheel | -0.047 |
hot | -0.046 |
icle | -0.044 |
uster | -0.044 |
Token | had |
Token ID | 550 |
Feature activation | -2.22e-03 |
Pos logit contributions | |
ls | +0.059 |
cks | +0.057 |
irs | +0.056 |
its | +0.051 |
vows | +0.050 |
Neg logit contributions | |
sill | -0.045 |
wheel | -0.044 |
hot | -0.041 |
my | -0.040 |
happiest | -0.040 |
Token | fun |
Token ID | 1257 |
Feature activation | +9.61e-04 |
Pos logit contributions | |
sill | +0.003 |
3 | +0.002 |
so | +0.002 |
happiest | +0.002 |
wheel | +0.002 |
Neg logit contributions | |
ls | -0.005 |
irs | -0.005 |
cks | -0.005 |
its | -0.005 |
vows | -0.005 |
Token | monkeys |
Token ID | 26697 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ls | +0.009 |
vows | +0.009 |
cks | +0.009 |
irs | +0.008 |
its | +0.008 |
Neg logit contributions | |
sill | -0.007 |
wheel | -0.006 |
hot | -0.006 |
bar | -0.006 |
est | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
ls | +0.063 |
vows | +0.063 |
irs | +0.060 |
cks | +0.059 |
ves | +0.057 |
Neg logit contributions | |
wheel | -0.037 |
sill | -0.035 |
hot | -0.032 |
bar | -0.032 |
uit | -0.031 |
Token | elephants |
Token ID | 25368 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
irs | +0.039 |
ls | +0.039 |
its | +0.037 |
cks | +0.036 |
vows | +0.036 |
Neg logit contributions | |
sill | -0.032 |
wheel | -0.028 |
3 | -0.028 |
bear | -0.026 |
my | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ls | +0.089 |
vows | +0.086 |
irs | +0.083 |
cks | +0.083 |
ves | +0.079 |
Neg logit contributions | |
wheel | -0.051 |
sill | -0.050 |
hot | -0.047 |
bar | -0.045 |
uit | -0.043 |
Token | gir |
Token ID | 37370 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
ls | +0.041 |
irs | +0.040 |
cks | +0.038 |
its | +0.037 |
vows | +0.037 |
Neg logit contributions | |
sill | -0.037 |
wheel | -0.033 |
3 | -0.031 |
happiest | -0.031 |
vest | -0.031 |
Token | aff |
Token ID | 2001 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
ls | +0.070 |
cks | +0.068 |
vows | +0.067 |
irs | +0.064 |
spills | +0.063 |
Neg logit contributions | |
wheel | -0.086 |
sill | -0.085 |
est | -0.082 |
hot | -0.082 |
bar | -0.081 |
Token | es |
Token ID | 274 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
passports | +0.130 |
vows | +0.125 |
spills | +0.124 |
heit | +0.114 |
hides | +0.113 |
Neg logit contributions | |
ah | -0.111 |
my | -0.104 |
bird | -0.103 |
uit | -0.100 |
ter | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +2.56e-03 |
Pos logit contributions | |
ls | +0.067 |
cks | +0.064 |
vows | +0.062 |
irs | +0.061 |
its | +0.058 |
Neg logit contributions | |
sill | -0.041 |
wheel | -0.040 |
hot | -0.039 |
uit | -0.036 |
est | -0.034 |
Token | too |
Token ID | 1165 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
ls | +0.005 |
irs | +0.005 |
vows | +0.005 |
cks | +0.005 |
ves | +0.005 |
Neg logit contributions | |
sill | -0.004 |
wheel | -0.003 |
hot | -0.003 |
bar | -0.003 |
icle | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
vows | +0.042 |
ls | +0.039 |
irs | +0.039 |
ils | +0.039 |
cks | +0.038 |
Neg logit contributions | |
sill | -0.018 |
wheel | -0.016 |
handy | -0.016 |
hot | -0.015 |
stump | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
ls | +0.026 |
cks | +0.024 |
vows | +0.023 |
ves | +0.022 |
ils | +0.021 |
Neg logit contributions | |
sill | -0.027 |
wheel | -0.026 |
hot | -0.025 |
icle | -0.024 |
uster | -0.024 |
Token | lions |
Token ID | 31420 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
ls | +0.056 |
cks | +0.053 |
its | +0.051 |
irs | +0.050 |
vows | +0.050 |
Neg logit contributions | |
sill | -0.048 |
wheel | -0.045 |
3 | -0.044 |
hot | -0.044 |
so | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
ls | +0.073 |
vows | +0.071 |
cks | +0.069 |
irs | +0.068 |
its | +0.064 |
Neg logit contributions | |
wheel | -0.035 |
sill | -0.033 |
hot | -0.033 |
uit | -0.030 |
est | -0.030 |
Token | elephants |
Token ID | 25368 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.013 |
its | +0.012 |
irs | +0.012 |
vows | +0.012 |
Neg logit contributions | |
sill | -0.009 |
wheel | -0.009 |
3 | -0.008 |
vest | -0.008 |
my | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
vows | +0.099 |
ls | +0.099 |
irs | +0.097 |
cks | +0.096 |
heit | +0.096 |
Neg logit contributions | |
wheel | -0.053 |
sill | -0.052 |
hot | -0.052 |
my | -0.046 |
uit | -0.046 |
Token | gir |
Token ID | 37370 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
ls | +0.033 |
cks | +0.033 |
irs | +0.032 |
its | +0.030 |
vows | +0.030 |
Neg logit contributions | |
sill | -0.027 |
wheel | -0.026 |
vest | -0.024 |
3 | -0.024 |
est | -0.024 |
Token | aff |
Token ID | 2001 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
ls | +0.069 |
cks | +0.069 |
vows | +0.067 |
spills | +0.063 |
irs | +0.062 |
Neg logit contributions | |
wheel | -0.089 |
hot | -0.086 |
sill | -0.086 |
est | -0.085 |
icle | -0.083 |
Token | es |
Token ID | 274 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
vows | +0.139 |
passports | +0.135 |
heit | +0.133 |
spills | +0.129 |
hides | +0.122 |
Neg logit contributions | |
uit | -0.109 |
my | -0.109 |
hot | -0.108 |
ah | -0.104 |
ock | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ls | +0.059 |
cks | +0.057 |
vows | +0.055 |
irs | +0.054 |
heit | +0.052 |
Neg logit contributions | |
wheel | -0.038 |
hot | -0.038 |
sill | -0.038 |
uit | -0.034 |
est | -0.033 |
Token | Anna |
Token ID | 11735 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ls | +0.033 |
cks | +0.033 |
irs | +0.032 |
vows | +0.028 |
nations | +0.028 |
Neg logit contributions | |
sill | -0.031 |
hot | -0.029 |
aback | -0.028 |
3 | -0.027 |
inter | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
cks | +0.049 |
irs | +0.048 |
ls | +0.048 |
its | +0.042 |
vows | +0.041 |
Neg logit contributions | |
sill | -0.032 |
my | -0.032 |
wheel | -0.032 |
3 | -0.031 |
vest | -0.030 |
Token | very |
Token ID | 845 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
hot | +0.002 |
uster | +0.002 |
icle | +0.002 |
Neg logit contributions | |
ls | -0.004 |
cks | -0.004 |
vows | -0.004 |
ves | -0.003 |
irs | -0.003 |
Token | lions |
Token ID | 31420 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
hot | +0.003 |
icle | +0.003 |
vest | +0.003 |
Neg logit contributions | |
ls | -0.003 |
cks | -0.003 |
vows | -0.003 |
irs | -0.003 |
ves | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ls | +0.067 |
vows | +0.063 |
cks | +0.062 |
irs | +0.061 |
ves | +0.057 |
Neg logit contributions | |
wheel | -0.043 |
sill | -0.042 |
hot | -0.040 |
bar | -0.037 |
icle | -0.037 |
Token | monkeys |
Token ID | 26697 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
ls | +0.021 |
cks | +0.020 |
its | +0.019 |
irs | +0.019 |
vows | +0.019 |
Neg logit contributions | |
sill | -0.014 |
wheel | -0.014 |
3 | -0.013 |
icle | -0.012 |
bar | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ls | +0.097 |
vows | +0.094 |
irs | +0.092 |
cks | +0.088 |
heit | +0.086 |
Neg logit contributions | |
wheel | -0.059 |
sill | -0.057 |
hot | -0.052 |
bar | -0.050 |
uit | -0.047 |
Token | gir |
Token ID | 37370 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
ls | +0.049 |
cks | +0.045 |
irs | +0.044 |
its | +0.044 |
ves | +0.043 |
Neg logit contributions | |
sill | -0.040 |
wheel | -0.038 |
3 | -0.036 |
vest | -0.034 |
hot | -0.034 |
Token | aff |
Token ID | 2001 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
ls | +0.070 |
vows | +0.068 |
cks | +0.068 |
irs | +0.065 |
spills | +0.064 |
Neg logit contributions | |
wheel | -0.086 |
sill | -0.082 |
hot | -0.081 |
bar | -0.080 |
est | -0.080 |
Token | es |
Token ID | 274 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
vows | +0.130 |
passports | +0.129 |
spills | +0.126 |
hides | +0.123 |
heit | +0.122 |
Neg logit contributions | |
ah | -0.108 |
my | -0.105 |
uit | -0.105 |
hot | -0.103 |
bird | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
ls | +0.060 |
cks | +0.058 |
vows | +0.056 |
irs | +0.054 |
heit | +0.052 |
Neg logit contributions | |
wheel | -0.040 |
sill | -0.040 |
hot | -0.040 |
uit | -0.036 |
aback | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ls | +0.028 |
cks | +0.026 |
vows | +0.025 |
ves | +0.023 |
irs | +0.023 |
Neg logit contributions | |
sill | -0.032 |
wheel | -0.032 |
hot | -0.031 |
uster | -0.030 |
icle | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
ls | +0.026 |
vows | +0.025 |
cks | +0.024 |
ils | +0.023 |
nations | +0.023 |
Neg logit contributions | |
wheel | -0.013 |
sill | -0.013 |
hot | -0.012 |
uster | -0.011 |
handy | -0.011 |
Token | They |
Token ID | 2990 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ls | +0.030 |
vows | +0.028 |
cks | +0.027 |
ils | +0.025 |
nations | +0.024 |
Neg logit contributions | |
hot | -0.021 |
wheel | -0.021 |
sill | -0.020 |
handy | -0.019 |
bar | -0.019 |
Token | water |
Token ID | 1660 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.015 |
ves | +0.014 |
vows | +0.013 |
irs | +0.013 |
Neg logit contributions | |
sill | -0.013 |
wheel | -0.012 |
vest | -0.012 |
est | -0.011 |
hot | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
ls | +0.006 |
cks | +0.006 |
vows | +0.005 |
irs | +0.005 |
ves | +0.005 |
Neg logit contributions | |
sill | -0.004 |
wheel | -0.004 |
hot | -0.004 |
est | -0.004 |
icle | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -4.20e-04 |
Pos logit contributions | |
ls | +0.002 |
vows | +0.002 |
cks | +0.002 |
irs | +0.002 |
nations | +0.002 |
Neg logit contributions | |
wheel | -0.002 |
icle | -0.002 |
sill | -0.002 |
bar | -0.002 |
Aid | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
hot | +0.001 |
uster | +0.001 |
icle | +0.001 |
Neg logit contributions | |
ls | -0.001 |
cks | -0.001 |
vows | -0.001 |
irs | -0.001 |
ves | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +5.94e-03 |
Pos logit contributions | |
ls | +0.010 |
cks | +0.009 |
vows | +0.009 |
irs | +0.008 |
ves | +0.008 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.007 |
hot | -0.007 |
uster | -0.007 |
aback | -0.007 |
Token | mer |
Token ID | 4017 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
ls | +0.012 |
cks | +0.012 |
irs | +0.011 |
ves | +0.011 |
vows | +0.010 |
Neg logit contributions | |
sill | -0.009 |
wheel | -0.008 |
vest | -0.008 |
hot | -0.008 |
Vest | -0.007 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
ls | +0.136 |
cks | +0.131 |
irs | +0.122 |
ves | +0.121 |
runs | +0.118 |
Neg logit contributions | |
sill | -0.120 |
wheel | -0.116 |
est | -0.115 |
uster | -0.112 |
expert | -0.109 |
Token | smiled |
Token ID | 13541 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
cks | +0.057 |
ls | +0.057 |
irs | +0.053 |
its | +0.051 |
vows | +0.049 |
Neg logit contributions | |
sill | -0.045 |
wheel | -0.044 |
bar | -0.042 |
est | -0.041 |
3 | -0.040 |
Token | at |
Token ID | 379 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
wheel | +0.018 |
Aid | +0.015 |
icle | +0.015 |
hot | +0.015 |
uster | +0.015 |
Neg logit contributions | |
ls | -0.016 |
vows | -0.014 |
points | -0.014 |
their | -0.013 |
cks | -0.013 |
Token | Melody |
Token ID | 38906 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.013 |
vows | +0.013 |
irs | +0.012 |
ves | +0.012 |
Neg logit contributions | |
wheel | -0.013 |
sill | -0.013 |
hot | -0.012 |
uster | -0.012 |
icle | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -8.50e-03 |
Pos logit contributions | |
ls | +0.008 |
cks | +0.008 |
vows | +0.008 |
irs | +0.008 |
its | +0.007 |
Neg logit contributions | |
sill | -0.004 |
wheel | -0.004 |
est | -0.004 |
hot | -0.004 |
aback | -0.004 |
Token | castle |
Token ID | 16669 |
Feature activation | -3.11e-03 |
Pos logit contributions | |
sill | +0.013 |
wheel | +0.012 |
hot | +0.011 |
vest | +0.011 |
uster | +0.011 |
Neg logit contributions | |
ls | -0.017 |
cks | -0.015 |
vows | -0.015 |
irs | -0.014 |
ves | -0.014 |
Token | so |
Token ID | 523 |
Feature activation | -5.55e-03 |
Pos logit contributions | |
uster | +0.005 |
hot | +0.005 |
wheel | +0.005 |
Aid | +0.005 |
aback | +0.005 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.004 |
vows | -0.004 |
ves | -0.004 |
runs | -0.004 |
Token | much |
Token ID | 881 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
sill | +0.008 |
wheel | +0.007 |
hot | +0.007 |
bar | +0.006 |
cleaner | +0.006 |
Neg logit contributions | |
cks | -0.011 |
ls | -0.011 |
vows | -0.011 |
irs | -0.010 |
ils | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -9.51e-03 |
Pos logit contributions | |
wheel | +0.024 |
sill | +0.024 |
hot | +0.023 |
uster | +0.022 |
icle | +0.022 |
Neg logit contributions | |
ls | -0.031 |
cks | -0.028 |
vows | -0.027 |
irs | -0.026 |
ves | -0.026 |
Token | The |
Token ID | 383 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
wheel | +0.013 |
uster | +0.012 |
sill | +0.012 |
Aid | +0.012 |
hot | +0.011 |
Neg logit contributions | |
ls | -0.019 |
vows | -0.018 |
cks | -0.017 |
their | -0.016 |
nations | -0.016 |
Token | mer |
Token ID | 4017 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
cks | +0.017 |
ls | +0.016 |
irs | +0.015 |
ves | +0.015 |
vows | +0.014 |
Neg logit contributions | |
sill | -0.013 |
wheel | -0.012 |
vest | -0.012 |
est | -0.011 |
Vest | -0.011 |
Token | maid |
Token ID | 23151 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
ls | +0.137 |
cks | +0.130 |
irs | +0.128 |
ves | +0.124 |
runs | +0.118 |
Neg logit contributions | |
sill | -0.122 |
est | -0.117 |
wheel | -0.109 |
icle | -0.103 |
uster | -0.103 |
Token | said |
Token ID | 531 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
cks | +0.055 |
ls | +0.054 |
irs | +0.053 |
vows | +0.050 |
nations | +0.049 |
Neg logit contributions | |
wheel | -0.038 |
sill | -0.036 |
bar | -0.035 |
hot | -0.034 |
vest | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.008 |
hot | +0.007 |
uster | +0.007 |
aback | +0.007 |
Neg logit contributions | |
ls | -0.010 |
cks | -0.009 |
vows | -0.009 |
irs | -0.009 |
ves | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -6.61e-04 |
Pos logit contributions | |
wheel | +0.025 |
sill | +0.024 |
uster | +0.023 |
hot | +0.023 |
aback | +0.022 |
Neg logit contributions | |
ls | -0.032 |
cks | -0.029 |
vows | -0.029 |
ves | -0.027 |
irs | -0.027 |
Token | I |
Token ID | 40 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
hot | +0.001 |
uster | +0.001 |
icle | +0.001 |
Neg logit contributions | |
ls | -0.001 |
cks | -0.001 |
vows | -0.001 |
irs | -0.001 |
ves | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
ls | +0.053 |
vows | +0.047 |
ves | +0.046 |
cks | +0.046 |
ils | +0.043 |
Neg logit contributions | |
sill | -0.042 |
hot | -0.039 |
wheel | -0.038 |
aback | -0.037 |
vest | -0.037 |
Token | tank |
Token ID | 6873 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
ls | +0.049 |
cks | +0.047 |
irs | +0.045 |
ves | +0.044 |
ils | +0.042 |
Neg logit contributions | |
sill | -0.048 |
vest | -0.047 |
knee | -0.044 |
wheel | -0.043 |
inter | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ls | +0.065 |
irs | +0.062 |
cks | +0.062 |
vows | +0.061 |
ves | +0.058 |
Neg logit contributions | |
sill | -0.049 |
wheel | -0.047 |
hot | -0.044 |
bar | -0.043 |
vest | -0.042 |
Token | The |
Token ID | 383 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ls | +0.027 |
cks | +0.025 |
vows | +0.024 |
irs | +0.023 |
ves | +0.023 |
Neg logit contributions | |
wheel | -0.024 |
sill | -0.023 |
hot | -0.022 |
uster | -0.021 |
aback | -0.021 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
ls | +0.030 |
cks | +0.027 |
vows | +0.027 |
nations | +0.025 |
ves | +0.025 |
Neg logit contributions | |
wheel | -0.021 |
sill | -0.020 |
hot | -0.019 |
uster | -0.019 |
aback | -0.018 |
Token | guys |
Token ID | 3730 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
ls | +0.031 |
cks | +0.029 |
vows | +0.028 |
irs | +0.026 |
ves | +0.026 |
Neg logit contributions | |
wheel | -0.029 |
sill | -0.028 |
hot | -0.027 |
uster | -0.026 |
icle | -0.026 |
Token | run |
Token ID | 1057 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
vows | +0.123 |
irs | +0.117 |
ls | +0.116 |
pulp | +0.109 |
ves | +0.109 |
Neg logit contributions | |
wheel | -0.123 |
he | -0.111 |
sill | -0.107 |
boat | -0.107 |
beam | -0.106 |
Token | away |
Token ID | 1497 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ls | +0.044 |
cks | +0.042 |
vows | +0.041 |
irs | +0.040 |
ves | +0.039 |
Neg logit contributions | |
wheel | -0.023 |
sill | -0.023 |
hot | -0.022 |
aback | -0.021 |
uster | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
ls | +0.062 |
cks | +0.060 |
irs | +0.059 |
vows | +0.059 |
ves | +0.056 |
Neg logit contributions | |
sill | -0.032 |
wheel | -0.029 |
aback | -0.027 |
hot | -0.026 |
handy | -0.026 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ls | +0.016 |
ves | +0.015 |
irs | +0.015 |
vows | +0.015 |
cks | +0.014 |
Neg logit contributions | |
sill | -0.015 |
wheel | -0.014 |
knee | -0.013 |
vest | -0.013 |
hot | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
irs | +0.050 |
ls | +0.048 |
vows | +0.046 |
cks | +0.045 |
ves | +0.043 |
Neg logit contributions | |
sill | -0.050 |
wheel | -0.049 |
knee | -0.047 |
aback | -0.046 |
vest | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | -3.76e-03 |
Pos logit contributions | |
ls | +0.007 |
ils | +0.007 |
cks | +0.007 |
irs | +0.007 |
vows | +0.006 |
Neg logit contributions | |
sill | -0.002 |
hot | -0.002 |
wheel | -0.002 |
3 | -0.002 |
handy | -0.002 |
Token | Free |
Token ID | 11146 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.006 |
icle | +0.005 |
bar | +0.005 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.007 |
vows | -0.007 |
ves | -0.006 |
irs | -0.006 |
Token | mel |
Token ID | 7758 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
ls | +0.050 |
cks | +0.043 |
irs | +0.040 |
vows | +0.039 |
ves | +0.037 |
Neg logit contributions | |
wheel | -0.047 |
sill | -0.047 |
hot | -0.045 |
icle | -0.044 |
est | -0.044 |
Token | on |
Token ID | 261 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
ls | +0.005 |
cks | +0.005 |
vows | +0.005 |
irs | +0.005 |
nations | +0.005 |
Neg logit contributions | |
wheel | -0.004 |
hot | -0.003 |
sill | -0.003 |
bar | -0.003 |
icle | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.015 |
vows | +0.014 |
irs | +0.014 |
nations | +0.013 |
Neg logit contributions | |
wheel | -0.012 |
hot | -0.011 |
sill | -0.011 |
bar | -0.010 |
icle | -0.010 |
Token | Enjoy |
Token ID | 18179 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
ls | +0.072 |
cks | +0.066 |
vows | +0.064 |
ves | +0.061 |
irs | +0.060 |
Neg logit contributions | |
wheel | -0.046 |
sill | -0.046 |
hot | -0.044 |
uster | -0.041 |
icle | -0.041 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ls | +0.139 |
cks | +0.122 |
irs | +0.120 |
vows | +0.117 |
nations | +0.111 |
Neg logit contributions | |
sill | -0.110 |
icle | -0.105 |
est | -0.100 |
uit | -0.098 |
wheel | -0.098 |
Token | They |
Token ID | 1119 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
ls | +0.020 |
cks | +0.018 |
vows | +0.018 |
ves | +0.017 |
irs | +0.017 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
hot | -0.016 |
uster | -0.016 |
bar | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ls | +0.053 |
cks | +0.049 |
irs | +0.046 |
ves | +0.043 |
its | +0.042 |
Neg logit contributions | |
wheel | -0.043 |
sill | -0.042 |
hot | -0.042 |
3 | -0.040 |
uit | -0.038 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
ls | +0.048 |
irs | +0.044 |
ves | +0.043 |
ils | +0.042 |
cks | +0.041 |
Neg logit contributions | |
sill | -0.022 |
wheel | -0.018 |
hesitant | -0.017 |
hot | -0.016 |
handy | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
ls | +0.044 |
cks | +0.043 |
vows | +0.042 |
irs | +0.042 |
heit | +0.041 |
Neg logit contributions | |
sill | -0.021 |
wheel | -0.019 |
hot | -0.017 |
vest | -0.017 |
cleaner | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
wheel | +0.016 |
sill | +0.015 |
hot | +0.015 |
uster | +0.014 |
icle | +0.014 |
Neg logit contributions | |
ls | -0.021 |
cks | -0.019 |
vows | -0.018 |
nations | -0.017 |
irs | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ls | +0.021 |
cks | +0.019 |
vows | +0.019 |
ves | +0.018 |
ils | +0.017 |
Neg logit contributions | |
sill | -0.016 |
wheel | -0.016 |
hot | -0.015 |
aback | -0.014 |
icle | -0.014 |
Token | sea |
Token ID | 5417 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.013 |
hot | +0.013 |
uster | +0.013 |
aback | +0.012 |
Neg logit contributions | |
ls | -0.021 |
cks | -0.019 |
vows | -0.019 |
irs | -0.017 |
nations | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ls | +0.033 |
cks | +0.030 |
vows | +0.029 |
irs | +0.028 |
ves | +0.027 |
Neg logit contributions | |
sill | -0.025 |
wheel | -0.025 |
hot | -0.024 |
bar | -0.023 |
aback | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +7.04e-03 |
Pos logit contributions | |
sill | +0.043 |
wheel | +0.043 |
hot | +0.040 |
aback | +0.038 |
icle | +0.038 |
Neg logit contributions | |
ls | -0.045 |
cks | -0.041 |
vows | -0.039 |
irs | -0.037 |
ves | -0.036 |
Token | mer |
Token ID | 4017 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.013 |
irs | +0.012 |
ves | +0.012 |
vows | +0.012 |
Neg logit contributions | |
sill | -0.011 |
wheel | -0.010 |
est | -0.009 |
vest | -0.009 |
3 | -0.009 |
Token | maid |
Token ID | 23151 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
ls | +0.136 |
irs | +0.136 |
cks | +0.135 |
ves | +0.129 |
runs | +0.129 |
Neg logit contributions | |
sill | -0.111 |
est | -0.107 |
imm | -0.093 |
boat | -0.092 |
wheel | -0.090 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
cks | +0.054 |
ls | +0.053 |
irs | +0.052 |
its | +0.049 |
vows | +0.049 |
Neg logit contributions | |
wheel | -0.040 |
sill | -0.040 |
boat | -0.036 |
bar | -0.035 |
est | -0.035 |
Token | chose |
Token ID | 7690 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ls | +0.026 |
cks | +0.024 |
irs | +0.023 |
vows | +0.022 |
nations | +0.022 |
Neg logit contributions | |
sill | -0.023 |
wheel | -0.022 |
hot | -0.020 |
bar | -0.020 |
aback | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-03 |
Pos logit contributions | |
sill | +0.019 |
wheel | +0.018 |
hot | +0.017 |
aback | +0.017 |
icle | +0.016 |
Neg logit contributions | |
ls | -0.027 |
cks | -0.026 |
vows | -0.024 |
irs | -0.024 |
ves | -0.023 |
Token | It |
Token ID | 632 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
wheel | +0.004 |
sill | +0.004 |
hot | +0.004 |
vest | +0.004 |
Aid | +0.004 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.005 |
vows | -0.005 |
irs | -0.005 |
nations | -0.005 |
Token | faces |
Token ID | 6698 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ls | +0.044 |
vows | +0.039 |
cks | +0.039 |
irs | +0.039 |
ves | +0.034 |
Neg logit contributions | |
sill | -0.070 |
est | -0.068 |
wheel | -0.065 |
vest | -0.064 |
hot | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | +5.47e-03 |
Pos logit contributions | |
ls | +0.042 |
cks | +0.039 |
vows | +0.038 |
irs | +0.036 |
ves | +0.035 |
Neg logit contributions | |
wheel | -0.023 |
sill | -0.023 |
hot | -0.021 |
icle | -0.020 |
uster | -0.020 |
Token | shapes |
Token ID | 15268 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ls | +0.011 |
cks | +0.010 |
irs | +0.010 |
vows | +0.009 |
ves | +0.008 |
Neg logit contributions | |
sill | -0.009 |
wheel | -0.009 |
cleaner | -0.008 |
vest | -0.008 |
hot | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
ls | +0.042 |
cks | +0.039 |
irs | +0.038 |
vows | +0.038 |
heit | +0.037 |
Neg logit contributions | |
sill | -0.029 |
wheel | -0.027 |
hot | -0.025 |
icle | -0.025 |
cleaner | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
ls | +0.068 |
cks | +0.062 |
vows | +0.059 |
ves | +0.058 |
irs | +0.056 |
Neg logit contributions | |
sill | -0.050 |
hot | -0.047 |
icle | -0.045 |
3 | -0.044 |
cleaner | -0.044 |
Token | topp |
Token ID | 23126 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
ls | +0.018 |
cks | +0.016 |
vows | +0.016 |
irs | +0.015 |
ves | +0.015 |
Neg logit contributions | |
sill | -0.015 |
wheel | -0.015 |
hot | -0.014 |
icle | -0.014 |
vest | -0.014 |
Token | ings |
Token ID | 654 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
ls | +0.129 |
irs | +0.119 |
cks | +0.114 |
nations | +0.111 |
boarding | +0.108 |
Neg logit contributions | |
est | -0.127 |
icle | -0.126 |
sill | -0.126 |
uit | -0.112 |
bar | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ls | +0.005 |
cks | +0.005 |
vows | +0.005 |
irs | +0.004 |
ves | +0.004 |
Neg logit contributions | |
wheel | -0.005 |
sill | -0.005 |
hot | -0.005 |
uster | -0.005 |
icle | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ls | +0.033 |
cks | +0.030 |
vows | +0.030 |
ves | +0.028 |
irs | +0.028 |
Neg logit contributions | |
sill | -0.023 |
wheel | -0.022 |
hot | -0.021 |
uster | -0.020 |
icle | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
ls | +0.023 |
cks | +0.022 |
vows | +0.022 |
ils | +0.020 |
nations | +0.020 |
Neg logit contributions | |
wheel | -0.013 |
sill | -0.012 |
hot | -0.012 |
uster | -0.011 |
icle | -0.011 |
Token | " |
Token ID | 1 |
Feature activation | -5.25e-04 |
Pos logit contributions | |
ls | +0.037 |
cks | +0.035 |
vows | +0.034 |
ils | +0.031 |
irs | +0.031 |
Neg logit contributions | |
hot | -0.024 |
wheel | -0.023 |
sill | -0.023 |
uster | -0.022 |
handy | -0.021 |
Token | ashes |
Token ID | 7465 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.006 |
vows | +0.005 |
runs | +0.005 |
ves | +0.005 |
Neg logit contributions | |
Tooth | -0.014 |
Vest | -0.014 |
vest | -0.014 |
wheel | -0.014 |
sill | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
ls | +0.023 |
vows | +0.022 |
cks | +0.022 |
irs | +0.021 |
ves | +0.020 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
hot | -0.016 |
aback | -0.015 |
icle | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
ls | +0.032 |
cks | +0.029 |
vows | +0.027 |
irs | +0.027 |
nations | +0.026 |
Neg logit contributions | |
sill | -0.030 |
wheel | -0.028 |
hot | -0.028 |
icle | -0.027 |
uster | -0.027 |
Token | laugh |
Token ID | 6487 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ls | +0.094 |
cks | +0.085 |
vows | +0.082 |
irs | +0.081 |
ves | +0.080 |
Neg logit contributions | |
wheel | -0.068 |
sill | -0.066 |
hot | -0.060 |
beam | -0.058 |
vest | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
ls | +0.061 |
cks | +0.056 |
vows | +0.055 |
ves | +0.052 |
irs | +0.051 |
Neg logit contributions | |
wheel | -0.043 |
sill | -0.042 |
hot | -0.040 |
uster | -0.039 |
icle | -0.038 |
Token | g |
Token ID | 308 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
ls | +0.010 |
cks | +0.009 |
vows | +0.009 |
irs | +0.008 |
ves | +0.008 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.008 |
hot | -0.008 |
vest | -0.007 |
aback | -0.007 |
Token | iggle |
Token ID | 24082 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ls | +0.170 |
cks | +0.152 |
vows | +0.152 |
cor | +0.149 |
ves | +0.145 |
Neg logit contributions | |
wheel | -0.082 |
sill | -0.080 |
icle | -0.075 |
uster | -0.075 |
inter | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
ls | +0.049 |
cks | +0.046 |
vows | +0.044 |
irs | +0.044 |
ves | +0.041 |
Neg logit contributions | |
sill | -0.038 |
wheel | -0.038 |
hot | -0.037 |
est | -0.034 |
uster | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
ls | +0.037 |
cks | +0.035 |
irs | +0.033 |
ils | +0.033 |
vows | +0.033 |
Neg logit contributions | |
sill | -0.019 |
hot | -0.017 |
3 | -0.016 |
aback | -0.015 |
wheel | -0.015 |
Token | feel |
Token ID | 1254 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
ls | +0.068 |
cks | +0.062 |
vows | +0.058 |
irs | +0.057 |
ves | +0.056 |
Neg logit contributions | |
wheel | -0.057 |
sill | -0.055 |
hot | -0.051 |
vest | -0.049 |
aback | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
wheel | +0.015 |
sill | +0.014 |
bar | +0.013 |
hot | +0.013 |
uster | +0.013 |
Neg logit contributions | |
ls | -0.018 |
cks | -0.017 |
vows | -0.016 |
irs | -0.015 |
runs | -0.015 |
Token | 're |
Token ID | 821 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
ls | +0.023 |
cks | +0.021 |
ves | +0.019 |
vows | +0.018 |
irs | +0.018 |
Neg logit contributions | |
wheel | -0.026 |
hot | -0.026 |
sill | -0.025 |
aback | -0.024 |
Vest | -0.024 |
Token | welcome |
Token ID | 7062 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
ls | +0.004 |
cks | +0.004 |
vows | +0.004 |
nations | +0.004 |
irs | +0.004 |
Neg logit contributions | |
wheel | -0.002 |
uster | -0.002 |
sill | -0.002 |
bar | -0.001 |
hot | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
ls | +0.054 |
cks | +0.052 |
vows | +0.049 |
irs | +0.049 |
ves | +0.047 |
Neg logit contributions | |
sill | -0.035 |
wheel | -0.033 |
hot | -0.033 |
aback | -0.031 |
uit | -0.031 |
Token | kids |
Token ID | 3988 |
Feature activation | +9.17e-03 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
hot | +0.003 |
uster | +0.003 |
aback | +0.003 |
Neg logit contributions | |
ls | -0.004 |
cks | -0.003 |
vows | -0.003 |
ves | -0.003 |
irs | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.014 |
vows | +0.014 |
irs | +0.012 |
ves | +0.012 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.016 |
hot | -0.015 |
uster | -0.015 |
aback | -0.015 |
Token | Enjoy |
Token ID | 18179 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
ls | +0.009 |
cks | +0.008 |
vows | +0.008 |
runs | +0.008 |
irs | +0.008 |
Neg logit contributions | |
wheel | -0.006 |
sill | -0.006 |
hot | -0.005 |
uster | -0.005 |
vest | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
ls | +0.140 |
cks | +0.121 |
irs | +0.119 |
vows | +0.115 |
pulp | +0.114 |
Neg logit contributions | |
sill | -0.109 |
uit | -0.100 |
wheel | -0.099 |
icle | -0.097 |
handy | -0.097 |
Token | show |
Token ID | 905 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
wheel | +0.005 |
sill | +0.004 |
vest | +0.004 |
est | +0.004 |
hot | +0.004 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.005 |
irs | -0.005 |
vows | -0.005 |
ves | -0.005 |
Token | !" |
Token ID | 2474 |
Feature activation | +9.43e-03 |
Pos logit contributions | |
ls | +0.028 |
cks | +0.025 |
vows | +0.024 |
irs | +0.023 |
ves | +0.022 |
Neg logit contributions | |
wheel | -0.023 |
sill | -0.023 |
hot | -0.022 |
icle | -0.021 |
est | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
ls | +0.020 |
cks | +0.019 |
vows | +0.018 |
irs | +0.017 |
ils | +0.017 |
Neg logit contributions | |
sill | -0.013 |
wheel | -0.013 |
hot | -0.012 |
aback | -0.011 |
uster | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ls | +0.013 |
vows | +0.012 |
cks | +0.012 |
irs | +0.011 |
ils | +0.011 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.007 |
hot | -0.007 |
uster | -0.006 |
aback | -0.006 |
Token | anas |
Token ID | 15991 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
ls | +0.058 |
cks | +0.052 |
vows | +0.050 |
irs | +0.047 |
nations | +0.046 |
Neg logit contributions | |
wheel | -0.064 |
sill | -0.063 |
hot | -0.060 |
uster | -0.059 |
icle | -0.058 |
Token | available |
Token ID | 1695 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ls | +0.090 |
cks | +0.082 |
vows | +0.075 |
irs | +0.073 |
nations | +0.072 |
Neg logit contributions | |
wheel | -0.078 |
hot | -0.078 |
icle | -0.073 |
sill | -0.072 |
uit | -0.071 |
Token | for |
Token ID | 329 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ls | +0.022 |
cks | +0.020 |
vows | +0.019 |
irs | +0.019 |
nations | +0.018 |
Neg logit contributions | |
wheel | -0.013 |
hot | -0.013 |
sill | -0.012 |
icle | -0.012 |
uit | -0.012 |
Token | feeding |
Token ID | 13017 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
ls | +0.038 |
vows | +0.032 |
cks | +0.032 |
its | +0.029 |
ves | +0.029 |
Neg logit contributions | |
wheel | -0.029 |
icle | -0.029 |
hot | -0.028 |
operation | -0.028 |
sill | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ls | +0.074 |
cks | +0.067 |
vows | +0.064 |
irs | +0.059 |
ves | +0.059 |
Neg logit contributions | |
hot | -0.070 |
wheel | -0.069 |
sill | -0.068 |
icle | -0.067 |
aback | -0.064 |
Token | gor |
Token ID | 30344 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
irs | +0.043 |
ls | +0.042 |
cks | +0.039 |
packs | +0.036 |
ils | +0.036 |
Neg logit contributions | |
sill | -0.047 |
est | -0.046 |
3 | -0.044 |
happiest | -0.041 |
operation | -0.041 |
Token | illas |
Token ID | 25314 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
vows | +0.117 |
ls | +0.112 |
runs | +0.110 |
spills | +0.106 |
irs | +0.105 |
Neg logit contributions | |
bar | -0.110 |
ive | -0.109 |
mallow | -0.109 |
sill | -0.106 |
wheel | -0.105 |
Token | ." |
Token ID | 526 |
Feature activation | -3.59e-04 |
Pos logit contributions | |
ls | +0.091 |
cks | +0.084 |
vows | +0.080 |
irs | +0.078 |
ves | +0.077 |
Neg logit contributions | |
wheel | -0.070 |
sill | -0.069 |
hot | -0.068 |
icle | -0.063 |
handy | -0.062 |
Token | She |
Token ID | 1375 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
wheel | +0.000 |
sill | +0.000 |
hot | +0.000 |
uster | +0.000 |
aback | +0.000 |
Neg logit contributions | |
ls | -0.001 |
cks | -0.001 |
vows | -0.001 |
irs | -0.001 |
ves | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.007 |
hot | +0.006 |
bar | +0.006 |
vest | +0.006 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.006 |
irs | -0.006 |
vows | -0.006 |
nations | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +9.14e-03 |
Pos logit contributions | |
ls | +0.009 |
cks | +0.009 |
irs | +0.008 |
nations | +0.008 |
vows | +0.008 |
Neg logit contributions | |
wheel | -0.005 |
hot | -0.005 |
sill | -0.005 |
icle | -0.005 |
aback | -0.004 |
Token | One |
Token ID | 3198 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
ls | +0.031 |
cks | +0.030 |
irs | +0.029 |
vows | +0.029 |
ils | +0.027 |
Neg logit contributions | |
sill | -0.015 |
hot | -0.015 |
wheel | -0.014 |
est | -0.013 |
Whe | -0.012 |
Token | day |
Token ID | 1110 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
wheel | +0.004 |
aback | +0.004 |
uster | +0.004 |
bar | +0.004 |
hot | +0.004 |
Neg logit contributions | |
ls | -0.005 |
vows | -0.005 |
cks | -0.005 |
ves | -0.005 |
runs | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
cks | +0.040 |
irs | +0.037 |
its | +0.036 |
nations | +0.036 |
ils | +0.036 |
Neg logit contributions | |
est | -0.004 |
3 | -0.004 |
hot | -0.004 |
icle | -0.003 |
aback | -0.003 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
sill | +0.006 |
3 | +0.006 |
icle | +0.005 |
hot | +0.005 |
Whe | +0.005 |
Neg logit contributions | |
cks | -0.010 |
irs | -0.009 |
ls | -0.009 |
nations | -0.009 |
ils | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
cks | +0.034 |
irs | +0.033 |
ls | +0.033 |
vows | +0.032 |
ves | +0.031 |
Neg logit contributions | |
sill | -0.020 |
my | -0.019 |
wheel | -0.019 |
vest | -0.019 |
est | -0.018 |
Token | Coco |
Token ID | 48222 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
ls | +0.017 |
cks | +0.016 |
vows | +0.015 |
irs | +0.015 |
ves | +0.015 |
Neg logit contributions | |
wheel | -0.012 |
hot | -0.012 |
sill | -0.012 |
vest | -0.012 |
Vest | -0.011 |
Token | go |
Token ID | 467 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
cks | +0.173 |
irs | +0.157 |
ves | +0.156 |
ls | +0.154 |
ants | +0.150 |
Neg logit contributions | |
hot | -0.078 |
my | -0.076 |
happiest | -0.075 |
wheel | -0.075 |
vest | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
ls | +0.016 |
cks | +0.015 |
vows | +0.014 |
irs | +0.013 |
ves | +0.013 |
Neg logit contributions | |
wheel | -0.014 |
sill | -0.014 |
hot | -0.013 |
uster | -0.013 |
aback | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
ls | +0.004 |
cks | +0.004 |
vows | +0.004 |
ves | +0.004 |
irs | +0.004 |
Neg logit contributions | |
wheel | -0.003 |
sill | -0.003 |
hot | -0.003 |
aback | -0.003 |
vest | -0.003 |
Token | park |
Token ID | 3952 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
wheel | +0.015 |
sill | +0.015 |
hot | +0.014 |
uster | +0.014 |
aback | +0.014 |
Neg logit contributions | |
ls | -0.016 |
vows | -0.014 |
cks | -0.014 |
nations | -0.013 |
ves | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
ls | +0.031 |
cks | +0.028 |
vows | +0.027 |
ves | +0.025 |
nations | +0.025 |
Neg logit contributions | |
wheel | -0.028 |
sill | -0.027 |
hot | -0.027 |
uster | -0.027 |
icle | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
ls | +0.023 |
cks | +0.021 |
irs | +0.019 |
ves | +0.019 |
vows | +0.019 |
Neg logit contributions | |
wheel | -0.022 |
sill | -0.022 |
hot | -0.021 |
icle | -0.021 |
uster | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
wheel | +0.011 |
sill | +0.011 |
hot | +0.010 |
icle | +0.010 |
uster | +0.010 |
Neg logit contributions | |
ls | -0.011 |
cks | -0.010 |
ves | -0.010 |
vows | -0.010 |
irs | -0.009 |
Token | S |
Token ID | 50 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
sill | +0.004 |
wheel | +0.004 |
icle | +0.004 |
hot | +0.004 |
uster | +0.004 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.004 |
vows | -0.004 |
ves | -0.004 |
irs | -0.004 |
Token | ki |
Token ID | 4106 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
ls | +0.023 |
cks | +0.021 |
irs | +0.020 |
vows | +0.020 |
ils | +0.019 |
Neg logit contributions | |
sill | -0.014 |
wheel | -0.013 |
hot | -0.012 |
knee | -0.012 |
icle | -0.012 |
Token | pping |
Token ID | 2105 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
wheel | +0.026 |
sill | +0.025 |
hot | +0.024 |
bar | +0.024 |
est | +0.023 |
Neg logit contributions | |
ls | -0.027 |
cks | -0.025 |
vows | -0.025 |
irs | -0.023 |
nations | -0.022 |
Token | mer |
Token ID | 4017 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
wheel | +0.011 |
sill | +0.010 |
hot | +0.010 |
icle | +0.010 |
uster | +0.010 |
Neg logit contributions | |
ls | -0.012 |
cks | -0.011 |
vows | -0.010 |
ves | -0.010 |
runs | -0.010 |
Token | rily |
Token ID | 28904 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ls | +0.129 |
cks | +0.118 |
vows | +0.117 |
irs | +0.117 |
nations | +0.116 |
Neg logit contributions | |
wheel | -0.107 |
uster | -0.107 |
est | -0.106 |
sill | -0.105 |
imm | -0.102 |
Token | along |
Token ID | 1863 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ls | +0.019 |
cks | +0.017 |
vows | +0.016 |
irs | +0.016 |
nations | +0.015 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
hot | -0.016 |
aback | -0.016 |
icle | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ls | +0.020 |
cks | +0.019 |
vows | +0.018 |
ves | +0.017 |
nations | +0.017 |
Neg logit contributions | |
wheel | -0.019 |
sill | -0.019 |
hot | -0.018 |
uster | -0.018 |
icle | -0.018 |
Token | Hawk |
Token ID | 26698 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
wheel | +0.029 |
hot | +0.028 |
sill | +0.028 |
icle | +0.028 |
uster | +0.028 |
Neg logit contributions | |
ls | -0.037 |
cks | -0.034 |
vows | -0.033 |
runs | -0.032 |
cor | -0.032 |
Token | came |
Token ID | 1625 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
ls | +0.024 |
cks | +0.022 |
vows | +0.021 |
irs | +0.020 |
nations | +0.019 |
Neg logit contributions | |
wheel | -0.020 |
sill | -0.020 |
hot | -0.019 |
bar | -0.018 |
aback | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
wheel | +0.027 |
sill | +0.026 |
icle | +0.025 |
uster | +0.025 |
bar | +0.025 |
Neg logit contributions | |
ls | -0.036 |
vows | -0.031 |
runs | -0.030 |
cks | -0.030 |
points | -0.029 |
Token | said |
Token ID | 531 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
wheel | +0.032 |
sill | +0.031 |
hot | +0.030 |
uster | +0.030 |
icle | +0.030 |
Neg logit contributions | |
ls | -0.028 |
cks | -0.025 |
vows | -0.024 |
ves | -0.022 |
runs | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
cks | +0.008 |
ls | +0.008 |
vows | +0.007 |
irs | +0.007 |
nations | +0.007 |
Neg logit contributions | |
wheel | -0.004 |
hot | -0.004 |
sill | -0.004 |
aback | -0.003 |
knee | -0.003 |
Token | thank |
Token ID | 40716 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
wheel | +0.054 |
uster | +0.054 |
sill | +0.053 |
vest | +0.052 |
aback | +0.051 |
Neg logit contributions | |
ls | -0.053 |
cks | -0.047 |
its | -0.047 |
ves | -0.045 |
vows | -0.045 |
Token | you |
Token ID | 345 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
ls | +0.001 |
cks | +0.000 |
runs | +0.000 |
ils | +0.000 |
them | +0.000 |
Neg logit contributions | |
sill | -0.003 |
uster | -0.003 |
inter | -0.003 |
wheel | -0.003 |
boat | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
wheel | +0.030 |
Aid | +0.030 |
Whe | +0.029 |
sill | +0.029 |
Vest | +0.029 |
Neg logit contributions | |
ls | -0.020 |
vows | -0.020 |
their | -0.019 |
them | -0.018 |
ves | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
Vest | +0.154 |
icle | +0.154 |
uster | +0.153 |
bar | +0.153 |
initely | +0.152 |
Neg logit contributions | |
ls | -0.111 |
they | -0.091 |
their | -0.082 |
s | -0.082 |
runs | -0.080 |
Token | her |
Token ID | 607 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
ls | +0.006 |
cks | +0.006 |
irs | +0.005 |
vows | +0.005 |
runs | +0.005 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.007 |
hot | -0.007 |
aback | -0.007 |
uster | -0.007 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
aback | +0.015 |
wheel | +0.015 |
initely | +0.015 |
sill | +0.014 |
hot | +0.014 |
Neg logit contributions | |
ls | -0.009 |
their | -0.008 |
they | -0.007 |
vows | -0.007 |
ies | -0.007 |
Token | my |
Token ID | 1820 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
uster | +0.040 |
wheel | +0.039 |
Aid | +0.038 |
Vest | +0.038 |
Whe | +0.037 |
Neg logit contributions | |
ls | -0.091 |
cks | -0.084 |
their | -0.083 |
runs | -0.083 |
ies | -0.081 |
Token | for |
Token ID | 329 |
Feature activation | +8.88e-04 |
Pos logit contributions | |
wheel | +0.061 |
sill | +0.058 |
Aid | +0.058 |
icle | +0.058 |
uster | +0.057 |
Neg logit contributions | |
ls | -0.040 |
cks | -0.034 |
vows | -0.033 |
runs | -0.031 |
nations | -0.031 |
Token | understand |
Token ID | 1833 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
bar | +0.001 |
hot | +0.001 |
icle | +0.001 |
Neg logit contributions | |
ls | -0.001 |
vows | -0.001 |
cks | -0.001 |
runs | -0.001 |
nations | -0.001 |
Token | what |
Token ID | 644 |
Feature activation | +9.64e-03 |
Pos logit contributions | |
wheel | +0.026 |
sill | +0.025 |
uster | +0.024 |
hot | +0.024 |
bar | +0.024 |
Neg logit contributions | |
ls | -0.028 |
cks | -0.026 |
vows | -0.024 |
nations | -0.023 |
ves | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
ls | +0.017 |
cks | +0.016 |
vows | +0.015 |
ves | +0.015 |
nations | +0.014 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.016 |
uster | -0.015 |
hot | -0.015 |
aback | -0.015 |
Token | mod |
Token ID | 4666 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
uster | +0.051 |
wheel | +0.050 |
sill | +0.049 |
aback | +0.048 |
Vest | +0.047 |
Neg logit contributions | |
ls | -0.070 |
cks | -0.064 |
ves | -0.060 |
vows | -0.060 |
its | -0.058 |
Token | est |
Token ID | 395 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
wheel | +0.016 |
sill | +0.013 |
hot | +0.013 |
Aid | +0.013 |
uster | +0.012 |
Neg logit contributions | |
ls | -0.073 |
vows | -0.067 |
cks | -0.067 |
nations | -0.065 |
its | -0.065 |
Token | " |
Token ID | 1 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
wheel | +0.028 |
sill | +0.028 |
hot | +0.027 |
uster | +0.026 |
icle | +0.026 |
Neg logit contributions | |
ls | -0.033 |
cks | -0.030 |
vows | -0.029 |
irs | -0.027 |
ves | -0.027 |
Token | meant |
Token ID | 4001 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
uster | +0.140 |
Aid | +0.136 |
Vest | +0.135 |
knee | +0.129 |
initely | +0.128 |
Neg logit contributions | |
ls | -0.127 |
ves | -0.105 |
vows | -0.102 |
runs | -0.098 |
they | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
wheel | +0.030 |
sill | +0.030 |
hot | +0.029 |
icle | +0.027 |
aback | +0.027 |
Neg logit contributions | |
ls | -0.045 |
cks | -0.042 |
vows | -0.040 |
irs | -0.039 |
ils | -0.037 |
Token | but |
Token ID | 475 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Aid | +0.038 |
uster | +0.038 |
wheel | +0.038 |
Vest | +0.038 |
aback | +0.037 |
Neg logit contributions | |
ls | -0.070 |
vows | -0.063 |
ves | -0.063 |
points | -0.063 |
cks | -0.062 |
Token | he |
Token ID | 339 |
Feature activation | -2.66e-03 |
Pos logit contributions | |
wheel | +0.028 |
sill | +0.027 |
uster | +0.026 |
hot | +0.026 |
aback | +0.025 |
Neg logit contributions | |
ls | -0.039 |
cks | -0.036 |
vows | -0.035 |
ves | -0.033 |
nations | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -9.54e-03 |
Pos logit contributions | |
wheel | +0.005 |
sill | +0.004 |
hot | +0.004 |
aback | +0.004 |
icle | +0.004 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.004 |
vows | -0.004 |
irs | -0.004 |
nations | -0.004 |
Token | would |
Token ID | 561 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
sill | +0.003 |
wheel | +0.003 |
bar | +0.003 |
aback | +0.003 |
vest | +0.003 |
Neg logit contributions | |
ls | -0.004 |
cks | -0.004 |
irs | -0.004 |
vows | -0.003 |
nations | -0.003 |
Token | whisper |
Token ID | 31992 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
ls | +0.053 |
cks | +0.047 |
vows | +0.044 |
ves | +0.043 |
irs | +0.043 |
Neg logit contributions | |
sill | -0.042 |
wheel | -0.041 |
hot | -0.038 |
vest | -0.037 |
bar | -0.037 |
Token | " |
Token ID | 366 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.014 |
vows | +0.014 |
irs | +0.013 |
ves | +0.013 |
Neg logit contributions | |
wheel | -0.012 |
sill | -0.012 |
hot | -0.011 |
aback | -0.010 |
uster | -0.010 |
Token | thank |
Token ID | 40716 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
wheel | +0.043 |
sill | +0.041 |
uster | +0.040 |
hot | +0.039 |
aback | +0.039 |
Neg logit contributions | |
ls | -0.058 |
cks | -0.054 |
vows | -0.052 |
irs | -0.049 |
ves | -0.049 |
Token | you |
Token ID | 345 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
wheel | +0.013 |
sill | +0.012 |
uster | +0.012 |
hot | +0.012 |
icle | +0.012 |
Neg logit contributions | |
ls | -0.008 |
cks | -0.007 |
vows | -0.006 |
ves | -0.006 |
irs | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
wheel | +0.013 |
sill | +0.013 |
hot | +0.012 |
aback | +0.012 |
uster | +0.012 |
Neg logit contributions | |
ls | -0.010 |
vows | -0.009 |
cks | -0.009 |
ves | -0.008 |
irs | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +8.08e-03 |
Pos logit contributions | |
uster | +0.137 |
knee | +0.136 |
icle | +0.136 |
Vest | +0.136 |
bar | +0.135 |
Neg logit contributions | |
ls | -0.123 |
vows | -0.101 |
ves | -0.098 |
points | -0.093 |
runs | -0.092 |
Token | whoever |
Token ID | 16958 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
vows | +0.012 |
irs | +0.011 |
ves | +0.011 |
Neg logit contributions | |
wheel | -0.015 |
sill | -0.014 |
hot | -0.014 |
uster | -0.014 |
aback | -0.013 |
Token | put |
Token ID | 1234 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ls | +0.018 |
cks | +0.017 |
irs | +0.016 |
vows | +0.016 |
its | +0.014 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
hot | -0.016 |
aback | -0.015 |
est | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
wheel | +0.052 |
sill | +0.050 |
hot | +0.048 |
uster | +0.048 |
aback | +0.046 |
Neg logit contributions | |
ls | -0.046 |
cks | -0.041 |
vows | -0.039 |
ves | -0.037 |
irs | -0.036 |
Token | there |
Token ID | 612 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
wheel | +0.036 |
sill | +0.035 |
hot | +0.033 |
uster | +0.032 |
aback | +0.032 |
Neg logit contributions | |
ls | -0.054 |
cks | -0.050 |
vows | -0.049 |
irs | -0.046 |
ves | -0.046 |
Token | he |
Token ID | 339 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
ls | +0.012 |
cks | +0.011 |
vows | +0.010 |
irs | +0.010 |
ves | +0.010 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.008 |
hot | -0.007 |
aback | -0.007 |
uster | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -5.98e-04 |
Pos logit contributions | |
wheel | +0.052 |
sill | +0.051 |
hot | +0.049 |
uster | +0.048 |
icle | +0.048 |
Neg logit contributions | |
ls | -0.042 |
cks | -0.037 |
vows | -0.037 |
ves | -0.033 |
irs | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
uster | +0.001 |
hot | +0.001 |
bar | +0.001 |
Neg logit contributions | |
ls | -0.001 |
vows | -0.001 |
cks | -0.001 |
ves | -0.001 |
runs | -0.001 |
Token | thank |
Token ID | 40716 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
uster | +0.058 |
wheel | +0.056 |
knee | +0.055 |
operation | +0.055 |
inter | +0.054 |
Neg logit contributions | |
ls | -0.069 |
vows | -0.069 |
cks | -0.067 |
cor | -0.065 |
ils | -0.064 |
Token | you |
Token ID | 345 |
Feature activation | -7.69e-03 |
Pos logit contributions | |
wheel | +0.004 |
uster | +0.004 |
inter | +0.004 |
sill | +0.004 |
bar | +0.004 |
Neg logit contributions | |
ls | -0.002 |
cks | -0.001 |
vows | -0.001 |
cor | -0.001 |
ils | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
wheel | +0.016 |
sill | +0.016 |
aback | +0.016 |
Aid | +0.016 |
uster | +0.015 |
Neg logit contributions | |
vows | -0.010 |
ls | -0.009 |
ves | -0.008 |
cks | -0.007 |
cor | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +7.74e-03 |
Pos logit contributions | |
knee | +0.138 |
initely | +0.136 |
uster | +0.136 |
ivering | +0.135 |
operation | +0.134 |
Neg logit contributions | |
ls | -0.112 |
they | -0.090 |
ves | -0.089 |
vows | -0.087 |
runs | -0.085 |
Token | his |
Token ID | 465 |
Feature activation | +1.59e-03 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
vows | +0.012 |
irs | +0.011 |
ves | +0.011 |
Neg logit contributions | |
hot | -0.013 |
wheel | -0.013 |
sill | -0.013 |
aback | -0.013 |
uster | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
ls | +0.003 |
vows | +0.002 |
cks | +0.002 |
runs | +0.002 |
ves | +0.002 |
Neg logit contributions | |
wheel | -0.003 |
hot | -0.003 |
uster | -0.003 |
aback | -0.003 |
sill | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-03 |
Pos logit contributions | |
wheel | +0.040 |
uster | +0.039 |
Aid | +0.038 |
aback | +0.038 |
sill | +0.038 |
Neg logit contributions | |
ls | -0.029 |
vows | -0.027 |
cks | -0.026 |
runs | -0.024 |
nations | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
wheel | +0.002 |
sill | +0.002 |
hot | +0.002 |
aback | +0.002 |
uster | +0.002 |
Neg logit contributions | |
ls | -0.003 |
cks | -0.002 |
vows | -0.002 |
irs | -0.002 |
ves | -0.002 |
Token | know |
Token ID | 760 |
Feature activation | -3.34e-04 |
Pos logit contributions | |
sill | +0.006 |
bar | +0.006 |
wheel | +0.006 |
icle | +0.006 |
Vest | +0.006 |
Neg logit contributions | |
ls | -0.005 |
vows | -0.004 |
runs | -0.004 |
cks | -0.004 |
points | -0.004 |
Token | what |
Token ID | 644 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
hot | +0.001 |
uster | +0.001 |
aback | +0.001 |
Neg logit contributions | |
ls | -0.001 |
cks | -0.000 |
vows | -0.000 |
irs | -0.000 |
ves | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
ls | +0.005 |
cks | +0.005 |
vows | +0.005 |
ves | +0.005 |
nations | +0.004 |
Neg logit contributions | |
sill | -0.006 |
wheel | -0.005 |
uster | -0.005 |
aback | -0.005 |
hot | -0.005 |
Token | mod |
Token ID | 4666 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
sill | +0.052 |
wheel | +0.051 |
uster | +0.051 |
Vest | +0.048 |
aback | +0.048 |
Neg logit contributions | |
ls | -0.071 |
cks | -0.065 |
ves | -0.060 |
vows | -0.060 |
its | -0.059 |
Token | est |
Token ID | 395 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
wheel | +0.019 |
sill | +0.016 |
Aid | +0.016 |
handy | +0.016 |
uit | +0.015 |
Neg logit contributions | |
ls | -0.068 |
its | -0.062 |
cks | -0.061 |
runs | -0.061 |
nations | -0.060 |
Token | " |
Token ID | 1 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
wheel | +0.013 |
sill | +0.012 |
hot | +0.012 |
uster | +0.011 |
icle | +0.011 |
Neg logit contributions | |
ls | -0.017 |
cks | -0.016 |
vows | -0.015 |
irs | -0.015 |
ves | -0.014 |
Token | meant |
Token ID | 4001 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
uster | +0.142 |
Aid | +0.140 |
Vest | +0.138 |
initely | +0.133 |
knee | +0.132 |
Neg logit contributions | |
ls | -0.114 |
ves | -0.092 |
they | -0.090 |
their | -0.088 |
s | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
wheel | +0.038 |
sill | +0.037 |
hot | +0.035 |
uster | +0.035 |
Aid | +0.034 |
Neg logit contributions | |
ls | -0.045 |
cks | -0.041 |
vows | -0.041 |
ves | -0.038 |
nations | -0.037 |
Token | but |
Token ID | 475 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Aid | +0.033 |
sill | +0.033 |
wheel | +0.033 |
iddle | +0.033 |
Vest | +0.032 |
Neg logit contributions | |
ls | -0.071 |
cks | -0.063 |
vows | -0.063 |
ves | -0.062 |
they | -0.062 |
Token | he |
Token ID | 339 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
wheel | +0.036 |
sill | +0.035 |
uster | +0.035 |
aback | +0.033 |
inter | +0.032 |
Neg logit contributions | |
ls | -0.040 |
cks | -0.035 |
vows | -0.034 |
runs | -0.034 |
their | -0.034 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
wheel | +0.005 |
sill | +0.005 |
hot | +0.005 |
uster | +0.005 |
aback | +0.005 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.004 |
vows | -0.004 |
ves | -0.004 |
irs | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
cks | +0.002 |
ls | +0.002 |
irs | +0.002 |
vows | +0.002 |
nations | +0.002 |
Neg logit contributions | |
wheel | -0.001 |
sill | -0.001 |
hot | -0.001 |
aback | -0.001 |
icle | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ls | +0.020 |
vows | +0.018 |
cks | +0.018 |
ves | +0.016 |
irs | +0.016 |
Neg logit contributions | |
wheel | -0.021 |
sill | -0.020 |
hot | -0.019 |
uster | -0.019 |
aback | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
wheel | +0.027 |
hot | +0.026 |
uster | +0.025 |
sill | +0.025 |
bar | +0.024 |
Neg logit contributions | |
ls | -0.028 |
vows | -0.026 |
runs | -0.026 |
points | -0.024 |
nations | -0.024 |
Token | thank |
Token ID | 40716 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
wheel | +0.044 |
uster | +0.043 |
sill | +0.042 |
Vest | +0.042 |
vest | +0.042 |
Neg logit contributions | |
ls | -0.057 |
cks | -0.053 |
vows | -0.052 |
ves | -0.050 |
irs | -0.049 |
Token | you |
Token ID | 345 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
wheel | +0.016 |
sill | +0.015 |
uster | +0.015 |
vest | +0.015 |
bar | +0.015 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.006 |
vows | -0.006 |
ves | -0.005 |
nations | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
wheel | +0.029 |
sill | +0.028 |
Aid | +0.027 |
aback | +0.027 |
Vest | +0.027 |
Neg logit contributions | |
ls | -0.018 |
vows | -0.017 |
cks | -0.015 |
ves | -0.015 |
nations | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Vest | +0.138 |
uster | +0.138 |
Aid | +0.134 |
bar | +0.134 |
wheel | +0.134 |
Neg logit contributions | |
ls | -0.122 |
vows | -0.099 |
ves | -0.095 |
runs | -0.093 |
points | -0.093 |
Token | smiled |
Token ID | 13541 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
wheel | +0.017 |
sill | +0.017 |
hot | +0.015 |
aback | +0.015 |
cleaner | +0.015 |
Neg logit contributions | |
ls | -0.019 |
cks | -0.018 |
irs | -0.016 |
nations | -0.016 |
vows | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
wheel | +0.020 |
Aid | +0.018 |
uster | +0.018 |
bar | +0.018 |
hot | +0.018 |
Neg logit contributions | |
ls | -0.014 |
vows | -0.013 |
cks | -0.012 |
their | -0.012 |
points | -0.011 |
Token | Mama |
Token ID | 40084 |
Feature activation | -5.56e-03 |
Pos logit contributions | |
wheel | +0.009 |
sill | +0.009 |
hot | +0.008 |
uster | +0.008 |
aback | +0.008 |
Neg logit contributions | |
ls | -0.014 |
cks | -0.013 |
vows | -0.013 |
irs | -0.012 |
ves | -0.012 |
Token | p |
Token ID | 279 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.009 |
hot | +0.009 |
uster | +0.009 |
aback | +0.009 |
Neg logit contributions | |
ls | -0.010 |
cks | -0.009 |
vows | -0.008 |
irs | -0.008 |
ves | -0.008 |
Token | about |
Token ID | 546 |
Feature activation | +8.18e-03 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.007 |
hot | +0.006 |
aback | +0.006 |
cleaner | +0.006 |
Neg logit contributions | |
ls | -0.012 |
cks | -0.011 |
vows | -0.011 |
ves | -0.010 |
irs | -0.010 |
Token | who |
Token ID | 508 |
Feature activation | +9.39e-04 |
Pos logit contributions | |
ls | +0.018 |
cks | +0.017 |
vows | +0.016 |
ves | +0.016 |
irs | +0.015 |
Neg logit contributions | |
wheel | -0.010 |
sill | -0.010 |
operation | -0.010 |
3 | -0.009 |
happiest | -0.009 |
Token | has |
Token ID | 468 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ls | +0.002 |
vows | +0.002 |
cks | +0.002 |
irs | +0.001 |
ves | +0.001 |
Neg logit contributions | |
wheel | -0.001 |
sill | -0.001 |
aback | -0.001 |
hot | -0.001 |
operation | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
sill | +0.027 |
wheel | +0.026 |
aback | +0.025 |
cleaner | +0.024 |
hot | +0.023 |
Neg logit contributions | |
ls | -0.044 |
cks | -0.042 |
vows | -0.039 |
irs | -0.038 |
ves | -0.038 |
Token | sh |
Token ID | 427 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
wheel | +0.060 |
hot | +0.057 |
uster | +0.054 |
sill | +0.053 |
aback | +0.053 |
Neg logit contributions | |
ls | -0.068 |
vows | -0.064 |
nations | -0.062 |
cks | -0.060 |
cor | -0.060 |
Token | ini |
Token ID | 5362 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
hot | +0.026 |
wheel | +0.026 |
Vest | +0.025 |
aback | +0.024 |
vest | +0.024 |
Neg logit contributions | |
ls | -0.054 |
cks | -0.052 |
its | -0.050 |
ves | -0.049 |
irs | -0.045 |
Token | est |
Token ID | 395 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
wheel | +0.066 |
uster | +0.066 |
hot | +0.065 |
handy | +0.060 |
uit | +0.055 |
Neg logit contributions | |
ls | -0.173 |
vows | -0.167 |
runs | -0.165 |
cor | -0.164 |
points | -0.162 |
Token | gem |
Token ID | 16840 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.013 |
hot | +0.013 |
uster | +0.012 |
aback | +0.012 |
Neg logit contributions | |
ls | -0.015 |
cks | -0.014 |
vows | -0.014 |
ves | -0.013 |
irs | -0.013 |
Token | or |
Token ID | 393 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
wheel | +0.029 |
sill | +0.028 |
hot | +0.027 |
vest | +0.025 |
aback | +0.025 |
Neg logit contributions | |
ls | -0.036 |
cks | -0.034 |
vows | -0.033 |
irs | -0.032 |
ves | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
sill | +0.014 |
wheel | +0.013 |
vest | +0.013 |
happiest | +0.012 |
bar | +0.012 |
Neg logit contributions | |
ls | -0.021 |
cks | -0.019 |
vows | -0.018 |
ves | -0.018 |
irs | -0.018 |
Token | best |
Token ID | 1266 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
wheel | +0.028 |
sill | +0.026 |
hot | +0.026 |
uster | +0.025 |
aback | +0.025 |
Neg logit contributions | |
ls | -0.033 |
cks | -0.031 |
vows | -0.030 |
nations | -0.028 |
cor | -0.028 |
Token | really |
Token ID | 1107 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
icle | +0.003 |
uit | +0.003 |
bar | +0.003 |
Neg logit contributions | |
ls | -0.002 |
vows | -0.002 |
cks | -0.002 |
runs | -0.002 |
nations | -0.002 |
Token | understand |
Token ID | 1833 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ls | +0.025 |
cks | +0.023 |
vows | +0.023 |
irs | +0.021 |
ves | +0.021 |
Neg logit contributions | |
wheel | -0.018 |
sill | -0.018 |
hot | -0.017 |
uster | -0.016 |
aback | -0.016 |
Token | what |
Token ID | 644 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
wheel | +0.026 |
sill | +0.026 |
uster | +0.024 |
hot | +0.024 |
bar | +0.024 |
Neg logit contributions | |
ls | -0.024 |
cks | -0.022 |
vows | -0.021 |
ves | -0.020 |
nations | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
vows | +0.012 |
ves | +0.011 |
nations | +0.011 |
Neg logit contributions | |
sill | -0.012 |
wheel | -0.012 |
uster | -0.012 |
hot | -0.011 |
aback | -0.011 |
Token | value |
Token ID | 8367 |
Feature activation | -3.57e-03 |
Pos logit contributions | |
uster | +0.062 |
sill | +0.059 |
wheel | +0.059 |
Vest | +0.057 |
knee | +0.057 |
Neg logit contributions | |
ls | -0.080 |
cks | -0.072 |
its | -0.068 |
ves | -0.067 |
vows | -0.065 |
Token | " |
Token ID | 1 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
wheel | +0.006 |
hot | +0.006 |
sill | +0.006 |
uster | +0.006 |
icle | +0.006 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.006 |
vows | -0.005 |
irs | -0.005 |
nations | -0.005 |
Token | meant |
Token ID | 4001 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
uster | +0.144 |
Vest | +0.138 |
Aid | +0.136 |
initely | +0.132 |
knee | +0.131 |
Neg logit contributions | |
ls | -0.111 |
they | -0.089 |
their | -0.088 |
ves | -0.087 |
them | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
wheel | +0.051 |
sill | +0.050 |
Aid | +0.047 |
uster | +0.047 |
hot | +0.047 |
Neg logit contributions | |
ls | -0.053 |
cks | -0.048 |
vows | -0.046 |
ves | -0.044 |
points | -0.043 |
Token | but |
Token ID | 475 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
wheel | +0.034 |
aback | +0.033 |
Aid | +0.033 |
uster | +0.033 |
Vest | +0.033 |
Neg logit contributions | |
ls | -0.057 |
their | -0.054 |
they | -0.053 |
cor | -0.052 |
ves | -0.052 |
Token | he |
Token ID | 339 |
Feature activation | -4.01e-03 |
Pos logit contributions | |
uster | +0.039 |
wheel | +0.039 |
aback | +0.037 |
hot | +0.036 |
sill | +0.036 |
Neg logit contributions | |
ls | -0.034 |
their | -0.031 |
vows | -0.030 |
runs | -0.029 |
they | -0.029 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.007 |
hot | +0.007 |
uster | +0.007 |
aback | +0.007 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.006 |
vows | -0.006 |
ves | -0.005 |
ils | -0.005 |
Token | understanding |
Token ID | 4547 |
Feature activation | -7.91e-04 |
Pos logit contributions | |
wheel | +0.073 |
hot | +0.070 |
uster | +0.070 |
icle | +0.068 |
inter | +0.065 |
Neg logit contributions | |
ls | -0.080 |
cks | -0.076 |
vows | -0.073 |
points | -0.071 |
runs | -0.071 |
Token | now |
Token ID | 783 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
hot | +0.001 |
uster | +0.001 |
aback | +0.001 |
Neg logit contributions | |
ls | -0.002 |
cks | -0.001 |
vows | -0.001 |
irs | -0.001 |
ves | -0.001 |
Token | what |
Token ID | 644 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
wheel | +0.044 |
sill | +0.043 |
hot | +0.041 |
uster | +0.040 |
aback | +0.039 |
Neg logit contributions | |
ls | -0.057 |
cks | -0.052 |
vows | -0.051 |
irs | -0.048 |
ves | -0.047 |
Token | " |
Token ID | 366 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.014 |
vows | +0.013 |
irs | +0.012 |
ves | +0.012 |
Neg logit contributions | |
wheel | -0.015 |
sill | -0.015 |
hot | -0.014 |
aback | -0.014 |
vest | -0.014 |
Token | repeat |
Token ID | 44754 |
Feature activation | -4.50e-03 |
Pos logit contributions | |
wheel | +0.053 |
uster | +0.052 |
sill | +0.051 |
vest | +0.050 |
Vest | +0.050 |
Neg logit contributions | |
ls | -0.066 |
cks | -0.060 |
vows | -0.057 |
ves | -0.057 |
irs | -0.054 |
Token | " |
Token ID | 1 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.007 |
hot | +0.007 |
uster | +0.007 |
aback | +0.007 |
Neg logit contributions | |
ls | -0.008 |
cks | -0.007 |
vows | -0.007 |
irs | -0.007 |
ves | -0.007 |
Token | meant |
Token ID | 4001 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
uster | +0.129 |
Vest | +0.128 |
icle | +0.124 |
wheel | +0.124 |
Aid | +0.124 |
Neg logit contributions | |
ls | -0.124 |
vows | -0.099 |
ves | -0.097 |
runs | -0.097 |
points | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
wheel | +0.048 |
sill | +0.047 |
hot | +0.045 |
uster | +0.043 |
aback | +0.043 |
Neg logit contributions | |
ls | -0.061 |
cks | -0.056 |
vows | -0.054 |
irs | -0.051 |
ves | -0.051 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
wheel | +0.029 |
sill | +0.027 |
uster | +0.027 |
Vest | +0.026 |
vest | +0.026 |
Neg logit contributions | |
ls | -0.027 |
irs | -0.025 |
vows | -0.024 |
cks | -0.024 |
runs | -0.023 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
wheel | +0.051 |
sill | +0.050 |
hot | +0.047 |
uster | +0.047 |
bar | +0.046 |
Neg logit contributions | |
ls | -0.046 |
cks | -0.041 |
vows | -0.039 |
irs | -0.037 |
ves | -0.037 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
ls | +0.036 |
cks | +0.034 |
vows | +0.033 |
ves | +0.030 |
irs | +0.030 |
Neg logit contributions | |
wheel | -0.031 |
sill | -0.031 |
hot | -0.030 |
uster | -0.029 |
aback | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
hot | +0.001 |
aback | +0.001 |
uster | +0.001 |
Neg logit contributions | |
ls | -0.002 |
cks | -0.002 |
vows | -0.002 |
irs | -0.002 |
nations | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
wheel | +0.032 |
sill | +0.031 |
hot | +0.030 |
uster | +0.029 |
aback | +0.029 |
Neg logit contributions | |
ls | -0.040 |
vows | -0.037 |
cks | -0.036 |
ves | -0.034 |
irs | -0.033 |
Token | You |
Token ID | 1639 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
wheel | +0.036 |
knee | +0.034 |
inter | +0.033 |
vest | +0.033 |
operation | +0.033 |
Neg logit contributions | |
ls | -0.033 |
vows | -0.032 |
cks | -0.032 |
irs | -0.030 |
cor | -0.030 |
Token | 're |
Token ID | 821 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
ls | +0.006 |
vows | +0.006 |
cks | +0.005 |
nations | +0.005 |
irs | +0.005 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.007 |
hot | -0.007 |
uster | -0.007 |
icle | -0.007 |
Token | welcome |
Token ID | 7062 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
uster | +0.012 |
wheel | +0.011 |
inter | +0.011 |
Aid | +0.011 |
vest | +0.011 |
Neg logit contributions | |
cks | -0.013 |
their | -0.013 |
vows | -0.011 |
runs | -0.011 |
our | -0.011 |
Token | " |
Token ID | 1 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
ls | +0.017 |
vows | +0.015 |
cks | +0.014 |
cor | +0.014 |
runs | +0.014 |
Neg logit contributions | |
wheel | -0.021 |
sill | -0.019 |
bar | -0.019 |
hot | -0.019 |
Aid | -0.019 |
Token | before |
Token ID | 878 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
wheel | +0.125 |
sill | +0.116 |
vest | +0.116 |
icle | +0.115 |
knee | +0.115 |
Neg logit contributions | |
ls | -0.139 |
vows | -0.115 |
cks | -0.113 |
cor | -0.110 |
points | -0.109 |
Token | returning |
Token ID | 8024 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
ls | +0.020 |
vows | +0.020 |
ils | +0.019 |
cks | +0.019 |
nations | +0.019 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.015 |
hot | -0.014 |
handy | -0.014 |
uit | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -6.56e-04 |
Pos logit contributions | |
ls | +0.012 |
cks | +0.011 |
vows | +0.011 |
irs | +0.010 |
ves | +0.010 |
Neg logit contributions | |
wheel | -0.011 |
sill | -0.011 |
hot | -0.010 |
uster | -0.010 |
aback | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
hot | +0.001 |
uster | +0.001 |
aback | +0.001 |
Neg logit contributions | |
ls | -0.001 |
cks | -0.001 |
vows | -0.001 |
irs | -0.001 |
ves | -0.001 |
Token | stable |
Token ID | 8245 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
sill | +0.013 |
wheel | +0.013 |
hot | +0.012 |
vest | +0.012 |
aback | +0.011 |
Neg logit contributions | |
ls | -0.019 |
cks | -0.018 |
vows | -0.017 |
irs | -0.017 |
ves | -0.017 |
Token | for |
Token ID | 329 |
Feature activation | +5.47e-03 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.014 |
icle | +0.013 |
uster | +0.013 |
Aid | +0.013 |
Neg logit contributions | |
ls | -0.017 |
vows | -0.015 |
cks | -0.015 |
runs | -0.014 |
ils | -0.014 |
Token | explaining |
Token ID | 11170 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
ls | +0.009 |
cks | +0.009 |
vows | +0.008 |
irs | +0.008 |
nations | +0.008 |
Neg logit contributions | |
wheel | -0.009 |
sill | -0.009 |
uster | -0.009 |
hot | -0.009 |
aback | -0.008 |
Token | what |
Token ID | 644 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ls | +0.026 |
cks | +0.024 |
vows | +0.023 |
irs | +0.022 |
ves | +0.021 |
Neg logit contributions | |
wheel | -0.021 |
sill | -0.021 |
hot | -0.020 |
aback | -0.019 |
icle | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
ls | +0.035 |
cks | +0.035 |
irs | +0.031 |
vows | +0.031 |
its | +0.030 |
Neg logit contributions | |
wheel | -0.031 |
hot | -0.029 |
sill | -0.028 |
vest | -0.028 |
Vest | -0.027 |
Token | trade |
Token ID | 25351 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
sill | +0.062 |
uster | +0.060 |
knee | +0.058 |
wheel | +0.057 |
Vest | +0.056 |
Neg logit contributions | |
ls | -0.092 |
cks | -0.082 |
ves | -0.078 |
vows | -0.078 |
ils | -0.077 |
Token | " |
Token ID | 1 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
ls | +0.002 |
cks | +0.002 |
vows | +0.002 |
irs | +0.002 |
ves | +0.002 |
Neg logit contributions | |
wheel | -0.002 |
sill | -0.002 |
hot | -0.002 |
uster | -0.002 |
aback | -0.002 |
Token | meant |
Token ID | 4001 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
Vest | +0.132 |
uster | +0.131 |
bar | +0.130 |
knee | +0.128 |
Aid | +0.127 |
Neg logit contributions | |
ls | -0.111 |
ves | -0.092 |
runs | -0.088 |
they | -0.088 |
vows | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -9.24e-03 |
Pos logit contributions | |
wheel | +0.037 |
sill | +0.037 |
hot | +0.035 |
Aid | +0.034 |
uster | +0.034 |
Neg logit contributions | |
ls | -0.042 |
cks | -0.038 |
vows | -0.038 |
ves | -0.035 |
irs | -0.035 |
Token | From |
Token ID | 3574 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.014 |
hot | +0.013 |
uster | +0.013 |
aback | +0.013 |
Neg logit contributions | |
ls | -0.018 |
cks | -0.016 |
vows | -0.016 |
irs | -0.015 |
ves | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
wheel | +0.035 |
sill | +0.034 |
uster | +0.034 |
est | +0.033 |
inter | +0.033 |
Neg logit contributions | |
ls | -0.043 |
cks | -0.039 |
vows | -0.035 |
their | -0.035 |
nations | -0.034 |
Token | day |
Token ID | 1110 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
wheel | +0.054 |
sill | +0.051 |
uster | +0.050 |
hot | +0.048 |
aback | +0.048 |
Neg logit contributions | |
ls | -0.069 |
vows | -0.063 |
ves | -0.062 |
runs | -0.062 |
cks | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
wheel | +0.011 |
sill | +0.010 |
uster | +0.010 |
hot | +0.010 |
icle | +0.009 |
Neg logit contributions | |
ls | -0.014 |
cks | -0.013 |
vows | -0.012 |
points | -0.012 |
runs | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +6.75e-03 |
Pos logit contributions | |
wheel | +0.031 |
sill | +0.031 |
hot | +0.028 |
aback | +0.027 |
vest | +0.026 |
Neg logit contributions | |
ls | -0.045 |
cks | -0.043 |
irs | -0.040 |
vows | -0.040 |
nations | -0.039 |
Token | " |
Token ID | 366 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.013 |
vows | +0.012 |
irs | +0.012 |
nations | +0.012 |
Neg logit contributions | |
wheel | -0.009 |
sill | -0.009 |
hot | -0.009 |
aback | -0.008 |
icle | -0.008 |
Token | thank |
Token ID | 40716 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
uster | +0.047 |
wheel | +0.047 |
knee | +0.046 |
operation | +0.044 |
inter | +0.044 |
Neg logit contributions | |
ls | -0.062 |
vows | -0.058 |
cks | -0.058 |
ves | -0.054 |
cor | -0.054 |
Token | you |
Token ID | 345 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
uster | +0.003 |
vest | +0.003 |
bar | +0.003 |
Neg logit contributions | |
ls | -0.002 |
cks | -0.001 |
vows | -0.001 |
ils | -0.001 |
ves | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
wheel | +0.032 |
Aid | +0.031 |
sill | +0.031 |
aback | +0.030 |
Vest | +0.030 |
Neg logit contributions | |
ls | -0.019 |
vows | -0.019 |
cks | -0.016 |
ves | -0.016 |
nations | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
wheel | +0.132 |
uster | +0.132 |
Vest | +0.132 |
sill | +0.131 |
Aid | +0.130 |
Neg logit contributions | |
ls | -0.120 |
vows | -0.097 |
ves | -0.093 |
they | -0.091 |
their | -0.091 |
Token | its |
Token ID | 663 |
Feature activation | -7.29e-03 |
Pos logit contributions | |
ls | +0.005 |
cks | +0.005 |
vows | +0.004 |
irs | +0.004 |
runs | +0.004 |
Neg logit contributions | |
wheel | -0.005 |
sill | -0.005 |
hot | -0.005 |
uster | -0.005 |
aback | -0.004 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
wheel | +0.013 |
hot | +0.013 |
uster | +0.013 |
sill | +0.012 |
aback | +0.012 |
Neg logit contributions | |
ls | -0.012 |
vows | -0.011 |
cks | -0.010 |
nations | -0.010 |
runs | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.006 |
uster | +0.006 |
aback | +0.006 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.006 |
vows | -0.006 |
ves | -0.005 |
irs | -0.005 |
Token | The |
Token ID | 383 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
wheel | +0.004 |
sill | +0.004 |
hot | +0.004 |
uster | +0.004 |
aback | +0.004 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.004 |
vows | -0.004 |
irs | -0.004 |
ves | -0.004 |
Token | remembered |
Token ID | 12086 |
Feature activation | -3.53e-03 |
Pos logit contributions | |
wheel | +0.034 |
sill | +0.033 |
hot | +0.032 |
uster | +0.031 |
icle | +0.031 |
Neg logit contributions | |
ls | -0.030 |
cks | -0.027 |
vows | -0.026 |
irs | -0.024 |
ves | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
wheel | +0.005 |
sill | +0.005 |
hot | +0.005 |
aback | +0.005 |
icle | +0.005 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.007 |
vows | -0.006 |
ves | -0.006 |
irs | -0.006 |
Token | say |
Token ID | 910 |
Feature activation | -4.32e-03 |
Pos logit contributions | |
ls | +0.006 |
cks | +0.006 |
vows | +0.006 |
irs | +0.005 |
ves | +0.005 |
Neg logit contributions | |
wheel | -0.006 |
sill | -0.006 |
hot | -0.006 |
uster | -0.006 |
aback | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.007 |
hot | +0.007 |
uster | +0.006 |
aback | +0.006 |
Neg logit contributions | |
ls | -0.008 |
cks | -0.007 |
vows | -0.007 |
ves | -0.006 |
irs | -0.006 |
Token | please |
Token ID | 29688 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
sill | +0.075 |
knee | +0.073 |
wheel | +0.073 |
uster | +0.073 |
vest | +0.073 |
Neg logit contributions | |
ls | -0.105 |
cks | -0.096 |
vows | -0.091 |
irs | -0.091 |
ves | -0.090 |
Token | " |
Token ID | 1 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
ls | +0.023 |
cks | +0.020 |
vows | +0.020 |
irs | +0.018 |
ves | +0.018 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.024 |
hot | -0.023 |
uster | -0.022 |
icle | -0.022 |
Token | whenever |
Token ID | 8797 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Vest | +0.125 |
uster | +0.123 |
Aid | +0.122 |
bar | +0.121 |
vest | +0.118 |
Neg logit contributions | |
ls | -0.119 |
vows | -0.099 |
ves | -0.098 |
they | -0.094 |
runs | -0.093 |
Token | she |
Token ID | 673 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ls | +0.022 |
cks | +0.021 |
vows | +0.020 |
irs | +0.019 |
ves | +0.018 |
Neg logit contributions | |
wheel | -0.020 |
sill | -0.019 |
hot | -0.019 |
aback | -0.018 |
icle | -0.018 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
wheel | +0.021 |
sill | +0.020 |
hot | +0.020 |
aback | +0.019 |
uster | +0.019 |
Neg logit contributions | |
ls | -0.016 |
cks | -0.014 |
vows | -0.014 |
irs | -0.013 |
ves | -0.012 |
Token | something |
Token ID | 1223 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
wheel | +0.030 |
sill | +0.030 |
hot | +0.029 |
aback | +0.028 |
icle | +0.027 |
Neg logit contributions | |
ls | -0.037 |
cks | -0.034 |
vows | -0.032 |
irs | -0.031 |
ves | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.014 |
vows | +0.013 |
ves | +0.013 |
irs | +0.012 |
Neg logit contributions | |
wheel | -0.014 |
sill | -0.014 |
hot | -0.013 |
uster | -0.013 |
icle | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
wheel | +0.011 |
hot | +0.009 |
uster | +0.009 |
Aid | +0.009 |
icle | +0.009 |
Neg logit contributions | |
ls | -0.019 |
vows | -0.018 |
cks | -0.017 |
runs | -0.017 |
points | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
ls | +0.003 |
cks | +0.003 |
vows | +0.003 |
irs | +0.003 |
nations | +0.003 |
Neg logit contributions | |
wheel | -0.003 |
sill | -0.003 |
hot | -0.003 |
bar | -0.003 |
aback | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ls | +0.011 |
cks | +0.011 |
vows | +0.010 |
irs | +0.010 |
ves | +0.010 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.007 |
hot | -0.007 |
aback | -0.007 |
icle | -0.007 |
Token | thank |
Token ID | 40716 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
wheel | +0.035 |
sill | +0.034 |
uster | +0.033 |
knee | +0.033 |
vest | +0.033 |
Neg logit contributions | |
ls | -0.041 |
cks | -0.039 |
vows | -0.037 |
irs | -0.036 |
ves | -0.035 |
Token | you |
Token ID | 345 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ls | +0.002 |
cks | +0.002 |
vows | +0.002 |
nations | +0.001 |
ves | +0.001 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
uster | -0.004 |
icle | -0.004 |
hot | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
wheel | +0.026 |
sill | +0.025 |
Aid | +0.025 |
aback | +0.024 |
Vest | +0.024 |
Neg logit contributions | |
ls | -0.014 |
vows | -0.013 |
ves | -0.012 |
cks | -0.011 |
their | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
Vest | +0.128 |
uster | +0.127 |
Aid | +0.126 |
initely | +0.126 |
wheel | +0.126 |
Neg logit contributions | |
ls | -0.121 |
they | -0.094 |
vows | -0.093 |
ves | -0.093 |
runs | -0.091 |
Token | Tina |
Token ID | 35903 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
vows | +0.011 |
irs | +0.011 |
ves | +0.011 |
Neg logit contributions | |
wheel | -0.012 |
sill | -0.012 |
hot | -0.012 |
uster | -0.011 |
aback | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +4.42e-03 |
Pos logit contributions | |
wheel | +0.044 |
sill | +0.043 |
Aid | +0.042 |
hot | +0.042 |
icle | +0.041 |
Neg logit contributions | |
ls | -0.034 |
cks | -0.029 |
vows | -0.029 |
ves | -0.026 |
runs | -0.026 |
Token | told |
Token ID | 1297 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.007 |
vows | +0.006 |
irs | +0.006 |
ves | +0.006 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.008 |
hot | -0.008 |
uster | -0.007 |
aback | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
ls | +0.028 |
cks | +0.025 |
vows | +0.024 |
ves | +0.022 |
irs | +0.022 |
Neg logit contributions | |
wheel | -0.040 |
sill | -0.039 |
hot | -0.038 |
uster | -0.037 |
aback | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | -3.67e-03 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.009 |
hot | +0.009 |
uster | +0.009 |
cleaner | +0.008 |
Neg logit contributions | |
ls | -0.015 |
vows | -0.014 |
cks | -0.014 |
irs | -0.013 |
nations | -0.013 |
Token | even |
Token ID | 772 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.006 |
aback | +0.006 |
bar | +0.005 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.006 |
vows | -0.006 |
irs | -0.006 |
ves | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
wheel | +0.019 |
sill | +0.019 |
hot | +0.018 |
aback | +0.017 |
uster | +0.017 |
Neg logit contributions | |
ls | -0.019 |
cks | -0.018 |
vows | -0.017 |
irs | -0.016 |
ves | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.005 |
aback | +0.005 |
icle | +0.005 |
Neg logit contributions | |
ls | -0.009 |
cks | -0.008 |
vows | -0.008 |
irs | -0.008 |
nations | -0.007 |
Token | sorry |
Token ID | 41599 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
wheel | +0.042 |
sill | +0.041 |
uster | +0.040 |
knee | +0.040 |
vest | +0.039 |
Neg logit contributions | |
ls | -0.050 |
cks | -0.047 |
vows | -0.046 |
ves | -0.044 |
irs | -0.044 |
Token | " |
Token ID | 1 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
sill | +0.023 |
wheel | +0.023 |
uster | +0.022 |
bar | +0.022 |
Aid | +0.022 |
Neg logit contributions | |
ls | -0.015 |
vows | -0.014 |
ves | -0.013 |
cks | -0.013 |
nations | -0.012 |
Token | when |
Token ID | 618 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Vest | +0.123 |
Aid | +0.122 |
uster | +0.121 |
initely | +0.119 |
knee | +0.118 |
Neg logit contributions | |
ls | -0.114 |
ves | -0.096 |
vows | -0.092 |
they | -0.092 |
their | -0.091 |
Token | he |
Token ID | 339 |
Feature activation | +1.45e-04 |
Pos logit contributions | |
ls | +0.033 |
cks | +0.031 |
vows | +0.030 |
irs | +0.028 |
ils | +0.028 |
Neg logit contributions | |
wheel | -0.020 |
sill | -0.019 |
hot | -0.018 |
icle | -0.017 |
vest | -0.017 |
Token | didn |
Token ID | 1422 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
ls | +0.000 |
cks | +0.000 |
irs | +0.000 |
vows | +0.000 |
nations | +0.000 |
Neg logit contributions | |
wheel | -0.000 |
sill | -0.000 |
hot | -0.000 |
vest | -0.000 |
est | -0.000 |
Token | 't |
Token ID | 470 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.006 |
hot | +0.006 |
icle | +0.006 |
uster | +0.006 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.006 |
vows | -0.006 |
nations | -0.006 |
ils | -0.006 |
Token | mean |
Token ID | 1612 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
wheel | +0.020 |
sill | +0.019 |
hot | +0.018 |
aback | +0.017 |
icle | +0.017 |
Neg logit contributions | |
ls | -0.026 |
cks | -0.024 |
vows | -0.023 |
ves | -0.022 |
irs | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
wheel | +0.040 |
Aid | +0.040 |
uster | +0.039 |
aback | +0.039 |
sill | +0.039 |
Neg logit contributions | |
ls | -0.046 |
vows | -0.041 |
ves | -0.040 |
cks | -0.039 |
ils | -0.037 |
Token | put |
Token ID | 1234 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
wheel | +0.020 |
sill | +0.019 |
vest | +0.018 |
cleaner | +0.017 |
3 | +0.017 |
Neg logit contributions | |
cks | -0.023 |
ls | -0.023 |
irs | -0.020 |
its | -0.020 |
nations | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
wheel | +0.045 |
sill | +0.044 |
hot | +0.043 |
uster | +0.042 |
aback | +0.041 |
Neg logit contributions | |
ls | -0.033 |
cks | -0.029 |
vows | -0.028 |
irs | -0.025 |
ves | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.006 |
its | +0.006 |
nations | +0.006 |
vows | +0.006 |
Neg logit contributions | |
sill | -0.005 |
wheel | -0.005 |
vest | -0.005 |
hot | -0.005 |
Vest | -0.005 |
Token | sh |
Token ID | 427 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
wheel | +0.039 |
sill | +0.038 |
hot | +0.037 |
uster | +0.035 |
aback | +0.035 |
Neg logit contributions | |
ls | -0.047 |
cks | -0.043 |
vows | -0.042 |
ves | -0.040 |
irs | -0.039 |
Token | ini |
Token ID | 5362 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
hot | +0.041 |
wheel | +0.038 |
happiest | +0.036 |
Boy | +0.035 |
Doctor | +0.034 |
Neg logit contributions | |
cks | -0.057 |
ves | -0.054 |
vows | -0.052 |
its | -0.050 |
ls | -0.049 |
Token | est |
Token ID | 395 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
wheel | +0.105 |
hot | +0.098 |
sill | +0.092 |
hesitant | +0.090 |
uster | +0.090 |
Neg logit contributions | |
ls | -0.148 |
vows | -0.146 |
ves | -0.131 |
ils | -0.131 |
cks | -0.130 |
Token | shoes |
Token ID | 10012 |
Feature activation | -9.58e-03 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.014 |
hot | +0.013 |
vest | +0.013 |
uster | +0.013 |
Neg logit contributions | |
ls | -0.020 |
cks | -0.019 |
vows | -0.018 |
irs | -0.017 |
ves | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -6.52e-03 |
Pos logit contributions | |
wheel | +0.016 |
sill | +0.016 |
hot | +0.015 |
uster | +0.015 |
aback | +0.015 |
Neg logit contributions | |
ls | -0.017 |
cks | -0.015 |
vows | -0.015 |
ves | -0.014 |
irs | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.010 |
hot | +0.009 |
icle | +0.009 |
bar | +0.009 |
Neg logit contributions | |
ls | -0.012 |
vows | -0.011 |
cks | -0.011 |
irs | -0.010 |
runs | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.008 |
hot | +0.008 |
uster | +0.007 |
aback | +0.007 |
Neg logit contributions | |
ls | -0.013 |
cks | -0.012 |
vows | -0.012 |
nations | -0.011 |
irs | -0.011 |
Token | Mia |
Token ID | 32189 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
hot | +0.003 |
uster | +0.003 |
aback | +0.003 |
Neg logit contributions | |
ls | -0.003 |
cks | -0.003 |
vows | -0.003 |
irs | -0.003 |
ves | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
ls | +0.039 |
cks | +0.039 |
irs | +0.037 |
vows | +0.035 |
nations | +0.034 |
Neg logit contributions | |
wheel | -0.031 |
sill | -0.028 |
vest | -0.027 |
hot | -0.026 |
bar | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
cks | +0.012 |
ls | +0.012 |
irs | +0.011 |
nations | +0.010 |
vows | +0.010 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.006 |
hot | -0.006 |
est | -0.006 |
aback | -0.006 |
Token | thank |
Token ID | 40716 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
wheel | +0.035 |
aback | +0.033 |
uster | +0.033 |
sill | +0.033 |
knee | +0.032 |
Neg logit contributions | |
ls | -0.038 |
vows | -0.036 |
cks | -0.036 |
ves | -0.034 |
irs | -0.034 |
Token | you |
Token ID | 345 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ls | +0.004 |
cks | +0.003 |
vows | +0.002 |
runs | +0.002 |
ils | +0.002 |
Neg logit contributions | |
wheel | -0.008 |
uster | -0.008 |
sill | -0.008 |
inter | -0.008 |
icle | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
wheel | +0.021 |
aback | +0.021 |
Aid | +0.020 |
sill | +0.020 |
uster | +0.019 |
Neg logit contributions | |
ls | -0.013 |
vows | -0.013 |
ves | -0.011 |
their | -0.010 |
nations | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
uster | +0.145 |
bar | +0.141 |
Vest | +0.141 |
Aid | +0.138 |
initely | +0.137 |
Neg logit contributions | |
ls | -0.107 |
vows | -0.082 |
they | -0.081 |
runs | -0.081 |
ves | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.014 |
vows | +0.013 |
irs | +0.012 |
ves | +0.012 |
Neg logit contributions | |
wheel | -0.015 |
sill | -0.015 |
hot | -0.014 |
uster | -0.014 |
aback | -0.014 |
Token | fun |
Token ID | 1257 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
ls | +0.005 |
vows | +0.005 |
cks | +0.004 |
runs | +0.004 |
points | +0.004 |
Neg logit contributions | |
wheel | -0.005 |
sill | -0.004 |
hot | -0.004 |
uster | -0.004 |
bar | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.013 |
vows | +0.012 |
irs | +0.012 |
nations | +0.011 |
Neg logit contributions | |
wheel | -0.010 |
sill | -0.010 |
hot | -0.009 |
est | -0.009 |
vest | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
wheel | +0.020 |
sill | +0.019 |
hot | +0.019 |
uster | +0.018 |
aback | +0.018 |
Neg logit contributions | |
ls | -0.016 |
cks | -0.014 |
vows | -0.014 |
irs | -0.013 |
ves | -0.013 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
wheel | +0.017 |
sill | +0.017 |
hot | +0.016 |
aback | +0.016 |
bar | +0.016 |
Neg logit contributions | |
ls | -0.019 |
cks | -0.018 |
vows | -0.017 |
irs | -0.017 |
ves | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
wheel | +0.027 |
uster | +0.027 |
sill | +0.026 |
Vest | +0.026 |
hot | +0.025 |
Neg logit contributions | |
ls | -0.022 |
cks | -0.019 |
vows | -0.019 |
their | -0.018 |
nations | -0.018 |
Token | say |
Token ID | 910 |
Feature activation | -2.70e-03 |
Pos logit contributions | |
wheel | +0.018 |
sill | +0.018 |
hot | +0.016 |
aback | +0.016 |
icle | +0.016 |
Neg logit contributions | |
ls | -0.028 |
cks | -0.025 |
vows | -0.023 |
ves | -0.023 |
irs | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
wheel | +0.006 |
uster | +0.006 |
sill | +0.006 |
hot | +0.006 |
Aid | +0.006 |
Neg logit contributions | |
ls | -0.003 |
vows | -0.003 |
cks | -0.003 |
ves | -0.002 |
runs | -0.002 |
Token | hello |
Token ID | 31373 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
wheel | +0.062 |
uster | +0.062 |
knee | +0.060 |
sill | +0.060 |
Vest | +0.059 |
Neg logit contributions | |
ls | -0.075 |
vows | -0.067 |
runs | -0.066 |
cks | -0.066 |
cor | -0.064 |
Token | " |
Token ID | 1 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
ls | +0.020 |
cks | +0.017 |
vows | +0.016 |
runs | +0.015 |
nations | +0.015 |
Neg logit contributions | |
wheel | -0.031 |
sill | -0.031 |
Aid | -0.030 |
uster | -0.030 |
aback | -0.029 |
Token | too |
Token ID | 1165 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
Vest | +0.134 |
Aid | +0.133 |
uster | +0.132 |
initely | +0.127 |
operation | +0.126 |
Neg logit contributions | |
ls | -0.111 |
they | -0.089 |
runs | -0.088 |
points | -0.088 |
their | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
wheel | +0.031 |
sill | +0.030 |
hot | +0.029 |
uster | +0.028 |
aback | +0.028 |
Neg logit contributions | |
ls | -0.041 |
cks | -0.038 |
vows | -0.037 |
irs | -0.035 |
ves | -0.034 |
Token | so |
Token ID | 523 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Aid | +0.025 |
wheel | +0.024 |
Vest | +0.023 |
uster | +0.023 |
aback | +0.023 |
Neg logit contributions | |
ls | -0.042 |
runs | -0.039 |
cks | -0.039 |
their | -0.038 |
points | -0.038 |
Token | he |
Token ID | 339 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
ls | +0.025 |
cks | +0.023 |
vows | +0.022 |
irs | +0.021 |
ves | +0.021 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.015 |
hot | -0.014 |
uster | -0.014 |
aback | -0.014 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
cks | +0.011 |
ls | +0.011 |
irs | +0.010 |
nations | +0.009 |
vows | +0.009 |
Neg logit contributions | |
wheel | -0.012 |
sill | -0.012 |
hot | -0.011 |
3 | -0.011 |
bar | -0.011 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ls | +0.011 |
vows | +0.010 |
cks | +0.010 |
runs | +0.010 |
nations | +0.010 |
Neg logit contributions | |
wheel | -0.006 |
hot | -0.006 |
sill | -0.006 |
uster | -0.006 |
aback | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
ls | +0.031 |
vows | +0.027 |
cks | +0.026 |
ves | +0.025 |
runs | +0.024 |
Neg logit contributions | |
wheel | -0.038 |
sill | -0.037 |
uster | -0.037 |
hot | -0.037 |
icle | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
ls | +0.012 |
cks | +0.011 |
vows | +0.011 |
ves | +0.010 |
irs | +0.010 |
Neg logit contributions | |
wheel | -0.010 |
sill | -0.009 |
hot | -0.009 |
uster | -0.009 |
aback | -0.009 |
Token | thank |
Token ID | 40716 |
Feature activation | +9.89e-04 |
Pos logit contributions | |
uster | +0.030 |
wheel | +0.030 |
knee | +0.029 |
operation | +0.029 |
inter | +0.029 |
Neg logit contributions | |
ls | -0.040 |
cks | -0.038 |
vows | -0.037 |
ves | -0.035 |
irs | -0.035 |
Token | you |
Token ID | 345 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ls | +0.001 |
cks | +0.001 |
runs | +0.001 |
vows | +0.001 |
nations | +0.001 |
Neg logit contributions | |
uster | -0.002 |
wheel | -0.002 |
sill | -0.002 |
inter | -0.002 |
icle | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
wheel | +0.026 |
Aid | +0.026 |
aback | +0.026 |
sill | +0.025 |
Vest | +0.025 |
Neg logit contributions | |
ls | -0.014 |
vows | -0.014 |
their | -0.012 |
ves | -0.011 |
nations | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
initely | +0.144 |
uster | +0.144 |
Vest | +0.143 |
icle | +0.142 |
operation | +0.141 |
Neg logit contributions | |
ls | -0.105 |
they | -0.079 |
runs | -0.076 |
s | -0.076 |
their | -0.073 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.006 |
aback | +0.006 |
icle | +0.006 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.006 |
vows | -0.005 |
irs | -0.005 |
ves | -0.005 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
sill | +0.010 |
uster | +0.010 |
wheel | +0.010 |
icle | +0.010 |
hot | +0.010 |
Neg logit contributions | |
ls | -0.008 |
vows | -0.007 |
cks | -0.007 |
runs | -0.007 |
ves | -0.006 |
Token | good |
Token ID | 922 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
uster | +0.023 |
icle | +0.023 |
bar | +0.022 |
uit | +0.022 |
inter | +0.021 |
Neg logit contributions | |
ls | -0.024 |
their | -0.022 |
cks | -0.021 |
runs | -0.021 |
vows | -0.020 |
Token | for |
Token ID | 329 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
sill | +0.046 |
uster | +0.045 |
wheel | +0.045 |
aback | +0.045 |
bar | +0.045 |
Neg logit contributions | |
ls | -0.033 |
vows | -0.027 |
cks | -0.026 |
runs | -0.025 |
points | -0.024 |
Token | 't |
Token ID | 470 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.013 |
vows | +0.013 |
irs | +0.012 |
ves | +0.012 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
hot | -0.016 |
uster | -0.016 |
icle | -0.016 |
Token | know |
Token ID | 760 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
bar | +0.006 |
icle | +0.006 |
uster | +0.006 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.005 |
vows | -0.004 |
runs | -0.004 |
nations | -0.004 |
Token | what |
Token ID | 644 |
Feature activation | +8.47e-03 |
Pos logit contributions | |
ls | +0.005 |
cks | +0.005 |
vows | +0.005 |
ves | +0.004 |
irs | +0.004 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.006 |
hot | -0.006 |
uster | -0.006 |
aback | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
ls | +0.013 |
ves | +0.012 |
vows | +0.012 |
their | +0.011 |
cks | +0.011 |
Neg logit contributions | |
sill | -0.016 |
wheel | -0.015 |
uster | -0.015 |
aback | -0.015 |
est | -0.014 |
Token | sort |
Token ID | 30619 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
wheel | +0.046 |
sill | +0.045 |
uster | +0.044 |
hot | +0.042 |
aback | +0.042 |
Neg logit contributions | |
ls | -0.062 |
cks | -0.057 |
vows | -0.054 |
ves | -0.053 |
its | -0.051 |
Token | " |
Token ID | 1 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
ls | +0.003 |
cks | +0.003 |
vows | +0.002 |
irs | +0.002 |
ves | +0.002 |
Neg logit contributions | |
wheel | -0.003 |
sill | -0.003 |
hot | -0.003 |
uster | -0.003 |
icle | -0.003 |
Token | meant |
Token ID | 4001 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
uster | +0.134 |
Vest | +0.129 |
Aid | +0.129 |
wheel | +0.125 |
initely | +0.123 |
Neg logit contributions | |
ls | -0.115 |
ves | -0.091 |
vows | -0.091 |
points | -0.088 |
runs | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
wheel | +0.056 |
sill | +0.054 |
hot | +0.052 |
uster | +0.050 |
aback | +0.050 |
Neg logit contributions | |
ls | -0.061 |
cks | -0.056 |
vows | -0.054 |
irs | -0.051 |
ves | -0.051 |
Token | but |
Token ID | 475 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
wheel | +0.034 |
Aid | +0.033 |
aback | +0.031 |
sill | +0.031 |
Vest | +0.031 |
Neg logit contributions | |
ls | -0.066 |
vows | -0.061 |
cks | -0.060 |
their | -0.059 |
points | -0.059 |
Token | his |
Token ID | 465 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
wheel | +0.026 |
sill | +0.025 |
uster | +0.024 |
hot | +0.024 |
aback | +0.023 |
Neg logit contributions | |
ls | -0.034 |
cks | -0.031 |
vows | -0.030 |
ves | -0.028 |
runs | -0.028 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ls | +0.013 |
vows | +0.012 |
cks | +0.011 |
nations | +0.011 |
runs | +0.011 |
Neg logit contributions | |
wheel | -0.014 |
hot | -0.014 |
aback | -0.013 |
sill | -0.013 |
uster | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.013 |
vows | +0.012 |
ves | +0.012 |
irs | +0.012 |
Neg logit contributions | |
wheel | -0.010 |
sill | -0.010 |
hot | -0.010 |
uster | -0.009 |
icle | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
ls | +0.020 |
vows | +0.020 |
cks | +0.019 |
ils | +0.018 |
nations | +0.018 |
Neg logit contributions | |
wheel | -0.011 |
sill | -0.011 |
hot | -0.011 |
aback | -0.010 |
uster | -0.010 |
Token | L |
Token ID | 43 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
ls | +0.044 |
vows | +0.043 |
cks | +0.041 |
irs | +0.040 |
ils | +0.039 |
Neg logit contributions | |
wheel | -0.020 |
hot | -0.020 |
sill | -0.019 |
aback | -0.017 |
handy | -0.017 |
Token | ily |
Token ID | 813 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.007 |
hot | +0.007 |
uster | +0.007 |
icle | +0.006 |
Neg logit contributions | |
ls | -0.016 |
cks | -0.015 |
vows | -0.015 |
irs | -0.014 |
cor | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
ls | +0.038 |
cks | +0.037 |
irs | +0.036 |
vows | +0.036 |
ves | +0.035 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
aback | -0.016 |
hot | -0.015 |
vest | -0.014 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.007 |
vows | +0.006 |
ves | +0.006 |
irs | +0.006 |
Neg logit contributions | |
wheel | -0.006 |
sill | -0.006 |
hot | -0.006 |
aback | -0.005 |
icle | -0.005 |
Token | are |
Token ID | 389 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ls | +0.073 |
cks | +0.064 |
vows | +0.063 |
ves | +0.062 |
irs | +0.062 |
Neg logit contributions | |
wheel | -0.085 |
sill | -0.084 |
hot | -0.081 |
aback | -0.080 |
beam | -0.075 |
Token | scared |
Token ID | 12008 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
ls | +0.041 |
vows | +0.039 |
irs | +0.037 |
cks | +0.037 |
ves | +0.036 |
Neg logit contributions | |
sill | -0.023 |
wheel | -0.022 |
hot | -0.020 |
aback | -0.020 |
knee | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.006 |
vows | +0.006 |
ves | +0.006 |
irs | +0.006 |
Neg logit contributions | |
wheel | -0.006 |
sill | -0.006 |
hot | -0.006 |
uster | -0.005 |
aback | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
ls | +0.012 |
cks | +0.011 |
vows | +0.011 |
irs | +0.010 |
ves | +0.010 |
Neg logit contributions | |
sill | -0.017 |
hot | -0.016 |
wheel | -0.016 |
aback | -0.016 |
icle | -0.015 |
Token | drop |
Token ID | 4268 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ls | +0.069 |
cks | +0.063 |
irs | +0.062 |
ves | +0.062 |
vows | +0.061 |
Neg logit contributions | |
wheel | -0.045 |
hot | -0.042 |
sill | -0.041 |
aback | -0.040 |
beam | -0.039 |
Token | The |
Token ID | 464 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ls | +0.008 |
cks | +0.007 |
vows | +0.007 |
nations | +0.007 |
irs | +0.007 |
Neg logit contributions | |
hot | -0.004 |
wheel | -0.004 |
sill | -0.004 |
aback | -0.004 |
Aid | -0.004 |
Token | bird |
Token ID | 6512 |
Feature activation | +5.65e-03 |
Pos logit contributions | |
ls | +0.035 |
cks | +0.033 |
vows | +0.032 |
irs | +0.032 |
ils | +0.030 |
Neg logit contributions | |
sill | -0.012 |
wheel | -0.012 |
est | -0.010 |
vest | -0.010 |
icle | -0.010 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ls | +0.009 |
vows | +0.009 |
cks | +0.008 |
irs | +0.008 |
nations | +0.008 |
Neg logit contributions | |
wheel | -0.010 |
sill | -0.010 |
bar | -0.009 |
est | -0.009 |
hot | -0.009 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
wheel | +0.027 |
sill | +0.026 |
hot | +0.026 |
aback | +0.025 |
icle | +0.025 |
Neg logit contributions | |
ls | -0.045 |
cks | -0.044 |
vows | -0.042 |
irs | -0.039 |
nations | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
ls | +0.008 |
vows | +0.007 |
cks | +0.007 |
irs | +0.007 |
ves | +0.006 |
Neg logit contributions | |
wheel | -0.005 |
sill | -0.005 |
hot | -0.005 |
bar | -0.005 |
aback | -0.005 |
Token | ch |
Token ID | 442 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.013 |
hot | +0.013 |
bar | +0.012 |
aback | +0.012 |
Neg logit contributions | |
ls | -0.015 |
cks | -0.014 |
vows | -0.014 |
irs | -0.014 |
its | -0.013 |
Token | ir |
Token ID | 343 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
vows | +0.080 |
ls | +0.075 |
ves | +0.073 |
phones | +0.071 |
passports | +0.067 |
Neg logit contributions | |
aback | -0.065 |
uster | -0.064 |
sill | -0.064 |
wheel | -0.062 |
hot | -0.062 |
Token | ped |
Token ID | 9124 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
ls | +0.009 |
vows | +0.008 |
cks | +0.008 |
passports | +0.007 |
irs | +0.007 |
Neg logit contributions | |
wheel | -0.011 |
sill | -0.011 |
est | -0.010 |
bar | -0.010 |
hot | -0.010 |
Token | at |
Token ID | 379 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
ls | +0.041 |
cks | +0.039 |
vows | +0.037 |
irs | +0.037 |
ves | +0.036 |
Neg logit contributions | |
sill | -0.028 |
wheel | -0.028 |
hot | -0.027 |
aback | -0.026 |
est | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
vows | +0.012 |
ves | +0.011 |
nations | +0.011 |
Neg logit contributions | |
sill | -0.011 |
hot | -0.011 |
wheel | -0.011 |
aback | -0.011 |
icle | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -8.87e-03 |
Pos logit contributions | |
ls | +0.011 |
cks | +0.010 |
vows | +0.010 |
irs | +0.009 |
ves | +0.009 |
Neg logit contributions | |
wheel | -0.011 |
sill | -0.011 |
hot | -0.010 |
uster | -0.010 |
aback | -0.010 |
Token | did |
Token ID | 750 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
ls | +0.026 |
cks | +0.025 |
vows | +0.023 |
irs | +0.023 |
ves | +0.021 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.024 |
hot | -0.023 |
vest | -0.023 |
bar | -0.022 |
Token | something |
Token ID | 1223 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ls | +0.032 |
cks | +0.029 |
vows | +0.029 |
irs | +0.028 |
nations | +0.027 |
Neg logit contributions | |
wheel | -0.024 |
sill | -0.022 |
vest | -0.020 |
knee | -0.020 |
hot | -0.020 |
Token | very |
Token ID | 845 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
ls | +0.051 |
cks | +0.043 |
ves | +0.042 |
vows | +0.042 |
points | +0.040 |
Neg logit contributions | |
sill | -0.054 |
uster | -0.053 |
hot | -0.051 |
wheel | -0.051 |
bar | -0.050 |
Token | special |
Token ID | 2041 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
ls | +0.039 |
cks | +0.036 |
vows | +0.035 |
irs | +0.033 |
ves | +0.033 |
Neg logit contributions | |
wheel | -0.031 |
sill | -0.030 |
hot | -0.029 |
uster | -0.028 |
aback | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
wheel | +0.033 |
sill | +0.033 |
uster | +0.033 |
hot | +0.032 |
aback | +0.032 |
Neg logit contributions | |
ls | -0.029 |
cks | -0.026 |
vows | -0.025 |
ves | -0.024 |
ils | -0.024 |
Token | everyone |
Token ID | 2506 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
wheel | +0.005 |
sill | +0.005 |
hot | +0.005 |
aback | +0.005 |
uster | +0.005 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.005 |
vows | -0.005 |
irs | -0.005 |
ves | -0.005 |
Token | started |
Token ID | 2067 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ls | +0.082 |
cks | +0.082 |
irs | +0.078 |
vows | +0.076 |
ves | +0.073 |
Neg logit contributions | |
wheel | -0.075 |
hot | -0.068 |
sill | -0.068 |
boat | -0.066 |
expert | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
ls | +0.045 |
vows | +0.041 |
cks | +0.041 |
ves | +0.039 |
irs | +0.039 |
Neg logit contributions | |
sill | -0.024 |
wheel | -0.024 |
3 | -0.021 |
bar | -0.021 |
vest | -0.020 |
Token | applaud |
Token ID | 22517 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
ls | +0.020 |
cks | +0.018 |
vows | +0.018 |
irs | +0.017 |
ves | +0.016 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
hot | -0.017 |
uster | -0.016 |
aback | -0.016 |
Token | him |
Token ID | 683 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ls | +0.075 |
cks | +0.068 |
vows | +0.066 |
irs | +0.062 |
ves | +0.062 |
Neg logit contributions | |
wheel | -0.065 |
sill | -0.064 |
hot | -0.062 |
icle | -0.059 |
uster | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
ls | +0.037 |
cks | +0.034 |
vows | +0.033 |
irs | +0.031 |
ves | +0.031 |
Neg logit contributions | |
wheel | -0.035 |
sill | -0.034 |
hot | -0.033 |
uster | -0.031 |
icle | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
ls | +0.012 |
vows | +0.011 |
cks | +0.011 |
ils | +0.011 |
nations | +0.011 |
Neg logit contributions | |
sill | -0.006 |
wheel | -0.006 |
hot | -0.006 |
aback | -0.006 |
icle | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
ls | +0.016 |
vows | +0.015 |
cks | +0.015 |
ils | +0.015 |
nations | +0.014 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.007 |
hot | -0.007 |
aback | -0.006 |
handy | -0.006 |
Token | S |
Token ID | 50 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
vows | +0.028 |
ls | +0.027 |
cks | +0.026 |
irs | +0.026 |
ils | +0.026 |
Neg logit contributions | |
hot | -0.018 |
wheel | -0.017 |
sill | -0.016 |
handy | -0.015 |
bar | -0.015 |
Token | ara |
Token ID | 3301 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
ls | +0.031 |
cks | +0.031 |
vows | +0.030 |
irs | +0.028 |
nations | +0.028 |
Neg logit contributions | |
wheel | -0.027 |
sill | -0.026 |
uit | -0.026 |
hot | -0.025 |
icle | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
vows | +0.044 |
ls | +0.044 |
irs | +0.044 |
cks | +0.043 |
ves | +0.041 |
Neg logit contributions | |
wheel | -0.018 |
sill | -0.018 |
aback | -0.016 |
hot | -0.015 |
knee | -0.014 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
ls | +0.012 |
cks | +0.011 |
vows | +0.011 |
ves | +0.010 |
irs | +0.010 |
Neg logit contributions | |
wheel | -0.009 |
sill | -0.009 |
hot | -0.008 |
icle | -0.008 |
vest | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
ls | +0.084 |
irs | +0.077 |
ves | +0.076 |
vows | +0.076 |
cks | +0.075 |
Neg logit contributions | |
wheel | -0.077 |
sill | -0.074 |
hot | -0.073 |
aback | -0.073 |
beam | -0.070 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
ls | +0.022 |
vows | +0.021 |
irs | +0.020 |
cks | +0.019 |
ves | +0.019 |
Neg logit contributions | |
sill | -0.011 |
wheel | -0.011 |
hot | -0.010 |
knee | -0.009 |
aback | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
ls | +0.005 |
vows | +0.005 |
cks | +0.005 |
ves | +0.005 |
irs | +0.005 |
Neg logit contributions | |
sill | -0.004 |
wheel | -0.004 |
hot | -0.004 |
uster | -0.003 |
aback | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
irs | +0.012 |
ils | +0.011 |
vows | +0.011 |
Neg logit contributions | |
sill | -0.015 |
hot | -0.014 |
aback | -0.014 |
icle | -0.014 |
inter | -0.013 |
Token | do |
Token ID | 466 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
ls | +0.065 |
irs | +0.061 |
vows | +0.061 |
ves | +0.060 |
cks | +0.058 |
Neg logit contributions | |
wheel | -0.045 |
hot | -0.042 |
sill | -0.042 |
aback | -0.040 |
beam | -0.040 |
Token | m |
Token ID | 285 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
sill | +0.005 |
wheel | +0.005 |
hot | +0.004 |
bar | +0.004 |
vest | +0.004 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.005 |
vows | -0.005 |
irs | -0.004 |
ves | -0.004 |
Token | ak |
Token ID | 461 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
ls | +0.080 |
cks | +0.071 |
vows | +0.070 |
nations | +0.068 |
runs | +0.066 |
Neg logit contributions | |
wheel | -0.057 |
bar | -0.055 |
sill | -0.055 |
icle | -0.053 |
uster | -0.053 |
Token | r |
Token ID | 81 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
hot | +0.003 |
bar | +0.003 |
aback | +0.002 |
Neg logit contributions | |
ls | -0.004 |
cks | -0.003 |
vows | -0.003 |
irs | -0.003 |
nations | -0.003 |
Token | ut |
Token ID | 315 |
Feature activation | -7.07e-03 |
Pos logit contributions | |
ls | +0.088 |
cks | +0.078 |
nations | +0.075 |
vows | +0.074 |
passports | +0.072 |
Neg logit contributions | |
sill | -0.090 |
wheel | -0.089 |
bar | -0.087 |
icle | -0.085 |
est | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | -5.77e-04 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.010 |
hot | +0.010 |
bar | +0.010 |
uster | +0.009 |
Neg logit contributions | |
ls | -0.014 |
cks | -0.013 |
vows | -0.013 |
nations | -0.012 |
ves | -0.012 |
Token | pand |
Token ID | 19798 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
sill | +0.001 |
wheel | +0.001 |
bar | +0.001 |
hot | +0.001 |
vest | +0.001 |
Neg logit contributions | |
ls | -0.001 |
cks | -0.001 |
irs | -0.001 |
vows | -0.001 |
nations | -0.001 |
Token | an |
Token ID | 272 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ls | +0.079 |
vows | +0.070 |
cks | +0.068 |
runs | +0.065 |
points | +0.062 |
Neg logit contributions | |
wheel | -0.105 |
sill | -0.100 |
uster | -0.098 |
bar | -0.095 |
hot | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | +8.86e-03 |
Pos logit contributions | |
ls | +0.028 |
cks | +0.026 |
vows | +0.024 |
irs | +0.024 |
nations | +0.023 |
Neg logit contributions | |
wheel | -0.023 |
sill | -0.023 |
hot | -0.022 |
bar | -0.022 |
est | -0.021 |
Token | curry |
Token ID | 34611 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ls | +0.016 |
cks | +0.015 |
irs | +0.014 |
vows | +0.013 |
ves | +0.013 |
Neg logit contributions | |
sill | -0.015 |
wheel | -0.014 |
bar | -0.014 |
hot | -0.013 |
vest | -0.013 |
Token | leaf |
Token ID | 12835 |
Feature activation | +6.02e-03 |
Pos logit contributions | |
ls | +0.051 |
cks | +0.050 |
irs | +0.046 |
vows | +0.045 |
nations | +0.045 |
Neg logit contributions | |
wheel | -0.038 |
sill | -0.037 |
hot | -0.036 |
est | -0.033 |
icle | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
ls | +0.011 |
cks | +0.011 |
vows | +0.010 |
irs | +0.010 |
nations | +0.010 |
Neg logit contributions | |
wheel | -0.009 |
sill | -0.009 |
hot | -0.009 |
bar | -0.009 |
icle | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.007 |
vest | +0.007 |
my | +0.007 |
hot | +0.007 |
Neg logit contributions | |
ls | -0.009 |
cks | -0.009 |
vows | -0.009 |
irs | -0.008 |
ves | -0.008 |
Token | Rod |
Token ID | 6882 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.013 |
vows | +0.013 |
runs | +0.012 |
ves | +0.012 |
Neg logit contributions | |
wheel | -0.010 |
sill | -0.010 |
uster | -0.009 |
hot | -0.009 |
aback | -0.009 |
Token | went |
Token ID | 1816 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
cks | +0.071 |
ls | +0.069 |
irs | +0.065 |
vows | +0.061 |
pulp | +0.056 |
Neg logit contributions | |
wheel | -0.096 |
hot | -0.093 |
sill | -0.091 |
aback | -0.088 |
est | -0.087 |
Token | to |
Token ID | 284 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
ls | +0.004 |
cks | +0.004 |
vows | +0.004 |
irs | +0.003 |
ves | +0.003 |
Neg logit contributions | |
wheel | -0.003 |
sill | -0.003 |
hot | -0.003 |
aback | -0.003 |
uster | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
ls | +0.008 |
cks | +0.007 |
vows | +0.007 |
irs | +0.007 |
ves | +0.007 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.007 |
hot | -0.006 |
uster | -0.006 |
aback | -0.006 |
Token | park |
Token ID | 3952 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
wheel | +0.011 |
sill | +0.011 |
hot | +0.010 |
uster | +0.010 |
aback | +0.010 |
Neg logit contributions | |
ls | -0.012 |
cks | -0.011 |
vows | -0.011 |
nations | -0.010 |
irs | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
ls | +0.032 |
cks | +0.029 |
vows | +0.028 |
ves | +0.026 |
nations | +0.026 |
Neg logit contributions | |
wheel | -0.033 |
sill | -0.032 |
uster | -0.031 |
hot | -0.031 |
icle | -0.030 |
Token | They |
Token ID | 1119 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ls | +0.010 |
cks | +0.009 |
vows | +0.009 |
runs | +0.008 |
nations | +0.008 |
Neg logit contributions | |
wheel | -0.015 |
sill | -0.015 |
uster | -0.014 |
hot | -0.014 |
Aid | -0.014 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
ls | +0.037 |
cks | +0.036 |
vows | +0.034 |
irs | +0.033 |
its | +0.032 |
Neg logit contributions | |
wheel | -0.030 |
hot | -0.029 |
sill | -0.028 |
vest | -0.027 |
Vest | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.008 |
hot | +0.008 |
uster | +0.007 |
aback | +0.007 |
Neg logit contributions | |
ls | -0.010 |
cks | -0.009 |
vows | -0.009 |
irs | -0.008 |
ves | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | -6.86e-03 |
Pos logit contributions | |
ls | +0.053 |
vows | +0.046 |
cks | +0.046 |
ves | +0.043 |
nations | +0.042 |
Neg logit contributions | |
wheel | -0.058 |
sill | -0.058 |
hot | -0.055 |
aback | -0.054 |
uster | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
wheel | +0.033 |
sill | +0.032 |
uster | +0.032 |
aback | +0.031 |
est | +0.031 |
Neg logit contributions | |
ls | -0.034 |
cks | -0.031 |
their | -0.030 |
cor | -0.029 |
runs | -0.029 |
Token | little |
Token ID | 1310 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
ls | +0.041 |
vows | +0.037 |
cor | +0.034 |
cks | +0.034 |
runs | +0.034 |
Neg logit contributions | |
wheel | -0.046 |
sill | -0.044 |
hot | -0.043 |
aback | -0.043 |
uster | -0.043 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.52e-04 |
Pos logit contributions | |
ls | +0.004 |
runs | +0.004 |
cor | +0.004 |
nations | +0.004 |
vows | +0.004 |
Neg logit contributions | |
wheel | -0.004 |
uit | -0.003 |
uster | -0.003 |
hot | -0.003 |
sill | -0.003 |
Token | named |
Token ID | 3706 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ls | +0.002 |
cks | +0.001 |
vows | +0.001 |
irs | +0.001 |
ves | +0.001 |
Neg logit contributions | |
sill | -0.001 |
wheel | -0.001 |
hot | -0.001 |
est | -0.001 |
aback | -0.001 |
Token | Sue |
Token ID | 26089 |
Feature activation | -7.73e-04 |
Pos logit contributions | |
wheel | +0.015 |
sill | +0.015 |
hot | +0.015 |
aback | +0.013 |
uster | +0.013 |
Neg logit contributions | |
ls | -0.033 |
cks | -0.032 |
vows | -0.031 |
ves | -0.029 |
its | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
sill | +0.001 |
wheel | +0.001 |
hot | +0.001 |
my | +0.001 |
aback | +0.001 |
Neg logit contributions | |
ls | -0.002 |
vows | -0.001 |
cks | -0.001 |
irs | -0.001 |
ves | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
ls | +0.011 |
cks | +0.010 |
vows | +0.010 |
irs | +0.009 |
ves | +0.009 |
Neg logit contributions | |
wheel | -0.008 |
sill | -0.008 |
hot | -0.008 |
icle | -0.007 |
uster | -0.007 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ls | +0.043 |
cks | +0.040 |
irs | +0.036 |
ves | +0.035 |
its | +0.035 |
Neg logit contributions | |
hot | -0.033 |
wheel | -0.033 |
sill | -0.033 |
my | -0.030 |
happiest | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ls | +0.042 |
cks | +0.041 |
its | +0.038 |
ves | +0.038 |
vows | +0.038 |
Neg logit contributions | |
sill | -0.016 |
wheel | -0.015 |
3 | -0.015 |
hot | -0.015 |
operation | -0.015 |
Token | play |
Token ID | 711 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
ls | +0.029 |
cks | +0.026 |
irs | +0.024 |
vows | +0.024 |
ves | +0.024 |
Neg logit contributions | |
sill | -0.016 |
wheel | -0.015 |
vest | -0.014 |
icle | -0.013 |
hot | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
sill | +0.003 |
wheel | +0.003 |
uster | +0.003 |
bar | +0.003 |
icle | +0.003 |
Neg logit contributions | |
ls | -0.003 |
cks | -0.003 |
ves | -0.003 |
vows | -0.003 |
ils | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.010 |
hot | +0.009 |
aback | +0.008 |
bar | +0.008 |
Neg logit contributions | |
ls | -0.021 |
vows | -0.019 |
cks | -0.019 |
ves | -0.018 |
irs | -0.018 |
Token | touch |
Token ID | 3638 |
Feature activation | -9.69e-04 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.005 |
icle | +0.005 |
bar | +0.005 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.006 |
vows | -0.006 |
ves | -0.006 |
irs | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
wheel | +0.002 |
sill | +0.002 |
hot | +0.002 |
uster | +0.002 |
aback | +0.002 |
Neg logit contributions | |
ls | -0.002 |
cks | -0.001 |
vows | -0.001 |
irs | -0.001 |
ves | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
wheel | +0.049 |
uster | +0.048 |
sill | +0.048 |
Aid | +0.047 |
Vest | +0.047 |
Neg logit contributions | |
ls | -0.041 |
cks | -0.035 |
vows | -0.032 |
ves | -0.031 |
irs | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-03 |
Pos logit contributions | |
sill | +0.003 |
wheel | +0.003 |
hot | +0.003 |
aback | +0.003 |
icle | +0.003 |
Neg logit contributions | |
ls | -0.007 |
cks | -0.006 |
vows | -0.006 |
ils | -0.006 |
ves | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +9.31e-03 |
Pos logit contributions | |
wheel | +0.002 |
sill | +0.002 |
hot | +0.002 |
aback | +0.002 |
uster | +0.002 |
Neg logit contributions | |
ls | -0.004 |
vows | -0.003 |
cks | -0.003 |
ils | -0.003 |
nations | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
ls | +0.018 |
vows | +0.016 |
cks | +0.016 |
cor | +0.015 |
irs | +0.015 |
Neg logit contributions | |
wheel | -0.015 |
hot | -0.015 |
sill | -0.014 |
handy | -0.013 |
aback | -0.013 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.008 |
hot | +0.008 |
icle | +0.007 |
uster | +0.007 |
Neg logit contributions | |
ls | -0.012 |
cks | -0.011 |
vows | -0.011 |
irs | -0.010 |
ves | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
wheel | +0.032 |
uster | +0.031 |
sill | +0.031 |
hot | +0.030 |
Aid | +0.030 |
Neg logit contributions | |
ls | -0.029 |
cks | -0.027 |
runs | -0.025 |
vows | -0.025 |
points | -0.024 |
Token | no |
Token ID | 645 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ls | +0.022 |
cks | +0.020 |
vows | +0.020 |
ves | +0.018 |
nations | +0.018 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.024 |
hot | -0.023 |
uster | -0.023 |
aback | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
wheel | +0.027 |
sill | +0.026 |
hot | +0.025 |
uster | +0.024 |
icle | +0.024 |
Neg logit contributions | |
ls | -0.035 |
cks | -0.032 |
vows | -0.031 |
irs | -0.030 |
ves | -0.029 |
Token | dog |
Token ID | 3290 |
Feature activation | +3.78e-04 |
Pos logit contributions | |
wheel | +0.021 |
sill | +0.021 |
hot | +0.020 |
aback | +0.019 |
uster | +0.019 |
Neg logit contributions | |
ls | -0.023 |
cks | -0.022 |
vows | -0.021 |
irs | -0.020 |
ves | -0.020 |
Token | for |
Token ID | 329 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
ls | +0.001 |
cks | +0.001 |
vows | +0.001 |
irs | +0.001 |
ves | +0.001 |
Neg logit contributions | |
wheel | -0.001 |
sill | -0.001 |
hot | -0.000 |
uster | -0.000 |
aback | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
hot | +0.003 |
icle | +0.003 |
aback | +0.003 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.005 |
vows | -0.005 |
nations | -0.005 |
ves | -0.004 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
wheel | +0.006 |
sill | +0.006 |
hot | +0.005 |
uster | +0.005 |
aback | +0.005 |
Neg logit contributions | |
ls | -0.006 |
cks | -0.006 |
vows | -0.005 |
irs | -0.005 |
ves | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-05 |
Pos logit contributions | |
wheel | +0.034 |
Aid | +0.034 |
Vest | +0.032 |
sill | +0.032 |
uster | +0.031 |
Neg logit contributions | |
ls | -0.024 |
cks | -0.019 |
vows | -0.019 |
their | -0.019 |
ves | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
wheel | +0.000 |
sill | +0.000 |
est | +0.000 |
hot | +0.000 |
uster | +0.000 |
Neg logit contributions | |
ls | -0.000 |
cks | -0.000 |
vows | -0.000 |
irs | -0.000 |
ves | -0.000 |
Token | also |
Token ID | 635 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.012 |
vows | +0.011 |
irs | +0.011 |
ves | +0.011 |
Neg logit contributions | |
wheel | -0.013 |
sill | -0.013 |
hot | -0.012 |
aback | -0.012 |
bar | -0.012 |
Token | played |
Token ID | 2826 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ls | +0.002 |
cks | +0.002 |
vows | +0.002 |
irs | +0.002 |
ves | +0.002 |
Neg logit contributions | |
wheel | -0.002 |
sill | -0.002 |
hot | -0.002 |
aback | -0.002 |
bar | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
uster | +0.024 |
Aid | +0.024 |
sill | +0.023 |
bar | +0.023 |
inter | +0.023 |
Neg logit contributions | |
ls | -0.020 |
ves | -0.019 |
them | -0.018 |
their | -0.018 |
cks | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | -5.06e-03 |
Pos logit contributions | |
ls | +0.002 |
cks | +0.002 |
vows | +0.002 |
irs | +0.002 |
ves | +0.002 |
Neg logit contributions | |
wheel | -0.003 |
hot | -0.002 |
sill | -0.002 |
uster | -0.002 |
Aid | -0.002 |
Token | bedroom |
Token ID | 14043 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.008 |
hot | +0.007 |
uster | +0.007 |
aback | +0.007 |
Neg logit contributions | |
ls | -0.010 |
cks | -0.009 |
vows | -0.009 |
ves | -0.008 |
nations | -0.008 |
Token | It |
Token ID | 632 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
sill | +0.014 |
wheel | +0.013 |
iddle | +0.013 |
est | +0.013 |
icle | +0.012 |
Neg logit contributions | |
ls | -0.017 |
vows | -0.015 |
runs | -0.014 |
irs | -0.014 |
points | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
wheel | +0.008 |
sill | +0.008 |
hot | +0.008 |
bar | +0.008 |
est | +0.007 |
Neg logit contributions | |
ls | -0.010 |
cks | -0.009 |
vows | -0.009 |
irs | -0.009 |
nations | -0.009 |
Token | huge |
Token ID | 3236 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.003 |
hot | +0.002 |
uster | +0.002 |
aback | +0.002 |
Neg logit contributions | |
ls | -0.004 |
cks | -0.004 |
vows | -0.004 |
irs | -0.004 |
ves | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
wheel | +0.030 |
sill | +0.028 |
hot | +0.028 |
uster | +0.027 |
icle | +0.027 |
Neg logit contributions | |
ls | -0.039 |
cks | -0.035 |
vows | -0.034 |
points | -0.032 |
runs | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
wheel | +0.055 |
sill | +0.054 |
uster | +0.053 |
hot | +0.052 |
icle | +0.051 |
Neg logit contributions | |
ls | -0.067 |
cks | -0.060 |
vows | -0.058 |
points | -0.055 |
ves | -0.055 |
Token | Red |
Token ID | 2297 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.014 |
uster | +0.013 |
icle | +0.013 |
hot | +0.013 |
Neg logit contributions | |
ls | -0.014 |
cks | -0.013 |
vows | -0.012 |
ves | -0.012 |
irs | -0.011 |
Token | could |
Token ID | 714 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
ls | +0.023 |
cks | +0.021 |
vows | +0.020 |
irs | +0.020 |
nations | +0.019 |
Neg logit contributions | |
wheel | -0.022 |
sill | -0.021 |
hot | -0.021 |
bar | -0.020 |
aback | -0.020 |
Token | tell |
Token ID | 1560 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ls | +0.054 |
cks | +0.049 |
vows | +0.047 |
irs | +0.044 |
ves | +0.044 |
Neg logit contributions | |
wheel | -0.060 |
sill | -0.058 |
hot | -0.057 |
uster | -0.055 |
aback | -0.055 |
Token | it |
Token ID | 340 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
ls | +0.039 |
cks | +0.036 |
vows | +0.034 |
ves | +0.033 |
irs | +0.033 |
Neg logit contributions | |
wheel | -0.028 |
sill | -0.027 |
hot | -0.026 |
aback | -0.026 |
icle | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
wheel | +0.011 |
sill | +0.011 |
est | +0.010 |
hot | +0.010 |
aback | +0.009 |
Neg logit contributions | |
ls | -0.020 |
cks | -0.019 |
vows | -0.018 |
irs | -0.018 |
pulp | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.010 |
hot | +0.009 |
aback | +0.009 |
icle | +0.009 |
Neg logit contributions | |
ls | -0.016 |
cks | -0.014 |
vows | -0.014 |
irs | -0.013 |
ves | -0.013 |
Token | buy |
Token ID | 2822 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
ls | +0.014 |
cks | +0.013 |
vows | +0.013 |
irs | +0.012 |
runs | +0.012 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.015 |
uster | -0.015 |
hot | -0.014 |
bar | -0.014 |
Token | some |
Token ID | 617 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
ls | +0.010 |
cks | +0.009 |
vows | +0.009 |
irs | +0.008 |
nations | +0.008 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.007 |
hot | -0.006 |
icle | -0.006 |
aback | -0.006 |
Token | candy |
Token ID | 18550 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ls | +0.004 |
cks | +0.004 |
vows | +0.004 |
irs | +0.004 |
ves | +0.004 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
hot | -0.004 |
vest | -0.004 |
icle | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +6.06e-03 |
Pos logit contributions | |
ls | +0.026 |
cks | +0.024 |
vows | +0.023 |
irs | +0.022 |
nations | +0.021 |
Neg logit contributions | |
wheel | -0.023 |
sill | -0.022 |
hot | -0.022 |
icle | -0.020 |
uster | -0.020 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.11e-03 |
Pos logit contributions | |
ls | +0.012 |
cks | +0.011 |
vows | +0.011 |
irs | +0.010 |
ves | +0.010 |
Neg logit contributions | |
wheel | -0.009 |
sill | -0.009 |
hot | -0.008 |
uster | -0.008 |
aback | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.014 |
vows | +0.013 |
irs | +0.013 |
nations | +0.012 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.016 |
hot | -0.015 |
aback | -0.015 |
bar | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
wheel | +0.021 |
sill | +0.020 |
hot | +0.019 |
uster | +0.019 |
aback | +0.019 |
Neg logit contributions | |
ls | -0.026 |
cks | -0.024 |
vows | -0.023 |
ves | -0.022 |
irs | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ls | +0.041 |
vows | +0.036 |
cor | +0.032 |
ves | +0.032 |
cks | +0.032 |
Neg logit contributions | |
sill | -0.045 |
wheel | -0.045 |
hot | -0.043 |
aback | -0.043 |
uster | -0.043 |
Token | red |
Token ID | 2266 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
wheel | +0.020 |
sill | +0.020 |
uster | +0.019 |
aback | +0.019 |
hot | +0.018 |
Neg logit contributions | |
ls | -0.020 |
vows | -0.017 |
runs | -0.017 |
points | -0.016 |
cor | -0.016 |
Token | l |
Token ID | 300 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.014 |
aback | +0.013 |
uster | +0.013 |
hot | +0.013 |
Neg logit contributions | |
ls | -0.016 |
vows | -0.015 |
runs | -0.014 |
cor | -0.013 |
ves | -0.013 |
Token | oll |
Token ID | 692 |
Feature activation | -4.24e-03 |
Pos logit contributions | |
ls | +0.004 |
ves | +0.004 |
cks | +0.004 |
ils | +0.004 |
vows | +0.004 |
Neg logit contributions | |
aback | -0.002 |
sill | -0.002 |
handy | -0.002 |
cleaner | -0.002 |
icle | -0.002 |
Token | blanket |
Token ID | 18447 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
ls | +0.019 |
cks | +0.018 |
vows | +0.017 |
irs | +0.017 |
ves | +0.016 |
Neg logit contributions | |
wheel | -0.014 |
sill | -0.014 |
vest | -0.013 |
hot | -0.012 |
icle | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.006 |
vows | +0.006 |
ves | +0.005 |
runs | +0.005 |
Neg logit contributions | |
wheel | -0.005 |
sill | -0.005 |
uster | -0.005 |
Aid | -0.005 |
hot | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ls | +0.005 |
cks | +0.005 |
irs | +0.004 |
vows | +0.004 |
nations | +0.004 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
vest | -0.004 |
hot | -0.004 |
cleaner | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
ls | +0.030 |
cks | +0.028 |
irs | +0.028 |
vows | +0.027 |
nations | +0.027 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.024 |
hot | -0.023 |
knee | -0.022 |
vest | -0.022 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ls | +0.006 |
vows | +0.005 |
cks | +0.005 |
ves | +0.005 |
nations | +0.005 |
Neg logit contributions | |
wheel | -0.005 |
sill | -0.005 |
hot | -0.005 |
aback | -0.005 |
uster | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
ls | +0.032 |
cks | +0.031 |
vows | +0.029 |
irs | +0.029 |
nations | +0.028 |
Neg logit contributions | |
wheel | -0.034 |
sill | -0.033 |
hot | -0.030 |
vest | -0.030 |
est | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
wheel | +0.001 |
sill | +0.001 |
hot | +0.001 |
uster | +0.001 |
aback | +0.001 |
Neg logit contributions | |
ls | -0.003 |
cks | -0.003 |
vows | -0.002 |
irs | -0.002 |
ves | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -4.49e-04 |
Pos logit contributions | |
cks | +0.023 |
irs | +0.023 |
ls | +0.023 |
nations | +0.022 |
vows | +0.021 |
Neg logit contributions | |
wheel | -0.014 |
vest | -0.013 |
knee | -0.012 |
sill | -0.012 |
beam | -0.012 |
Token | upset |
Token ID | 9247 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
wheel | +0.001 |
hot | +0.001 |
uster | +0.001 |
sill | +0.001 |
icle | +0.001 |
Neg logit contributions | |
ls | -0.001 |
cks | -0.001 |
vows | -0.001 |
runs | -0.001 |
ves | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
wheel | +0.016 |
sill | +0.016 |
Vest | +0.015 |
bar | +0.015 |
uster | +0.015 |
Neg logit contributions | |
ls | -0.023 |
cks | -0.019 |
their | -0.018 |
runs | -0.018 |
points | -0.018 |
Token | started |
Token ID | 2067 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
wheel | +0.017 |
sill | +0.016 |
knee | +0.015 |
hot | +0.015 |
vest | +0.015 |
Neg logit contributions | |
ls | -0.022 |
irs | -0.022 |
cks | -0.022 |
vows | -0.022 |
nations | -0.020 |
Token | away |
Token ID | 1497 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
wheel | +0.075 |
ivering | +0.069 |
stump | +0.068 |
ooting | +0.068 |
uster | +0.067 |
Neg logit contributions | |
ls | -0.039 |
their | -0.039 |
them | -0.037 |
cks | -0.032 |
turns | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ls | +0.007 |
their | +0.007 |
vows | +0.007 |
cor | +0.006 |
cks | +0.006 |
Neg logit contributions | |
wheel | -0.011 |
uster | -0.010 |
sill | -0.010 |
hot | -0.010 |
bar | -0.010 |
Token | cubes |
Token ID | 34896 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
wheel | +0.030 |
hot | +0.030 |
uster | +0.029 |
sill | +0.027 |
aback | +0.026 |
Neg logit contributions | |
ls | -0.053 |
vows | -0.048 |
cks | -0.048 |
points | -0.046 |
nations | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
Labrador | +0.031 |
wheel | +0.030 |
Aid | +0.030 |
initely | +0.030 |
Whe | +0.030 |
Neg logit contributions | |
ls | -0.029 |
they | -0.022 |
their | -0.022 |
packs | -0.022 |
cks | -0.021 |
Token | went |
Token ID | 1816 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
wheel | +0.013 |
sill | +0.013 |
vest | +0.012 |
hot | +0.012 |
bar | +0.012 |
Neg logit contributions | |
ls | -0.013 |
cks | -0.013 |
vows | -0.012 |
irs | -0.011 |
nations | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +9.33e-04 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.010 |
hot | +0.009 |
uster | +0.009 |
aback | +0.009 |
Neg logit contributions | |
ls | -0.016 |
cks | -0.014 |
vows | -0.014 |
irs | -0.013 |
ves | -0.013 |
Token | bed |
Token ID | 3996 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
ls | +0.002 |
cks | +0.002 |
vows | +0.002 |
ves | +0.002 |
nations | +0.002 |
Neg logit contributions | |
wheel | -0.001 |
sill | -0.001 |
vest | -0.001 |
hot | -0.001 |
aback | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +4.26e-03 |
Pos logit contributions | |
ls | +0.017 |
vows | +0.015 |
cks | +0.015 |
ves | +0.015 |
irs | +0.014 |
Neg logit contributions | |
wheel | -0.012 |
sill | -0.012 |
hot | -0.012 |
icle | -0.011 |
uster | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | -2.76e-03 |
Pos logit contributions | |
ls | +0.007 |
their | +0.006 |
vows | +0.006 |
cks | +0.006 |
irs | +0.005 |
Neg logit contributions | |
wheel | -0.008 |
uster | -0.008 |
bar | -0.007 |
hot | -0.007 |
inter | -0.007 |
Token | favorite |
Token ID | 4004 |
Feature activation | +9.91e-04 |
Pos logit contributions | |
wheel | +0.004 |
sill | +0.004 |
hot | +0.004 |
uster | +0.004 |
aback | +0.004 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.005 |
vows | -0.005 |
nations | -0.004 |
irs | -0.004 |
Token | cube |
Token ID | 23441 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
ls | +0.002 |
vows | +0.002 |
cks | +0.002 |
nations | +0.002 |
points | +0.002 |
Neg logit contributions | |
wheel | -0.002 |
sill | -0.001 |
hot | -0.001 |
uster | -0.001 |
aback | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
wheel | +0.008 |
Aid | +0.008 |
icle | +0.008 |
hot | +0.008 |
uster | +0.008 |
Neg logit contributions | |
ls | -0.006 |
vows | -0.005 |
cks | -0.005 |
ves | -0.005 |
their | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
wheel | +0.012 |
sill | +0.012 |
hot | +0.011 |
uster | +0.011 |
bar | +0.011 |
Neg logit contributions | |
ls | -0.019 |
cks | -0.018 |
vows | -0.017 |
irs | -0.016 |
ves | -0.016 |
Token | One |
Token ID | 3198 |
Feature activation | -8.47e-03 |
Pos logit contributions | |
wheel | +0.042 |
sill | +0.041 |
hot | +0.039 |
uster | +0.039 |
bar | +0.038 |
Neg logit contributions | |
ls | -0.037 |
cks | -0.033 |
vows | -0.031 |
irs | -0.030 |
ves | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
uster | +0.013 |
wheel | +0.013 |
hot | +0.013 |
aback | +0.012 |
uit | +0.012 |
Neg logit contributions | |
ls | -0.016 |
runs | -0.014 |
cks | -0.014 |
their | -0.014 |
vows | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
cks | +0.031 |
vows | +0.030 |
nations | +0.029 |
ils | +0.029 |
ls | +0.029 |
Neg logit contributions | |
hot | -0.008 |
wheel | -0.008 |
icle | -0.008 |
aback | -0.007 |
bar | -0.007 |
Token | there |
Token ID | 612 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
wheel | +0.005 |
sill | +0.005 |
hot | +0.005 |
uster | +0.004 |
aback | +0.004 |
Neg logit contributions | |
ls | -0.008 |
cks | -0.007 |
vows | -0.007 |
irs | -0.007 |
ves | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ls | +0.003 |
cks | +0.002 |
vows | +0.002 |
irs | +0.002 |
nations | +0.002 |
Neg logit contributions | |
wheel | -0.002 |
sill | -0.002 |
hot | -0.002 |
icle | -0.002 |
aback | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
wheel | +0.024 |
uster | +0.023 |
sill | +0.022 |
aback | +0.022 |
bar | +0.022 |
Neg logit contributions | |
ls | -0.020 |
their | -0.019 |
cks | -0.018 |
cor | -0.017 |
vows | -0.017 |
Token | little |
Token ID | 1310 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
ls | +0.013 |
vows | +0.011 |
cor | +0.011 |
runs | +0.010 |
nations | +0.010 |
Neg logit contributions | |
aback | -0.018 |
wheel | -0.018 |
sill | -0.018 |
bar | -0.017 |
icle | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
wheel | +0.012 |
sill | +0.011 |
uit | +0.011 |
aback | +0.011 |
iddle | +0.010 |
Neg logit contributions | |
ls | -0.011 |
runs | -0.009 |
cor | -0.009 |
floats | -0.009 |
their | -0.009 |
Token | named |
Token ID | 3706 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
wheel | +0.023 |
sill | +0.023 |
hot | +0.022 |
uster | +0.021 |
aback | +0.021 |
Neg logit contributions | |
ls | -0.031 |
cks | -0.028 |
vows | -0.027 |
ves | -0.026 |
irs | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
ls | +0.032 |
cks | +0.029 |
vows | +0.029 |
irs | +0.027 |
nations | +0.026 |
Neg logit contributions | |
wheel | -0.026 |
sill | -0.025 |
hot | -0.024 |
aback | -0.023 |
vest | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
wheel | +0.010 |
sill | +0.010 |
hot | +0.009 |
uster | +0.009 |
icle | +0.009 |
Neg logit contributions | |
ls | -0.012 |
cks | -0.011 |
vows | -0.010 |
ves | -0.010 |
irs | -0.010 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
ls | +0.004 |
cks | +0.004 |
ves | +0.003 |
vows | +0.003 |
irs | +0.003 |
Neg logit contributions | |
sill | -0.005 |
wheel | -0.005 |
uster | -0.004 |
aback | -0.004 |
icle | -0.004 |
Token | â |
Token ID | 22940 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
ls | +0.003 |
cks | +0.003 |
vows | +0.002 |
irs | +0.002 |
ves | +0.002 |
Neg logit contributions | |
wheel | -0.003 |
sill | -0.003 |
hot | -0.003 |
uster | -0.003 |
aback | -0.003 |
Token | € |
Token ID | 26391 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
uster | +0.028 |
vest | +0.027 |
sill | +0.026 |
brand | +0.026 |
3 | +0.026 |
Neg logit contributions | |
cks | -0.049 |
runs | -0.046 |
ils | -0.045 |
vows | -0.045 |
ls | -0.044 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
ls | +0.029 |
cks | +0.026 |
vows | +0.026 |
irs | +0.024 |
nations | +0.024 |
Neg logit contributions | |
wheel | -0.027 |
sill | -0.026 |
hot | -0.025 |
uster | -0.024 |
aback | -0.024 |
Token | s |
Token ID | 82 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
wheel | +0.009 |
sill | +0.009 |
Aid | +0.008 |
hot | +0.008 |
uster | +0.008 |
Neg logit contributions | |
ls | -0.012 |
cks | -0.010 |
vows | -0.010 |
ves | -0.010 |
irs | -0.010 |
Token | mum |
Token ID | 25682 |
Feature activation | +2.31e-04 |
Pos logit contributions | |
ls | +0.033 |
cks | +0.030 |
vows | +0.029 |
irs | +0.027 |
ves | +0.027 |
Neg logit contributions | |
wheel | -0.026 |
sill | -0.025 |
hot | -0.024 |
uster | -0.023 |
aback | -0.023 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
ls | +0.000 |
cks | +0.000 |
vows | +0.000 |
irs | +0.000 |
ves | +0.000 |
Neg logit contributions | |
wheel | -0.000 |
sill | -0.000 |
hot | -0.000 |
aback | -0.000 |
uster | -0.000 |
Token | him |
Token ID | 683 |
Feature activation | +8.68e-03 |
Pos logit contributions | |
ls | +0.003 |
cks | +0.003 |
vows | +0.003 |
irs | +0.003 |
ves | +0.003 |
Neg logit contributions | |
wheel | -0.003 |
sill | -0.003 |
hot | -0.003 |
uster | -0.003 |
aback | -0.003 |
Token | complaining |
Token ID | 18705 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
ls | +0.016 |
cks | +0.014 |
vows | +0.014 |
irs | +0.013 |
ves | +0.013 |
Neg logit contributions | |
wheel | -0.014 |
sill | -0.014 |
hot | -0.013 |
uster | -0.013 |
aback | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | +6.73e-04 |
Pos logit contributions | |
sill | +0.003 |
wheel | +0.003 |
hot | +0.003 |
est | +0.003 |
icle | +0.003 |
Neg logit contributions | |
ls | -0.004 |
cks | -0.004 |
vows | -0.003 |
irs | -0.003 |
ves | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
ls | +0.001 |
cks | +0.001 |
vows | +0.001 |
irs | +0.001 |
ves | +0.001 |
Neg logit contributions | |
wheel | -0.001 |
sill | -0.001 |
hot | -0.001 |
uster | -0.001 |
aback | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +7.70e-03 |
Pos logit contributions | |
ls | +0.002 |
cks | +0.002 |
vows | +0.002 |
irs | +0.002 |
nations | +0.002 |
Neg logit contributions | |
wheel | -0.002 |
sill | -0.002 |
hot | -0.001 |
uster | -0.001 |
aback | -0.001 |
Token | Anna |
Token ID | 31160 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.014 |
vows | +0.014 |
irs | +0.013 |
nations | +0.012 |
Neg logit contributions | |
sill | -0.012 |
wheel | -0.011 |
hot | -0.011 |
uster | -0.010 |
vest | -0.010 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ls | +0.030 |
cks | +0.028 |
vows | +0.026 |
irs | +0.026 |
ves | +0.025 |
Neg logit contributions | |
wheel | -0.027 |
sill | -0.026 |
hot | -0.025 |
aback | -0.024 |
vest | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
wheel | +0.024 |
bar | +0.022 |
icle | +0.022 |
uster | +0.022 |
roach | +0.021 |
Neg logit contributions | |
ls | -0.017 |
points | -0.014 |
their | -0.014 |
runs | -0.013 |
cks | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
wheel | +0.071 |
sill | +0.069 |
hot | +0.067 |
aback | +0.065 |
uster | +0.064 |
Neg logit contributions | |
ls | -0.064 |
cks | -0.058 |
vows | -0.056 |
irs | -0.053 |
ves | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.007 |
vows | +0.007 |
irs | +0.006 |
nations | +0.006 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
hot | -0.004 |
aback | -0.004 |
icle | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
wheel | +0.038 |
sill | +0.037 |
hot | +0.035 |
uster | +0.035 |
aback | +0.034 |
Neg logit contributions | |
ls | -0.056 |
cks | -0.051 |
vows | -0.050 |
ves | -0.047 |
irs | -0.047 |
Token | I |
Token ID | 40 |
Feature activation | +2.43e-03 |
Pos logit contributions | |
uster | +0.019 |
wheel | +0.019 |
operation | +0.019 |
icle | +0.018 |
bar | +0.018 |
Neg logit contributions | |
ls | -0.026 |
cks | -0.025 |
vows | -0.025 |
points | -0.024 |
runs | -0.023 |
Token | 'm |
Token ID | 1101 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
ls | +0.004 |
cks | +0.004 |
vows | +0.004 |
ves | +0.004 |
irs | +0.004 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
hot | -0.004 |
uster | -0.004 |
icle | -0.004 |
Token | silly |
Token ID | 14397 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
ls | +0.029 |
cks | +0.026 |
vows | +0.026 |
ves | +0.024 |
irs | +0.024 |
Neg logit contributions | |
wheel | -0.025 |
sill | -0.025 |
hot | -0.024 |
uster | -0.023 |
aback | -0.023 |
Token | idea |
Token ID | 2126 |
Feature activation | -7.98e-03 |
Pos logit contributions | |
ls | +0.008 |
cks | +0.007 |
vows | +0.007 |
ves | +0.006 |
nations | +0.006 |
Neg logit contributions | |
wheel | -0.006 |
sill | -0.006 |
hot | -0.006 |
uster | -0.005 |
aback | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e-03 |
Pos logit contributions | |
wheel | +0.012 |
sill | +0.012 |
hot | +0.012 |
icle | +0.011 |
bar | +0.011 |
Neg logit contributions | |
ls | -0.016 |
cks | -0.014 |
vows | -0.014 |
irs | -0.013 |
nations | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.002 |
uster | +0.002 |
Aid | +0.002 |
hot | +0.002 |
Neg logit contributions | |
ls | -0.005 |
cks | -0.004 |
vows | -0.004 |
irs | -0.004 |
runs | -0.004 |
Token | thought |
Token ID | 1807 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
ls | +0.016 |
cks | +0.016 |
irs | +0.015 |
vows | +0.014 |
nations | +0.013 |
Neg logit contributions | |
wheel | -0.016 |
sill | -0.015 |
bar | -0.015 |
hot | -0.015 |
vest | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
ls | +0.015 |
cks | +0.014 |
vows | +0.013 |
irs | +0.012 |
nations | +0.012 |
Neg logit contributions | |
wheel | -0.013 |
sill | -0.013 |
hot | -0.012 |
uster | -0.012 |
icle | -0.012 |
Token | would |
Token ID | 561 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
wheel | +0.086 |
sill | +0.085 |
uster | +0.084 |
hot | +0.082 |
icle | +0.080 |
Neg logit contributions | |
ls | -0.066 |
cks | -0.058 |
vows | -0.057 |
ves | -0.053 |
runs | -0.051 |
Token | be |
Token ID | 307 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
ls | +0.040 |
cks | +0.036 |
vows | +0.035 |
irs | +0.033 |
ves | +0.033 |
Neg logit contributions | |
wheel | -0.038 |
sill | -0.037 |
hot | -0.035 |
uster | -0.034 |
aback | -0.034 |
Token | fun |
Token ID | 1257 |
Feature activation | -9.59e-03 |
Pos logit contributions | |
wheel | +0.013 |
sill | +0.013 |
hot | +0.012 |
aback | +0.012 |
uster | +0.012 |
Neg logit contributions | |
ls | -0.018 |
cks | -0.017 |
vows | -0.016 |
ves | -0.015 |
irs | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.014 |
hot | +0.013 |
aback | +0.013 |
uster | +0.012 |
Neg logit contributions | |
ls | -0.019 |
cks | -0.018 |
vows | -0.017 |
irs | -0.016 |
ves | -0.016 |
Token | come |
Token ID | 1282 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ls | +0.024 |
cks | +0.021 |
vows | +0.020 |
irs | +0.019 |
nations | +0.019 |
Neg logit contributions | |
wheel | -0.017 |
sill | -0.017 |
bar | -0.015 |
icle | -0.015 |
vest | -0.015 |
Token | apple |
Token ID | 17180 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
wheel | +0.016 |
uster | +0.016 |
hot | +0.015 |
sill | +0.015 |
uit | +0.014 |
Neg logit contributions | |
ls | -0.021 |
cks | -0.019 |
vows | -0.019 |
points | -0.018 |
runs | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
wheel | +0.021 |
sill | +0.020 |
uster | +0.019 |
hot | +0.019 |
aback | +0.019 |
Neg logit contributions | |
ls | -0.025 |
cks | -0.023 |
vows | -0.022 |
ves | -0.021 |
nations | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ls | +0.020 |
cks | +0.018 |
vows | +0.017 |
irs | +0.016 |
ves | +0.016 |
Neg logit contributions | |
sill | -0.024 |
wheel | -0.024 |
hot | -0.023 |
aback | -0.022 |
icle | -0.022 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
wheel | +0.017 |
sill | +0.017 |
hot | +0.016 |
vest | +0.015 |
icle | +0.015 |
Neg logit contributions | |
ls | -0.018 |
cks | -0.017 |
vows | -0.016 |
irs | -0.016 |
nations | -0.016 |
Token | juicy |
Token ID | 35075 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
ls | +0.028 |
cks | +0.026 |
vows | +0.025 |
irs | +0.024 |
ves | +0.024 |
Neg logit contributions | |
wheel | -0.019 |
sill | -0.018 |
hot | -0.017 |
uster | -0.017 |
icle | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
wheel | +0.035 |
uster | +0.032 |
sill | +0.032 |
Aid | +0.031 |
bar | +0.030 |
Neg logit contributions | |
ls | -0.040 |
cks | -0.035 |
vows | -0.033 |
points | -0.032 |
runs | -0.032 |
Token | sweet |
Token ID | 6029 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
wheel | +0.064 |
sill | +0.063 |
hot | +0.060 |
vest | +0.056 |
aback | +0.056 |
Neg logit contributions | |
ls | -0.092 |
cks | -0.086 |
vows | -0.085 |
irs | -0.082 |
nations | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
sill | +0.018 |
wheel | +0.018 |
hot | +0.017 |
est | +0.017 |
icle | +0.016 |
Neg logit contributions | |
ls | -0.021 |
cks | -0.020 |
vows | -0.019 |
irs | -0.019 |
ves | -0.018 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
ls | +0.017 |
cks | +0.016 |
vows | +0.015 |
irs | +0.014 |
ils | +0.014 |
Neg logit contributions | |
sill | -0.020 |
wheel | -0.020 |
hot | -0.020 |
aback | -0.019 |
uster | -0.019 |
Token | said |
Token ID | 531 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
ls | +0.009 |
cks | +0.008 |
vows | +0.008 |
irs | +0.008 |
nations | +0.008 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.006 |
hot | -0.006 |
aback | -0.006 |
vest | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ls | +0.007 |
cks | +0.007 |
irs | +0.007 |
vows | +0.007 |
nations | +0.006 |
Neg logit contributions | |
wheel | -0.004 |
sill | -0.004 |
hot | -0.004 |
aback | -0.004 |
icle | -0.004 |
Token | L |
Token ID | 43 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
ls | +0.010 |
cks | +0.010 |
vows | +0.009 |
irs | +0.009 |
cor | +0.009 |
Neg logit contributions | |
wheel | -0.007 |
sill | -0.006 |
hot | -0.006 |
uster | -0.006 |
vest | -0.006 |
Token | ily |
Token ID | 813 |
Feature activation | -1.22e-03 |
Pos logit contributions | |
wheel | +0.011 |
sill | +0.011 |
hot | +0.011 |
uster | +0.010 |
bar | +0.010 |
Neg logit contributions | |
ls | -0.017 |
cks | -0.016 |
vows | -0.015 |
irs | -0.015 |
ves | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
wheel | +0.002 |
sill | +0.002 |
hot | +0.002 |
uster | +0.002 |
icle | +0.002 |
Neg logit contributions | |
ls | -0.002 |
vows | -0.002 |
cks | -0.002 |
ves | -0.002 |
runs | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
uster | +0.018 |
hot | +0.017 |
inter | +0.017 |
icle | +0.017 |
wheel | +0.017 |
Neg logit contributions | |
cks | -0.017 |
ls | -0.017 |
vows | -0.016 |
their | -0.015 |
runs | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
uster | +0.003 |
wheel | +0.003 |
bar | +0.003 |
hot | +0.003 |
sill | +0.003 |
Neg logit contributions | |
ls | -0.003 |
vows | -0.002 |
cks | -0.002 |
their | -0.002 |
they | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
wheel | +0.077 |
sill | +0.075 |
hot | +0.073 |
uster | +0.072 |
icle | +0.071 |
Neg logit contributions | |
ls | -0.061 |
cks | -0.054 |
vows | -0.052 |
irs | -0.048 |
ves | -0.048 |
Token | used |
Token ID | 973 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
sill | +0.080 |
icle | +0.077 |
wheel | +0.076 |
uster | +0.075 |
bar | +0.074 |
Neg logit contributions | |
ls | -0.059 |
vows | -0.050 |
cks | -0.049 |
runs | -0.047 |
ils | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
wheel | +0.029 |
sill | +0.029 |
hot | +0.028 |
uster | +0.027 |
aback | +0.027 |
Neg logit contributions | |
ls | -0.022 |
cks | -0.020 |
vows | -0.019 |
irs | -0.017 |
ves | -0.017 |
Token | words |
Token ID | 2456 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
wheel | +0.031 |
sill | +0.030 |
hot | +0.029 |
uster | +0.028 |
icle | +0.028 |
Neg logit contributions | |
ls | -0.036 |
cks | -0.033 |
vows | -0.032 |
ves | -0.030 |
nations | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
wheel | +0.014 |
sill | +0.014 |
uster | +0.014 |
Vest | +0.014 |
Aid | +0.014 |
Neg logit contributions | |
ls | -0.013 |
vows | -0.011 |
cks | -0.011 |
their | -0.011 |
ves | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
wheel | +0.029 |
sill | +0.027 |
hot | +0.025 |
cleaner | +0.025 |
vest | +0.025 |
Neg logit contributions | |
ls | -0.029 |
cks | -0.028 |
vows | -0.025 |
irs | -0.025 |
its | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
ls | +0.022 |
cks | +0.019 |
vows | +0.019 |
ves | +0.019 |
irs | +0.019 |
Neg logit contributions | |
sill | -0.015 |
wheel | -0.013 |
hot | -0.013 |
3 | -0.013 |
icle | -0.013 |
Token | yellow |
Token ID | 7872 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
sill | +0.011 |
handy | +0.010 |
happiest | +0.010 |
wheel | +0.010 |
vest | +0.010 |
Neg logit contributions | |
ls | -0.016 |
cks | -0.016 |
irs | -0.015 |
its | -0.014 |
ves | -0.014 |
Token | boat |
Token ID | 8848 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
cks | +0.047 |
ls | +0.044 |
irs | +0.040 |
heit | +0.040 |
ves | +0.040 |
Neg logit contributions | |
boat | -0.026 |
est | -0.025 |
sill | -0.025 |
vest | -0.024 |
handy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-03 |
Pos logit contributions | |
wheel | +0.007 |
sill | +0.007 |
hot | +0.007 |
bar | +0.006 |
uster | +0.006 |
Neg logit contributions | |
ls | -0.008 |
cks | -0.008 |
vows | -0.008 |
irs | -0.007 |
ves | -0.007 |
Token | From |
Token ID | 3574 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
wheel | +0.003 |
sill | +0.002 |
hot | +0.002 |
uster | +0.002 |
aback | +0.002 |
Neg logit contributions | |
ls | -0.003 |
cks | -0.002 |
vows | -0.002 |
irs | -0.002 |
ves | -0.002 |
Token | then |
Token ID | 788 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
wheel | +0.042 |
sill | +0.040 |
hot | +0.038 |
uster | +0.038 |
aback | +0.037 |
Neg logit contributions | |
ls | -0.053 |
cks | -0.048 |
vows | -0.046 |
ves | -0.043 |
nations | -0.043 |
Token | on |
Token ID | 319 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
sill | +0.085 |
wheel | +0.085 |
uster | +0.080 |
aback | +0.078 |
Vest | +0.078 |
Neg logit contributions | |
ls | -0.073 |
cks | -0.066 |
ves | -0.060 |
vows | -0.059 |
runs | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
cks | +0.003 |
ls | +0.003 |
irs | +0.003 |
vows | +0.003 |
its | +0.003 |
Neg logit contributions | |
est | -0.001 |
sill | -0.001 |
hot | -0.001 |
wheel | -0.001 |
icle | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
wheel | +0.039 |
sill | +0.039 |
hot | +0.037 |
aback | +0.036 |
icle | +0.036 |
Neg logit contributions | |
ls | -0.025 |
cks | -0.022 |
vows | -0.022 |
irs | -0.019 |
ves | -0.019 |
Token | island |
Token ID | 7022 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ls | +0.013 |
cks | +0.013 |
irs | +0.012 |
vows | +0.012 |
ves | +0.011 |
Neg logit contributions | |
sill | -0.010 |
handy | -0.009 |
happiest | -0.009 |
est | -0.009 |
wheel | -0.009 |
Token | stayed |
Token ID | 9658 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
ls | +0.039 |
cks | +0.036 |
vows | +0.034 |
irs | +0.033 |
ves | +0.032 |
Neg logit contributions | |
wheel | -0.041 |
sill | -0.041 |
hot | -0.039 |
aback | -0.038 |
icle | -0.037 |