Token | mom |
Token ID | 1995 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
til | +0.076 |
ucks | +0.076 |
pret | +0.072 |
name | +0.068 |
Tracy | +0.066 |
Neg logit contributions | |
no | -0.049 |
unatt | -0.043 |
jected | -0.041 |
fore | -0.040 |
course | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ucks | +0.035 |
til | +0.034 |
pret | +0.032 |
name | +0.031 |
ours | +0.028 |
Neg logit contributions | |
jected | -0.031 |
unatt | -0.031 |
no | -0.030 |
Mic | -0.029 |
P | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
til | +0.033 |
name | +0.032 |
pret | +0.031 |
smell | +0.031 |
ucks | +0.031 |
Neg logit contributions | |
gh | -0.045 |
jected | -0.042 |
Mic | -0.042 |
iable | -0.041 |
vern | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +9.68e-03 |
Pos logit contributions | |
til | +0.062 |
ucks | +0.056 |
name | +0.054 |
pret | +0.054 |
smell | +0.051 |
Neg logit contributions | |
jected | -0.061 |
vern | -0.058 |
unatt | -0.058 |
gh | -0.056 |
ross | -0.055 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
ucks | +0.017 |
til | +0.016 |
pret | +0.016 |
Tracy | +0.015 |
Randy | +0.015 |
Neg logit contributions | |
no | -0.013 |
never | -0.011 |
fore | -0.011 |
unatt | -0.010 |
course | -0.010 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ucks | +0.014 |
til | +0.014 |
pret | +0.011 |
name | +0.010 |
ours | +0.008 |
Neg logit contributions | |
no | -0.043 |
unatt | -0.040 |
jected | -0.039 |
fore | -0.039 |
Jerry | -0.038 |
Token | hes |
Token ID | 956 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
ucks | +0.193 |
til | +0.191 |
pret | +0.169 |
name | +0.160 |
Tracy | +0.143 |
Neg logit contributions | |
no | -0.305 |
unatt | -0.290 |
fore | -0.273 |
jected | -0.273 |
course | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
ucks | +0.131 |
til | +0.131 |
pret | +0.123 |
name | +0.119 |
Tracy | +0.113 |
Neg logit contributions | |
no | -0.076 |
unatt | -0.071 |
jected | -0.067 |
fore | -0.064 |
iable | -0.062 |
Token | They |
Token ID | 1119 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
ucks | +0.041 |
til | +0.039 |
name | +0.036 |
pret | +0.034 |
Tracy | +0.029 |
Neg logit contributions | |
unatt | -0.074 |
jected | -0.071 |
no | -0.071 |
iable | -0.070 |
course | -0.069 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
til | +0.054 |
pret | +0.049 |
ucks | +0.048 |
name | +0.048 |
smell | +0.045 |
Neg logit contributions | |
unatt | -0.064 |
gh | -0.061 |
ross | -0.059 |
no | -0.058 |
vern | -0.057 |
Token | their |
Token ID | 511 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
unatt | +0.068 |
jected | +0.065 |
no | +0.063 |
course | +0.060 |
iable | +0.060 |
Neg logit contributions | |
ucks | -0.086 |
til | -0.084 |
name | -0.078 |
pret | -0.078 |
Tracy | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
Mic | +0.018 |
unatt | +0.018 |
iable | +0.018 |
vern | +0.017 |
P | +0.017 |
Neg logit contributions | |
til | -0.017 |
ucks | -0.016 |
pret | -0.015 |
name | -0.015 |
ours | -0.013 |
Token | run |
Token ID | 1057 |
Feature activation | -6.19e-03 |
Pos logit contributions | |
ucks | +0.037 |
til | +0.031 |
Tracy | +0.029 |
ora | +0.029 |
exception | +0.029 |
Neg logit contributions | |
no | -0.035 |
never | -0.030 |
unatt | -0.028 |
course | -0.027 |
Jerry | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
no | +0.007 |
unatt | +0.006 |
fore | +0.006 |
jected | +0.006 |
never | +0.005 |
Neg logit contributions | |
ucks | -0.012 |
til | -0.012 |
pret | -0.011 |
name | -0.011 |
Tracy | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
ucks | +0.058 |
til | +0.056 |
pret | +0.054 |
rig | +0.053 |
ucker | +0.052 |
Neg logit contributions | |
no | -0.023 |
never | -0.015 |
Jerry | -0.014 |
course | -0.012 |
back | -0.010 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
no | +0.004 |
unatt | +0.004 |
fore | +0.003 |
jected | +0.003 |
never | +0.003 |
Neg logit contributions | |
ucks | -0.004 |
til | -0.004 |
pret | -0.004 |
Tracy | -0.004 |
name | -0.004 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ucks | +0.009 |
til | +0.008 |
pret | +0.006 |
name | +0.006 |
ours | +0.004 |
Neg logit contributions | |
no | -0.034 |
unatt | -0.033 |
fore | -0.032 |
jected | -0.031 |
vern | -0.031 |
Token | hes |
Token ID | 956 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
til | +0.198 |
ucks | +0.198 |
pret | +0.177 |
name | +0.167 |
Tracy | +0.153 |
Neg logit contributions | |
no | -0.297 |
unatt | -0.283 |
jected | -0.267 |
fore | -0.267 |
course | -0.260 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ucks | +0.114 |
til | +0.113 |
pret | +0.106 |
name | +0.104 |
Tracy | +0.097 |
Neg logit contributions | |
unatt | -0.070 |
no | -0.068 |
jected | -0.066 |
Mic | -0.065 |
iable | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -7.72e-05 |
Pos logit contributions | |
til | +0.032 |
ucks | +0.032 |
pret | +0.031 |
Tracy | +0.028 |
le | +0.028 |
Neg logit contributions | |
no | -0.024 |
Jerry | -0.019 |
never | -0.018 |
fore | -0.017 |
Once | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
no | +0.000 |
never | +0.000 |
Once | +0.000 |
The | +0.000 |
fore | +0.000 |
Neg logit contributions | |
til | -0.000 |
pret | -0.000 |
ucks | -0.000 |
Tracy | -0.000 |
enery | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
no | +0.002 |
unatt | +0.002 |
fore | +0.002 |
jected | +0.002 |
iable | +0.002 |
Neg logit contributions | |
ucks | -0.004 |
til | -0.004 |
pret | -0.004 |
name | -0.003 |
Tracy | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
no | +0.015 |
unatt | +0.013 |
fore | +0.012 |
never | +0.012 |
ful | +0.011 |
Neg logit contributions | |
ucks | -0.025 |
pret | -0.023 |
til | -0.023 |
Tracy | -0.022 |
name | -0.022 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
no | +0.017 |
unatt | +0.014 |
fore | +0.014 |
never | +0.014 |
jected | +0.014 |
Neg logit contributions | |
ucks | -0.021 |
til | -0.020 |
pret | -0.019 |
name | -0.018 |
Tracy | -0.017 |
Token | at |
Token ID | 379 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
ucks | +0.030 |
til | +0.028 |
pret | +0.027 |
Tracy | +0.027 |
name | +0.026 |
Neg logit contributions | |
no | -0.014 |
unatt | -0.012 |
fore | -0.011 |
jected | -0.010 |
forever | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
no | +0.032 |
course | +0.024 |
unatt | +0.024 |
fore | +0.023 |
Jerry | +0.023 |
Neg logit contributions | |
ucks | -0.064 |
til | -0.063 |
pret | -0.061 |
name | -0.056 |
Tracy | -0.055 |
Token | ost |
Token ID | 23619 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
no | +0.020 |
never | +0.017 |
fore | +0.017 |
course | +0.015 |
gone | +0.015 |
Neg logit contributions | |
ucks | -0.028 |
til | -0.025 |
pret | -0.025 |
Tracy | -0.025 |
Randy | -0.025 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ucks | +0.003 |
til | +0.003 |
pret | +0.002 |
name | +0.002 |
ours | +0.002 |
Neg logit contributions | |
no | -0.011 |
unatt | -0.010 |
fore | -0.010 |
jected | -0.010 |
Jerry | -0.010 |
Token | hes |
Token ID | 956 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
til | +0.185 |
ucks | +0.184 |
pret | +0.163 |
name | +0.155 |
Tracy | +0.139 |
Neg logit contributions | |
no | -0.296 |
unatt | -0.285 |
fore | -0.266 |
jected | -0.266 |
course | -0.261 |
Token | . |
Token ID | 13 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
til | +0.100 |
ucks | +0.097 |
pret | +0.093 |
name | +0.091 |
Tracy | +0.085 |
Neg logit contributions | |
unatt | -0.067 |
Mic | -0.065 |
no | -0.064 |
jected | -0.063 |
iable | -0.061 |
Token | They |
Token ID | 1119 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ucks | +0.017 |
til | +0.016 |
pret | +0.015 |
ora | +0.014 |
Tracy | +0.014 |
Neg logit contributions | |
no | -0.014 |
fore | -0.011 |
Jerry | -0.011 |
unatt | -0.011 |
never | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
ucks | +0.031 |
til | +0.029 |
pret | +0.027 |
name | +0.026 |
Tracy | +0.025 |
Neg logit contributions | |
no | -0.030 |
unatt | -0.025 |
never | -0.025 |
fore | -0.025 |
jected | -0.024 |
Token | one |
Token ID | 530 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
no | +0.023 |
unatt | +0.020 |
fore | +0.018 |
jected | +0.018 |
course | +0.017 |
Neg logit contributions | |
ucks | -0.038 |
til | -0.038 |
pret | -0.036 |
name | -0.034 |
Tracy | -0.033 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
ucks | +0.046 |
til | +0.046 |
pret | +0.043 |
name | +0.040 |
Tracy | +0.039 |
Neg logit contributions | |
no | -0.041 |
unatt | -0.038 |
jected | -0.036 |
fore | -0.036 |
course | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
no | +0.004 |
unatt | +0.003 |
jected | +0.003 |
fore | +0.003 |
course | +0.003 |
Neg logit contributions | |
til | -0.006 |
ucks | -0.006 |
pret | -0.006 |
name | -0.006 |
Tracy | -0.005 |
Token | touch |
Token ID | 3638 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
no | +0.019 |
never | +0.016 |
unatt | +0.015 |
Jerry | +0.015 |
course | +0.015 |
Neg logit contributions | |
ucks | -0.020 |
til | -0.020 |
pret | -0.019 |
ours | -0.018 |
Tracy | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -6.74e-03 |
Pos logit contributions | |
no | +0.003 |
unatt | +0.002 |
fore | +0.002 |
course | +0.002 |
jected | +0.002 |
Neg logit contributions | |
ucks | -0.004 |
til | -0.004 |
pret | -0.004 |
name | -0.003 |
Tracy | -0.003 |
Token | ost |
Token ID | 23619 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
no | +0.010 |
course | +0.008 |
unatt | +0.008 |
fore | +0.008 |
never | +0.008 |
Neg logit contributions | |
ucks | -0.011 |
til | -0.011 |
Tracy | -0.010 |
pret | -0.010 |
Randy | -0.010 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ucks | +0.004 |
til | +0.004 |
pret | +0.003 |
name | +0.003 |
ours | +0.002 |
Neg logit contributions | |
no | -0.017 |
unatt | -0.016 |
fore | -0.015 |
jected | -0.015 |
vern | -0.015 |
Token | hes |
Token ID | 956 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
ucks | +0.172 |
til | +0.171 |
pret | +0.148 |
name | +0.143 |
ours | +0.128 |
Neg logit contributions | |
no | -0.306 |
unatt | -0.296 |
fore | -0.277 |
jected | -0.273 |
course | -0.270 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
til | +0.108 |
ucks | +0.104 |
pret | +0.102 |
name | +0.099 |
Tracy | +0.092 |
Neg logit contributions | |
unatt | -0.074 |
jected | -0.073 |
Mic | -0.072 |
no | -0.070 |
vern | -0.069 |
Token | They |
Token ID | 1119 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
til | +0.040 |
ucks | +0.039 |
pret | +0.037 |
name | +0.033 |
Tracy | +0.033 |
Neg logit contributions | |
no | -0.039 |
unatt | -0.035 |
fore | -0.033 |
jected | -0.033 |
Jerry | -0.032 |
Token | reached |
Token ID | 4251 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ucks | +0.055 |
til | +0.052 |
pret | +0.048 |
name | +0.046 |
Tracy | +0.045 |
Neg logit contributions | |
no | -0.043 |
unatt | -0.036 |
never | -0.035 |
jected | -0.035 |
fore | -0.035 |
Token | out |
Token ID | 503 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ucks | +0.042 |
pret | +0.038 |
til | +0.038 |
Copy | +0.037 |
Would | +0.037 |
Neg logit contributions | |
no | -0.021 |
back | -0.016 |
fore | -0.013 |
never | -0.013 |
gone | -0.013 |
Token | cried |
Token ID | 16896 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
ucks | +0.013 |
til | +0.012 |
pret | +0.012 |
name | +0.011 |
Tracy | +0.010 |
Neg logit contributions | |
no | -0.013 |
unatt | -0.012 |
jected | -0.012 |
fore | -0.011 |
never | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
unatt | +0.006 |
no | +0.006 |
jected | +0.006 |
course | +0.006 |
iable | +0.006 |
Neg logit contributions | |
til | -0.010 |
ucks | -0.010 |
pret | -0.009 |
name | -0.009 |
Tracy | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
til | +0.026 |
ucks | +0.026 |
pret | +0.024 |
name | +0.024 |
Tracy | +0.021 |
Neg logit contributions | |
unatt | -0.032 |
no | -0.031 |
jected | -0.030 |
iable | -0.029 |
vern | -0.029 |
Token | The |
Token ID | 464 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
til | +0.020 |
ucks | +0.020 |
pret | +0.019 |
name | +0.018 |
Tracy | +0.017 |
Neg logit contributions | |
no | -0.015 |
unatt | -0.013 |
jected | -0.012 |
fore | -0.012 |
course | -0.012 |
Token | ost |
Token ID | 23619 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
ucks | +0.004 |
til | +0.004 |
pret | +0.004 |
Tracy | +0.004 |
name | +0.004 |
Neg logit contributions | |
no | -0.003 |
unatt | -0.003 |
fore | -0.003 |
course | -0.003 |
jected | -0.003 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ucks | +0.014 |
til | +0.014 |
pret | +0.011 |
name | +0.010 |
ours | +0.009 |
Neg logit contributions | |
no | -0.047 |
unatt | -0.044 |
fore | -0.043 |
jected | -0.043 |
Jerry | -0.042 |
Token | hes |
Token ID | 956 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
til | +0.195 |
ucks | +0.195 |
pret | +0.177 |
name | +0.165 |
Tracy | +0.155 |
Neg logit contributions | |
no | -0.276 |
unatt | -0.259 |
jected | -0.248 |
fore | -0.246 |
course | -0.240 |
Token | are |
Token ID | 389 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ucks | +0.081 |
til | +0.080 |
pret | +0.076 |
name | +0.073 |
smell | +0.068 |
Neg logit contributions | |
unatt | -0.072 |
no | -0.072 |
jected | -0.068 |
Mic | -0.068 |
vern | -0.067 |
Token | mean |
Token ID | 1612 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
no | +0.026 |
unatt | +0.024 |
jected | +0.023 |
fore | +0.022 |
course | +0.021 |
Neg logit contributions | |
til | -0.043 |
ucks | -0.042 |
pret | -0.040 |
name | -0.039 |
Tracy | -0.037 |
Token | ! |
Token ID | 0 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
no | +0.016 |
unatt | +0.015 |
jected | +0.015 |
fore | +0.014 |
vern | +0.014 |
Neg logit contributions | |
ucks | -0.019 |
til | -0.019 |
pret | -0.018 |
name | -0.017 |
Tracy | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
no | +0.008 |
unatt | +0.008 |
jected | +0.007 |
fore | +0.007 |
course | +0.007 |
Neg logit contributions | |
ucks | -0.008 |
til | -0.008 |
pret | -0.007 |
name | -0.007 |
Tracy | -0.007 |
Token | too |
Token ID | 1165 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
no | +0.023 |
unatt | +0.020 |
never | +0.018 |
fore | +0.018 |
jected | +0.018 |
Neg logit contributions | |
til | -0.041 |
ucks | -0.041 |
pret | -0.039 |
name | -0.036 |
Tracy | -0.036 |
Token | close |
Token ID | 1969 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
ucks | +0.059 |
til | +0.057 |
name | +0.053 |
ora | +0.050 |
lands | +0.049 |
Neg logit contributions | |
unatt | -0.065 |
jected | -0.065 |
fore | -0.062 |
Mic | -0.062 |
asure | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
jected | +0.033 |
unatt | +0.032 |
no | +0.032 |
Mic | +0.031 |
iable | +0.030 |
Neg logit contributions | |
ucks | -0.049 |
til | -0.048 |
pret | -0.044 |
name | -0.044 |
Tracy | -0.041 |
Token | The |
Token ID | 383 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ucks | +0.017 |
til | +0.016 |
pret | +0.015 |
name | +0.015 |
Tracy | +0.014 |
Neg logit contributions | |
no | -0.015 |
unatt | -0.014 |
jected | -0.013 |
fore | -0.013 |
course | -0.012 |
Token | ost |
Token ID | 23619 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
ucks | +0.025 |
til | +0.023 |
pret | +0.022 |
Tracy | +0.021 |
Randy | +0.020 |
Neg logit contributions | |
no | -0.020 |
fore | -0.017 |
course | -0.017 |
never | -0.017 |
unatt | -0.016 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ucks | +0.006 |
til | +0.006 |
pret | +0.004 |
name | +0.004 |
ours | +0.003 |
Neg logit contributions | |
no | -0.021 |
unatt | -0.020 |
jected | -0.019 |
fore | -0.019 |
vern | -0.019 |
Token | hes |
Token ID | 956 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
til | +0.165 |
ucks | +0.165 |
pret | +0.144 |
name | +0.139 |
ours | +0.124 |
Neg logit contributions | |
no | -0.291 |
unatt | -0.286 |
fore | -0.264 |
Jerry | -0.262 |
jected | -0.262 |
Token | might |
Token ID | 1244 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
ucks | +0.077 |
til | +0.076 |
pret | +0.073 |
name | +0.071 |
smell | +0.065 |
Neg logit contributions | |
unatt | -0.064 |
no | -0.063 |
Mic | -0.062 |
jected | -0.060 |
vern | -0.060 |
Token | pe |
Token ID | 613 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
til | +0.099 |
ucks | +0.096 |
pret | +0.092 |
name | +0.089 |
Tracy | +0.082 |
Neg logit contributions | |
no | -0.079 |
unatt | -0.076 |
jected | -0.074 |
fore | -0.070 |
course | -0.068 |
Token | ck |
Token ID | 694 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
ucks | +0.040 |
til | +0.038 |
pret | +0.038 |
Tracy | +0.036 |
name | +0.035 |
Neg logit contributions | |
no | -0.039 |
unatt | -0.034 |
never | -0.033 |
iable | -0.033 |
jected | -0.033 |
Token | you |
Token ID | 345 |
Feature activation | +6.31e-03 |
Pos logit contributions | |
ucks | +0.064 |
til | +0.062 |
pret | +0.060 |
name | +0.056 |
le | +0.053 |
Neg logit contributions | |
unatt | -0.060 |
no | -0.060 |
vern | -0.057 |
Mic | -0.057 |
jected | -0.057 |
Token | shouted |
Token ID | 17293 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
no | +0.072 |
unatt | +0.062 |
fore | +0.061 |
jected | +0.060 |
Jerry | +0.059 |
Neg logit contributions | |
ucks | -0.084 |
til | -0.081 |
pret | -0.077 |
name | -0.072 |
Tracy | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +9.01e-03 |
Pos logit contributions | |
no | +0.005 |
unatt | +0.004 |
jected | +0.004 |
course | +0.004 |
fore | +0.004 |
Neg logit contributions | |
til | -0.009 |
ucks | -0.009 |
pret | -0.009 |
name | -0.008 |
Tracy | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
til | +0.016 |
ucks | +0.016 |
pret | +0.015 |
name | +0.014 |
Tracy | +0.013 |
Neg logit contributions | |
no | -0.011 |
unatt | -0.010 |
jected | -0.010 |
fore | -0.010 |
course | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
ucks | +0.006 |
til | +0.006 |
pret | +0.005 |
name | +0.005 |
Tracy | +0.005 |
Neg logit contributions | |
no | -0.005 |
unatt | -0.004 |
jected | -0.004 |
fore | -0.004 |
course | -0.004 |
Token | ost |
Token ID | 23619 |
Feature activation | +5.89e-03 |
Pos logit contributions | |
no | +0.003 |
course | +0.003 |
fore | +0.003 |
never | +0.003 |
unatt | +0.003 |
Neg logit contributions | |
ucks | -0.004 |
til | -0.004 |
pret | -0.004 |
Tracy | -0.004 |
ours | -0.003 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ucks | +0.004 |
til | +0.004 |
pret | +0.003 |
name | +0.002 |
ours | +0.002 |
Neg logit contributions | |
no | -0.014 |
unatt | -0.014 |
fore | -0.013 |
jected | -0.013 |
vern | -0.013 |
Token | hes |
Token ID | 956 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
til | +0.176 |
ucks | +0.175 |
pret | +0.156 |
name | +0.148 |
Tracy | +0.133 |
Neg logit contributions | |
no | -0.276 |
unatt | -0.266 |
fore | -0.248 |
jected | -0.247 |
course | -0.243 |
Token | are |
Token ID | 389 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
til | +0.075 |
ucks | +0.075 |
pret | +0.070 |
name | +0.068 |
Tracy | +0.063 |
Neg logit contributions | |
no | -0.064 |
unatt | -0.064 |
jected | -0.060 |
Mic | -0.059 |
vern | -0.058 |
Token | so |
Token ID | 523 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.027 |
fore | +0.026 |
never | +0.025 |
jected | +0.025 |
Neg logit contributions | |
ucks | -0.046 |
til | -0.044 |
pret | -0.042 |
name | -0.039 |
Tracy | -0.039 |
Token | funny |
Token ID | 8258 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
til | +0.101 |
ucks | +0.099 |
name | +0.092 |
pret | +0.092 |
Tracy | +0.086 |
Neg logit contributions | |
no | -0.065 |
unatt | -0.065 |
jected | -0.059 |
fore | -0.058 |
course | -0.056 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.53e-03 |
Pos logit contributions | |
no | +0.011 |
unatt | +0.010 |
jected | +0.010 |
fore | +0.009 |
course | +0.009 |
Neg logit contributions | |
til | -0.015 |
ucks | -0.015 |
pret | -0.014 |
name | -0.014 |
Tracy | -0.013 |
Token | should |
Token ID | 815 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
til | +0.025 |
ucks | +0.025 |
pret | +0.024 |
name | +0.024 |
smell | +0.022 |
Neg logit contributions | |
unatt | -0.023 |
no | -0.022 |
gh | -0.021 |
ross | -0.020 |
fore | -0.020 |
Token | not |
Token ID | 407 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
name | +0.002 |
ucks | +0.002 |
til | +0.002 |
pret | +0.002 |
smell | +0.002 |
Neg logit contributions | |
unatt | -0.001 |
jected | -0.001 |
no | -0.001 |
fore | -0.001 |
Mic | -0.001 |
Token | tease |
Token ID | 34691 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
no | +0.043 |
unatt | +0.041 |
jected | +0.039 |
fore | +0.039 |
vern | +0.037 |
Neg logit contributions | |
ucks | -0.034 |
til | -0.034 |
pret | -0.031 |
name | -0.031 |
smell | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +4.59e-04 |
Pos logit contributions | |
ucks | +0.035 |
til | +0.035 |
pret | +0.033 |
name | +0.032 |
Tracy | +0.030 |
Neg logit contributions | |
no | -0.024 |
jected | -0.023 |
unatt | -0.023 |
vern | -0.023 |
fore | -0.022 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ucks | +0.001 |
til | +0.001 |
Tracy | +0.001 |
Randy | +0.001 |
Stacy | +0.001 |
Neg logit contributions | |
no | -0.001 |
never | -0.001 |
fore | -0.001 |
course | -0.000 |
unatt | -0.000 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ucks | +0.007 |
til | +0.007 |
pret | +0.005 |
name | +0.005 |
ours | +0.004 |
Neg logit contributions | |
no | -0.025 |
unatt | -0.024 |
jected | -0.024 |
fore | -0.024 |
Jerry | -0.023 |
Token | hes |
Token ID | 956 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
til | +0.159 |
ucks | +0.159 |
pret | +0.138 |
name | +0.134 |
ours | +0.121 |
Neg logit contributions | |
no | -0.286 |
unatt | -0.279 |
fore | -0.259 |
jected | -0.255 |
Jerry | -0.255 |
Token | . |
Token ID | 13 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
ucks | +0.095 |
til | +0.093 |
pret | +0.092 |
name | +0.090 |
smell | +0.081 |
Neg logit contributions | |
Mic | -0.081 |
jected | -0.079 |
unatt | -0.077 |
vern | -0.074 |
Jerry | -0.072 |
Token | They |
Token ID | 1119 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
ucks | +0.035 |
til | +0.034 |
pret | +0.031 |
name | +0.030 |
Tracy | +0.028 |
Neg logit contributions | |
no | -0.041 |
unatt | -0.039 |
jected | -0.037 |
fore | -0.036 |
course | -0.036 |
Token | are |
Token ID | 389 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
til | +0.058 |
ucks | +0.058 |
pret | +0.055 |
name | +0.052 |
Tracy | +0.050 |
Neg logit contributions | |
no | -0.040 |
unatt | -0.037 |
jected | -0.034 |
fore | -0.034 |
course | -0.032 |
Token | not |
Token ID | 407 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
no | +0.025 |
unatt | +0.023 |
jected | +0.021 |
fore | +0.021 |
course | +0.020 |
Neg logit contributions | |
til | -0.051 |
ucks | -0.050 |
pret | -0.048 |
name | -0.046 |
Tracy | -0.044 |
Token | stitch |
Token ID | 24695 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
ucks | +0.079 |
til | +0.076 |
pret | +0.067 |
Tracy | +0.065 |
ours | +0.065 |
Neg logit contributions | |
no | -0.056 |
fore | -0.048 |
unatt | -0.046 |
vern | -0.046 |
course | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
til | +0.161 |
ucks | +0.157 |
pret | +0.153 |
name | +0.147 |
Tracy | +0.136 |
Neg logit contributions | |
no | -0.108 |
unatt | -0.104 |
jected | -0.102 |
iable | -0.099 |
Mic | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
til | +0.059 |
ucks | +0.058 |
pret | +0.055 |
name | +0.052 |
Tracy | +0.050 |
Neg logit contributions | |
no | -0.042 |
unatt | -0.039 |
jected | -0.037 |
fore | -0.036 |
course | -0.035 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ucks | +0.048 |
til | +0.047 |
pret | +0.042 |
Tracy | +0.040 |
ours | +0.039 |
Neg logit contributions | |
no | -0.045 |
unatt | -0.040 |
fore | -0.038 |
course | -0.037 |
jected | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
til | +0.071 |
pret | +0.069 |
ucks | +0.069 |
name | +0.066 |
Tracy | +0.059 |
Neg logit contributions | |
no | -0.049 |
unatt | -0.047 |
jected | -0.047 |
Mic | -0.044 |
ross | -0.044 |
Token | name |
Token ID | 1438 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ucks | +0.109 |
til | +0.108 |
pret | +0.099 |
name | +0.092 |
Tracy | +0.091 |
Neg logit contributions | |
no | -0.104 |
unatt | -0.094 |
fore | -0.090 |
jected | -0.089 |
course | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
ucks | +0.235 |
til | +0.233 |
name | +0.229 |
pret | +0.229 |
Tracy | +0.206 |
Neg logit contributions | |
unatt | -0.195 |
iable | -0.183 |
jected | -0.183 |
Mic | -0.182 |
no | -0.176 |
Token | They |
Token ID | 1119 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
til | +0.046 |
ucks | +0.045 |
pret | +0.043 |
ora | +0.039 |
enery | +0.039 |
Neg logit contributions | |
no | -0.031 |
Jerry | -0.025 |
Once | -0.024 |
His | -0.023 |
fore | -0.023 |
Token | called |
Token ID | 1444 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
til | +0.052 |
ucks | +0.052 |
pret | +0.049 |
name | +0.046 |
Tracy | +0.044 |
Neg logit contributions | |
no | -0.044 |
unatt | -0.041 |
jected | -0.039 |
fore | -0.039 |
course | -0.037 |
Token | him |
Token ID | 683 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
ucks | +0.112 |
til | +0.111 |
pret | +0.101 |
name | +0.093 |
ora | +0.092 |
Neg logit contributions | |
no | -0.103 |
unatt | -0.088 |
fore | -0.085 |
course | -0.082 |
never | -0.081 |
Token | Spot |
Token ID | 15899 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
ucks | +0.046 |
til | +0.046 |
pret | +0.042 |
name | +0.039 |
Tracy | +0.039 |
Neg logit contributions | |
no | -0.038 |
unatt | -0.032 |
fore | -0.031 |
never | -0.030 |
Jerry | -0.029 |
Token | name |
Token ID | 1438 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ucks | +0.034 |
til | +0.031 |
pret | +0.027 |
Tracy | +0.027 |
Randy | +0.026 |
Neg logit contributions | |
no | -0.051 |
unatt | -0.046 |
fore | -0.045 |
jected | -0.043 |
never | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
til | +0.227 |
name | +0.213 |
ucks | +0.213 |
pret | +0.212 |
Tracy | +0.191 |
Neg logit contributions | |
unatt | -0.176 |
no | -0.163 |
vern | -0.162 |
jected | -0.158 |
fore | -0.154 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
til | +0.046 |
ucks | +0.045 |
pret | +0.043 |
name | +0.040 |
Tracy | +0.037 |
Neg logit contributions | |
no | -0.058 |
unatt | -0.056 |
jected | -0.054 |
fore | -0.052 |
vern | -0.051 |
Token | writes |
Token ID | 6797 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ucks | +0.022 |
til | +0.021 |
pret | +0.019 |
name | +0.019 |
Tracy | +0.019 |
Neg logit contributions | |
no | -0.019 |
unatt | -0.016 |
jected | -0.016 |
course | -0.015 |
fore | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
ucks | +0.068 |
til | +0.068 |
pret | +0.063 |
name | +0.060 |
Tracy | +0.058 |
Neg logit contributions | |
no | -0.044 |
unatt | -0.039 |
jected | -0.037 |
fore | -0.037 |
course | -0.035 |
Token | name |
Token ID | 1438 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ucks | +0.020 |
til | +0.017 |
Tracy | +0.013 |
pret | +0.013 |
Randy | +0.012 |
Neg logit contributions | |
no | -0.062 |
fore | -0.056 |
unatt | -0.056 |
jected | -0.054 |
asure | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
til | +0.262 |
ucks | +0.254 |
pret | +0.249 |
name | +0.245 |
Tracy | +0.224 |
Neg logit contributions | |
unatt | -0.175 |
no | -0.171 |
jected | -0.159 |
vern | -0.157 |
fore | -0.157 |
Token | Then |
Token ID | 3244 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ucks | +0.042 |
til | +0.042 |
pret | +0.039 |
name | +0.038 |
Tracy | +0.036 |
Neg logit contributions | |
no | -0.035 |
unatt | -0.032 |
jected | -0.031 |
fore | -0.030 |
course | -0.029 |
Token | they |
Token ID | 484 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
til | +0.050 |
pret | +0.049 |
ucks | +0.048 |
name | +0.046 |
Tracy | +0.045 |
Neg logit contributions | |
unatt | -0.038 |
jected | -0.038 |
fore | -0.035 |
vern | -0.035 |
no | -0.034 |
Token | draw |
Token ID | 3197 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.027 |
never | +0.027 |
jected | +0.026 |
course | +0.026 |
Neg logit contributions | |
ucks | -0.034 |
til | -0.032 |
pret | -0.028 |
Tracy | -0.028 |
Randy | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
ucks | +0.009 |
til | +0.009 |
pret | +0.008 |
name | +0.008 |
Tracy | +0.008 |
Neg logit contributions | |
no | -0.006 |
unatt | -0.005 |
fore | -0.005 |
jected | -0.005 |
course | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
vern | +0.074 |
Fred | +0.072 |
Mic | +0.072 |
iable | +0.072 |
unatt | +0.071 |
Neg logit contributions | |
til | -0.055 |
name | -0.054 |
ucks | -0.051 |
pret | -0.050 |
smell | -0.045 |
Token | wrote |
Token ID | 2630 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
til | +0.033 |
ucks | +0.032 |
pret | +0.031 |
name | +0.028 |
Tracy | +0.027 |
Neg logit contributions | |
no | -0.035 |
unatt | -0.033 |
jected | -0.032 |
fore | -0.031 |
vern | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
til | +0.026 |
ucks | +0.026 |
pret | +0.025 |
name | +0.024 |
Tracy | +0.022 |
Neg logit contributions | |
no | -0.019 |
unatt | -0.019 |
jected | -0.018 |
fore | -0.018 |
course | -0.017 |
Token | grandma |
Token ID | 49890 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
ucks | +0.018 |
til | +0.018 |
pret | +0.016 |
Tracy | +0.015 |
ora | +0.014 |
Neg logit contributions | |
no | -0.024 |
unatt | -0.021 |
fore | -0.021 |
jected | -0.020 |
course | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
til | +0.046 |
ucks | +0.045 |
pret | +0.044 |
name | +0.043 |
Tracy | +0.041 |
Neg logit contributions | |
no | -0.021 |
unatt | -0.020 |
jected | -0.018 |
fore | -0.017 |
vern | -0.017 |
Token | name |
Token ID | 1438 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ucks | +0.071 |
til | +0.071 |
pret | +0.064 |
name | +0.058 |
Tracy | +0.058 |
Neg logit contributions | |
no | -0.091 |
unatt | -0.084 |
fore | -0.081 |
jected | -0.080 |
course | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
til | +0.232 |
name | +0.230 |
ucks | +0.225 |
pret | +0.224 |
Tracy | +0.208 |
Neg logit contributions | |
unatt | -0.194 |
no | -0.178 |
vern | -0.176 |
jected | -0.173 |
Mic | -0.169 |
Token | address |
Token ID | 2209 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
til | +0.050 |
ucks | +0.048 |
pret | +0.048 |
name | +0.044 |
Tracy | +0.042 |
Neg logit contributions | |
unatt | -0.051 |
no | -0.050 |
jected | -0.049 |
vern | -0.046 |
fore | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
ucks | +0.048 |
til | +0.047 |
pret | +0.046 |
name | +0.045 |
Tracy | +0.042 |
Neg logit contributions | |
unatt | -0.038 |
no | -0.036 |
Mic | -0.036 |
vern | -0.035 |
jected | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
ucks | +0.009 |
til | +0.009 |
pret | +0.008 |
name | +0.008 |
Tracy | +0.008 |
Neg logit contributions | |
no | -0.006 |
unatt | -0.006 |
jected | -0.005 |
fore | -0.005 |
course | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +7.07e-03 |
Pos logit contributions | |
ucks | +0.058 |
til | +0.055 |
ashes | +0.049 |
pret | +0.049 |
enery | +0.048 |
Neg logit contributions | |
no | -0.046 |
never | -0.041 |
fore | -0.038 |
jected | -0.036 |
gone | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
til | +0.242 |
ucks | +0.233 |
name | +0.232 |
pret | +0.231 |
Tracy | +0.211 |
Neg logit contributions | |
unatt | -0.161 |
no | -0.154 |
jected | -0.148 |
vern | -0.147 |
fore | -0.142 |
Token | and |
Token ID | 290 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
ucks | +0.056 |
til | +0.053 |
pret | +0.049 |
name | +0.047 |
ora | +0.047 |
Neg logit contributions | |
no | -0.039 |
unatt | -0.033 |
fore | -0.031 |
Jerry | -0.031 |
never | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
ucks | +0.029 |
til | +0.029 |
pret | +0.026 |
name | +0.025 |
Tracy | +0.024 |
Neg logit contributions | |
no | -0.024 |
unatt | -0.021 |
fore | -0.020 |
jected | -0.020 |
course | -0.019 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
ucks | +0.059 |
til | +0.054 |
pret | +0.048 |
rig | +0.048 |
ora | +0.048 |
Neg logit contributions | |
no | -0.036 |
unatt | -0.028 |
fore | -0.028 |
course | -0.027 |
never | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
ucks | +0.073 |
til | +0.073 |
pret | +0.069 |
name | +0.065 |
Tracy | +0.063 |
Neg logit contributions | |
no | -0.049 |
unatt | -0.043 |
jected | -0.041 |
fore | -0.041 |
course | -0.039 |
Token | name |
Token ID | 1438 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ucks | +0.058 |
til | +0.052 |
Randy | +0.043 |
pret | +0.042 |
ours | +0.042 |
Neg logit contributions | |
no | -0.083 |
fore | -0.071 |
asure | -0.071 |
, | -0.070 |
course | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
til | +0.277 |
ucks | +0.272 |
pret | +0.266 |
name | +0.259 |
Tracy | +0.244 |
Neg logit contributions | |
unatt | -0.147 |
no | -0.146 |
jected | -0.137 |
fore | -0.129 |
vern | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
ucks | +0.075 |
til | +0.073 |
pret | +0.067 |
name | +0.064 |
Tracy | +0.063 |
Neg logit contributions | |
no | -0.052 |
unatt | -0.045 |
fore | -0.042 |
Jerry | -0.041 |
never | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
til | +0.041 |
ucks | +0.041 |
pret | +0.038 |
name | +0.037 |
Tracy | +0.035 |
Neg logit contributions | |
no | -0.027 |
unatt | -0.024 |
jected | -0.022 |
fore | -0.022 |
course | -0.021 |
Token | cat |
Token ID | 3797 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
ucks | +0.071 |
til | +0.065 |
rig | +0.059 |
exception | +0.057 |
ora | +0.057 |
Neg logit contributions | |
no | -0.046 |
fore | -0.035 |
course | -0.034 |
unatt | -0.034 |
Jerry | -0.033 |
Token | 's |
Token ID | 338 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
ucks | +0.093 |
til | +0.093 |
pret | +0.087 |
name | +0.083 |
Tracy | +0.081 |
Neg logit contributions | |
no | -0.048 |
unatt | -0.042 |
fore | -0.039 |
jected | -0.038 |
course | -0.037 |
Token | paper |
Token ID | 3348 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
ucks | +0.001 |
til | +0.001 |
pret | +0.001 |
name | +0.001 |
Tracy | +0.001 |
Neg logit contributions | |
no | -0.000 |
unatt | -0.000 |
course | -0.000 |
fore | -0.000 |
jected | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
no | +0.050 |
unatt | +0.047 |
jected | +0.046 |
fore | +0.044 |
course | +0.042 |
Neg logit contributions | |
til | -0.062 |
ucks | -0.060 |
pret | -0.058 |
name | -0.055 |
Tracy | -0.052 |
Token | each |
Token ID | 1123 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
til | +0.035 |
ucks | +0.034 |
pret | +0.032 |
name | +0.030 |
Tracy | +0.028 |
Neg logit contributions | |
no | -0.039 |
unatt | -0.037 |
jected | -0.036 |
fore | -0.035 |
course | -0.034 |
Token | write |
Token ID | 3551 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
til | +0.036 |
ucks | +0.035 |
pret | +0.035 |
name | +0.033 |
Tracy | +0.031 |
Neg logit contributions | |
unatt | -0.032 |
no | -0.032 |
jected | -0.029 |
fore | -0.029 |
vern | -0.028 |
Token | their |
Token ID | 511 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
til | +0.045 |
name | +0.044 |
ucks | +0.043 |
pret | +0.043 |
Tracy | +0.038 |
Neg logit contributions | |
unatt | -0.037 |
no | -0.035 |
jected | -0.035 |
Mic | -0.033 |
course | -0.033 |
Token | name |
Token ID | 1438 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
no | +0.004 |
fore | +0.003 |
unatt | +0.003 |
never | +0.003 |
jected | +0.003 |
Neg logit contributions | |
ucks | -0.002 |
til | -0.002 |
pret | -0.002 |
Tracy | -0.002 |
Randy | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
til | +0.233 |
name | +0.228 |
pret | +0.225 |
ucks | +0.224 |
Tracy | +0.204 |
Neg logit contributions | |
unatt | -0.183 |
jected | -0.172 |
no | -0.170 |
Mic | -0.169 |
vern | -0.167 |
Token | it |
Token ID | 340 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
name | +0.026 |
til | +0.026 |
pret | +0.025 |
ucks | +0.025 |
Tracy | +0.023 |
Neg logit contributions | |
unatt | -0.029 |
jected | -0.028 |
vern | -0.026 |
no | -0.026 |
fore | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-04 |
Pos logit contributions | |
til | +0.087 |
ucks | +0.083 |
pret | +0.081 |
name | +0.081 |
Tracy | +0.075 |
Neg logit contributions | |
no | -0.055 |
unatt | -0.055 |
jected | -0.052 |
fore | -0.050 |
vern | -0.048 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
no | +0.001 |
unatt | +0.001 |
jected | +0.001 |
fore | +0.000 |
vern | +0.000 |
Neg logit contributions | |
ucks | -0.001 |
til | -0.001 |
pret | -0.000 |
name | -0.000 |
Tracy | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
til | +0.030 |
pret | +0.030 |
name | +0.030 |
ucks | +0.029 |
Tracy | +0.028 |
Neg logit contributions | |
unatt | -0.021 |
jected | -0.021 |
vern | -0.020 |
Mic | -0.019 |
fore | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
unatt | +0.017 |
Mic | +0.016 |
no | +0.016 |
jected | +0.016 |
fore | +0.016 |
Neg logit contributions | |
til | -0.022 |
ucks | -0.020 |
pret | -0.020 |
name | -0.019 |
smell | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ucks | +0.024 |
til | +0.024 |
pret | +0.023 |
name | +0.021 |
Tracy | +0.020 |
Neg logit contributions | |
no | -0.021 |
Jerry | -0.018 |
unatt | -0.018 |
fore | -0.017 |
course | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ucks | +0.030 |
til | +0.027 |
pret | +0.026 |
name | +0.024 |
Tracy | +0.024 |
Neg logit contributions | |
no | -0.023 |
never | -0.019 |
unatt | -0.019 |
fore | -0.018 |
jected | -0.018 |
Token | called |
Token ID | 1444 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
no | +0.039 |
never | +0.032 |
gone | +0.029 |
Jerry | +0.029 |
fore | +0.029 |
Neg logit contributions | |
ucks | -0.062 |
pret | -0.055 |
til | -0.054 |
ours | -0.050 |
Tracy | -0.050 |
Token | ost |
Token ID | 23619 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
til | +0.083 |
ucks | +0.079 |
name | +0.076 |
pret | +0.076 |
Tracy | +0.069 |
Neg logit contributions | |
no | -0.076 |
unatt | -0.075 |
jected | -0.073 |
fore | -0.068 |
iable | -0.067 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
til | +0.002 |
ucks | +0.002 |
pret | +0.001 |
name | +0.001 |
ours | +0.001 |
Neg logit contributions | |
no | -0.007 |
unatt | -0.007 |
fore | -0.006 |
jected | -0.006 |
course | -0.006 |
Token | hes |
Token ID | 956 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
til | +0.169 |
ucks | +0.162 |
pret | +0.148 |
name | +0.142 |
Tracy | +0.127 |
Neg logit contributions | |
no | -0.258 |
unatt | -0.253 |
jected | -0.234 |
fore | -0.233 |
course | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
til | +0.086 |
ucks | +0.082 |
pret | +0.079 |
name | +0.078 |
Tracy | +0.073 |
Neg logit contributions | |
unatt | -0.064 |
no | -0.060 |
jected | -0.058 |
vern | -0.058 |
Mic | -0.058 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
til | +0.025 |
ucks | +0.025 |
pret | +0.024 |
name | +0.022 |
Tracy | +0.021 |
Neg logit contributions | |
no | -0.021 |
unatt | -0.018 |
Jerry | -0.018 |
fore | -0.018 |
jected | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
ucks | +0.009 |
til | +0.009 |
pret | +0.008 |
name | +0.008 |
Tracy | +0.008 |
Neg logit contributions | |
no | -0.008 |
unatt | -0.007 |
fore | -0.007 |
jected | -0.007 |
never | -0.006 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ucks | +0.006 |
til | +0.006 |
pret | +0.005 |
name | +0.005 |
Tracy | +0.005 |
Neg logit contributions | |
no | -0.004 |
unatt | -0.004 |
fore | -0.004 |
jected | -0.004 |
Jerry | -0.004 |
Token | glitter |
Token ID | 31133 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
til | +0.057 |
pret | +0.054 |
ucks | +0.053 |
name | +0.049 |
Tracy | +0.045 |
Neg logit contributions | |
unatt | -0.061 |
no | -0.060 |
jected | -0.059 |
vern | -0.056 |
iable | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
ucks | +0.078 |
til | +0.076 |
pret | +0.070 |
name | +0.069 |
Tracy | +0.063 |
Neg logit contributions | |
no | -0.079 |
unatt | -0.078 |
jected | -0.074 |
fore | -0.072 |
Mic | -0.071 |
Token | gave |
Token ID | 2921 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
til | +0.057 |
pret | +0.055 |
ucks | +0.051 |
name | +0.049 |
smell | +0.045 |
Neg logit contributions | |
unatt | -0.066 |
jected | -0.065 |
no | -0.062 |
vern | -0.061 |
iable | -0.061 |
Token | it |
Token ID | 340 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
til | +0.049 |
ucks | +0.048 |
pret | +0.045 |
name | +0.040 |
Tracy | +0.039 |
Neg logit contributions | |
no | -0.050 |
unatt | -0.041 |
course | -0.041 |
fore | -0.040 |
never | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
ucks | +0.050 |
til | +0.050 |
pret | +0.047 |
name | +0.046 |
Tracy | +0.043 |
Neg logit contributions | |
no | -0.033 |
unatt | -0.032 |
jected | -0.030 |
fore | -0.029 |
course | -0.028 |
Token | name |
Token ID | 1438 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ucks | +0.099 |
til | +0.095 |
pret | +0.085 |
Tracy | +0.080 |
ours | +0.080 |
Neg logit contributions | |
no | -0.083 |
fore | -0.071 |
unatt | -0.070 |
course | -0.068 |
vern | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
ucks | +0.233 |
name | +0.232 |
til | +0.229 |
pret | +0.222 |
Tracy | +0.207 |
Neg logit contributions | |
unatt | -0.187 |
jected | -0.173 |
iable | -0.168 |
Mic | -0.168 |
no | -0.167 |
Token | They |
Token ID | 1119 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
ucks | +0.045 |
til | +0.044 |
pret | +0.042 |
ora | +0.040 |
exception | +0.039 |
Neg logit contributions | |
no | -0.037 |
Jerry | -0.030 |
fore | -0.028 |
never | -0.028 |
Once | -0.027 |
Token | called |
Token ID | 1444 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
til | +0.054 |
ucks | +0.054 |
pret | +0.051 |
name | +0.048 |
Tracy | +0.046 |
Neg logit contributions | |
no | -0.044 |
unatt | -0.041 |
jected | -0.039 |
fore | -0.038 |
course | -0.037 |
Token | it |
Token ID | 340 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
til | +0.109 |
ucks | +0.108 |
pret | +0.101 |
name | +0.097 |
Tracy | +0.092 |
Neg logit contributions | |
no | -0.088 |
unatt | -0.082 |
jected | -0.078 |
fore | -0.077 |
course | -0.073 |
Token | O |
Token ID | 440 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
ucks | +0.019 |
til | +0.019 |
pret | +0.017 |
name | +0.016 |
Tracy | +0.016 |
Neg logit contributions | |
no | -0.016 |
unatt | -0.014 |
fore | -0.013 |
jected | -0.013 |
never | -0.013 |
Token | cake |
Token ID | 12187 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
ucks | +0.003 |
til | +0.003 |
pret | +0.003 |
Tracy | +0.003 |
ora | +0.003 |
Neg logit contributions | |
no | -0.003 |
unatt | -0.002 |
fore | -0.002 |
course | -0.002 |
never | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
no | +0.054 |
jected | +0.053 |
unatt | +0.051 |
vern | +0.050 |
fore | +0.049 |
Neg logit contributions | |
til | -0.070 |
ucks | -0.068 |
pret | -0.066 |
name | -0.065 |
smell | -0.060 |
Token | candles |
Token ID | 32268 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
ucks | +0.045 |
til | +0.044 |
pret | +0.044 |
name | +0.043 |
Tracy | +0.040 |
Neg logit contributions | |
unatt | -0.044 |
jected | -0.043 |
vern | -0.041 |
no | -0.039 |
ross | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
Mic | +0.054 |
vern | +0.054 |
jected | +0.053 |
unatt | +0.053 |
Fred | +0.051 |
Neg logit contributions | |
ucks | -0.042 |
til | -0.041 |
name | -0.040 |
pret | -0.038 |
smell | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
til | +0.062 |
ucks | +0.062 |
pret | +0.061 |
name | +0.057 |
Tracy | +0.054 |
Neg logit contributions | |
no | -0.045 |
unatt | -0.044 |
jected | -0.042 |
fore | -0.039 |
vern | -0.039 |
Token | name |
Token ID | 1438 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ucks | +0.035 |
til | +0.033 |
pret | +0.030 |
Tracy | +0.029 |
ora | +0.028 |
Neg logit contributions | |
no | -0.029 |
unatt | -0.025 |
fore | -0.025 |
course | -0.023 |
jected | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
til | +0.216 |
ucks | +0.216 |
name | +0.215 |
pret | +0.213 |
Tracy | +0.192 |
Neg logit contributions | |
unatt | -0.196 |
jected | -0.186 |
Mic | -0.185 |
vern | -0.181 |
no | -0.173 |
Token | it |
Token ID | 340 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
til | +0.018 |
ucks | +0.017 |
pret | +0.017 |
name | +0.017 |
Tracy | +0.014 |
Neg logit contributions | |
unatt | -0.029 |
jected | -0.028 |
no | -0.028 |
fore | -0.027 |
vern | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
til | +0.089 |
ucks | +0.088 |
pret | +0.084 |
name | +0.081 |
Tracy | +0.078 |
Neg logit contributions | |
no | -0.047 |
unatt | -0.043 |
jected | -0.040 |
fore | -0.039 |
course | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ucks | +0.029 |
til | +0.028 |
pret | +0.026 |
name | +0.026 |
Tracy | +0.024 |
Neg logit contributions | |
no | -0.030 |
unatt | -0.029 |
jected | -0.028 |
fore | -0.027 |
course | -0.026 |
Token | had |
Token ID | 550 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
ucks | +0.044 |
til | +0.044 |
pret | +0.040 |
name | +0.039 |
Tracy | +0.038 |
Neg logit contributions | |
no | -0.032 |
unatt | -0.028 |
jected | -0.026 |
fore | -0.026 |
never | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
til | +0.040 |
ucks | +0.040 |
pret | +0.037 |
name | +0.034 |
Tracy | +0.033 |
Neg logit contributions | |
no | -0.038 |
unatt | -0.035 |
jected | -0.033 |
fore | -0.033 |
course | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
ucks | +0.007 |
til | +0.007 |
pret | +0.006 |
name | +0.006 |
Tracy | +0.006 |
Neg logit contributions | |
no | -0.005 |
unatt | -0.005 |
jected | -0.005 |
fore | -0.005 |
course | -0.005 |
Token | But |
Token ID | 1537 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ucks | +0.004 |
name | +0.003 |
til | +0.003 |
pret | +0.003 |
ora | +0.003 |
Neg logit contributions | |
unatt | -0.003 |
course | -0.003 |
no | -0.003 |
forever | -0.003 |
earthquake | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
vern | +0.023 |
jected | +0.023 |
unatt | +0.022 |
Mic | +0.022 |
iable | +0.021 |
Neg logit contributions | |
til | -0.024 |
pret | -0.022 |
ucks | -0.022 |
name | -0.021 |
Tracy | -0.020 |
Token | ost |
Token ID | 23619 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
no | +0.014 |
fore | +0.012 |
never | +0.011 |
course | +0.011 |
unatt | +0.010 |
Neg logit contributions | |
ucks | -0.017 |
til | -0.016 |
Tracy | -0.015 |
pret | -0.015 |
Randy | -0.015 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
no | +0.007 |
unatt | +0.006 |
fore | +0.006 |
jected | +0.006 |
Jerry | +0.006 |
Neg logit contributions | |
ucks | -0.002 |
til | -0.002 |
pret | -0.001 |
name | -0.001 |
ours | -0.001 |
Token | hes |
Token ID | 956 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
til | +0.150 |
ucks | +0.146 |
pret | +0.126 |
name | +0.121 |
ours | +0.110 |
Neg logit contributions | |
no | -0.274 |
unatt | -0.270 |
Jerry | -0.251 |
fore | -0.250 |
course | -0.249 |
Token | did |
Token ID | 750 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
til | +0.071 |
ucks | +0.071 |
pret | +0.066 |
name | +0.063 |
Tracy | +0.060 |
Neg logit contributions | |
no | -0.065 |
unatt | -0.062 |
jected | -0.058 |
fore | -0.057 |
vern | -0.056 |
Token | not |
Token ID | 407 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
no | +0.003 |
unatt | +0.002 |
jected | +0.002 |
fore | +0.002 |
course | +0.002 |
Neg logit contributions | |
til | -0.009 |
ucks | -0.009 |
pret | -0.009 |
name | -0.008 |
Tracy | -0.008 |
Token | like |
Token ID | 588 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
no | +0.040 |
unatt | +0.036 |
never | +0.034 |
fore | +0.034 |
jected | +0.033 |
Neg logit contributions | |
ucks | -0.043 |
til | -0.041 |
pret | -0.038 |
Tracy | -0.036 |
ours | -0.036 |
Token | that |
Token ID | 326 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
til | +0.102 |
ucks | +0.101 |
pret | +0.095 |
name | +0.090 |
Tracy | +0.087 |
Neg logit contributions | |
no | -0.074 |
unatt | -0.069 |
jected | -0.066 |
fore | -0.064 |
course | -0.062 |
Token | ball |
Token ID | 2613 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
til | +0.079 |
ucks | +0.079 |
pret | +0.074 |
name | +0.070 |
Tracy | +0.068 |
Neg logit contributions | |
no | -0.055 |
unatt | -0.050 |
jected | -0.047 |
fore | -0.047 |
course | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
iable | +0.034 |
unatt | +0.034 |
fore | +0.033 |
no | +0.033 |
vern | +0.033 |
Neg logit contributions | |
til | -0.036 |
ucks | -0.035 |
pret | -0.033 |
name | -0.031 |
ashes | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
til | +0.058 |
ucks | +0.056 |
pret | +0.054 |
name | +0.050 |
Tracy | +0.046 |
Neg logit contributions | |
no | -0.067 |
unatt | -0.065 |
jected | -0.063 |
fore | -0.061 |
vern | -0.059 |
Token | dog |
Token ID | 3290 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ucks | +0.051 |
til | +0.051 |
pret | +0.047 |
Tracy | +0.045 |
name | +0.044 |
Neg logit contributions | |
no | -0.040 |
unatt | -0.035 |
fore | -0.033 |
course | -0.033 |
jected | -0.032 |
Token | fet |
Token ID | 11351 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
til | +0.069 |
ucks | +0.069 |
pret | +0.065 |
name | +0.062 |
Tracy | +0.060 |
Neg logit contributions | |
no | -0.042 |
unatt | -0.038 |
jected | -0.036 |
fore | -0.035 |
course | -0.034 |
Token | ches |
Token ID | 2052 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
til | +0.090 |
ucks | +0.087 |
pret | +0.079 |
Tracy | +0.073 |
name | +0.072 |
Neg logit contributions | |
no | -0.105 |
course | -0.091 |
fore | -0.090 |
unatt | -0.090 |
jected | -0.090 |
Token | it |
Token ID | 340 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
til | +0.213 |
ucks | +0.213 |
pret | +0.198 |
name | +0.186 |
Tracy | +0.178 |
Neg logit contributions | |
no | -0.215 |
unatt | -0.200 |
jected | -0.191 |
fore | -0.189 |
course | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
til | +0.098 |
ucks | +0.097 |
pret | +0.092 |
name | +0.090 |
ashes | +0.081 |
Neg logit contributions | |
no | -0.066 |
unatt | -0.064 |
jected | -0.063 |
fore | -0.062 |
iable | -0.060 |
Token | They |
Token ID | 1119 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
til | +0.042 |
ucks | +0.042 |
pret | +0.039 |
name | +0.037 |
Tracy | +0.035 |
Neg logit contributions | |
no | -0.047 |
unatt | -0.043 |
jected | -0.041 |
fore | -0.040 |
course | -0.039 |
Token | hug |
Token ID | 16225 |
Feature activation | -6.22e-03 |
Pos logit contributions | |
ucks | +0.053 |
til | +0.049 |
pret | +0.045 |
Tracy | +0.043 |
ours | +0.043 |
Neg logit contributions | |
no | -0.047 |
unatt | -0.040 |
never | -0.040 |
course | -0.039 |
fore | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
no | +0.008 |
unatt | +0.007 |
jected | +0.007 |
fore | +0.007 |
vern | +0.007 |
Neg logit contributions | |
til | -0.011 |
ucks | -0.011 |
pret | -0.010 |
name | -0.010 |
Tracy | -0.009 |
Token | name |
Token ID | 1438 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ucks | +0.008 |
til | +0.007 |
pret | +0.005 |
Tracy | +0.005 |
ora | +0.005 |
Neg logit contributions | |
no | -0.021 |
fore | -0.018 |
unatt | -0.018 |
never | -0.018 |
asure | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
til | +0.224 |
name | +0.219 |
pret | +0.217 |
ucks | +0.216 |
Tracy | +0.191 |
Neg logit contributions | |
unatt | -0.181 |
no | -0.170 |
vern | -0.168 |
jected | -0.166 |
fore | -0.160 |
Token | his |
Token ID | 465 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ucks | +0.059 |
til | +0.057 |
pret | +0.052 |
ora | +0.051 |
name | +0.051 |
Neg logit contributions | |
no | -0.037 |
unatt | -0.031 |
fore | -0.030 |
Jerry | -0.029 |
never | -0.028 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
ucks | +0.018 |
til | +0.017 |
pret | +0.015 |
Tracy | +0.015 |
ora | +0.014 |
Neg logit contributions | |
no | -0.018 |
unatt | -0.015 |
fore | -0.015 |
asure | -0.014 |
course | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
til | +0.089 |
ucks | +0.088 |
pret | +0.087 |
name | +0.085 |
Tracy | +0.079 |
Neg logit contributions | |
no | -0.045 |
unatt | -0.045 |
jected | -0.041 |
vern | -0.040 |
fore | -0.039 |
Token | name |
Token ID | 1438 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ucks | +0.055 |
til | +0.050 |
pret | +0.044 |
ours | +0.040 |
Tracy | +0.040 |
Neg logit contributions | |
no | -0.092 |
unatt | -0.081 |
fore | -0.080 |
asure | -0.078 |
never | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
til | +0.266 |
pret | +0.261 |
name | +0.261 |
ucks | +0.258 |
Tracy | +0.234 |
Neg logit contributions | |
unatt | -0.154 |
jected | -0.140 |
no | -0.138 |
vern | -0.137 |
Mic | -0.130 |
Token | and |
Token ID | 290 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ucks | +0.078 |
til | +0.077 |
pret | +0.071 |
name | +0.068 |
Tracy | +0.067 |
Neg logit contributions | |
no | -0.051 |
unatt | -0.044 |
fore | -0.042 |
Jerry | -0.040 |
course | -0.040 |
Token | his |
Token ID | 465 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ucks | +0.050 |
til | +0.049 |
pret | +0.046 |
name | +0.044 |
Tracy | +0.043 |
Neg logit contributions | |
no | -0.025 |
unatt | -0.020 |
fore | -0.019 |
jected | -0.019 |
course | -0.018 |
Token | dog |
Token ID | 3290 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
ucks | +0.032 |
til | +0.030 |
pret | +0.027 |
ours | +0.026 |
Tracy | +0.026 |
Neg logit contributions | |
no | -0.022 |
fore | -0.017 |
unatt | -0.016 |
course | -0.016 |
never | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ucks | +0.056 |
til | +0.056 |
pret | +0.052 |
name | +0.049 |
Tracy | +0.049 |
Neg logit contributions | |
no | -0.029 |
unatt | -0.025 |
fore | -0.023 |
jected | -0.023 |
course | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
no | +0.001 |
unatt | +0.001 |
jected | +0.001 |
fore | +0.001 |
Mic | +0.001 |
Neg logit contributions | |
til | -0.002 |
ucks | -0.002 |
pret | -0.002 |
name | -0.002 |
Tracy | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
til | +0.102 |
ucks | +0.101 |
pret | +0.093 |
name | +0.087 |
Tracy | +0.082 |
Neg logit contributions | |
no | -0.140 |
unatt | -0.132 |
jected | -0.126 |
fore | -0.125 |
course | -0.122 |
Token | " |
Token ID | 366 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
til | +0.070 |
name | +0.069 |
pret | +0.066 |
ucks | +0.064 |
Tracy | +0.061 |
Neg logit contributions | |
unatt | -0.076 |
jected | -0.074 |
Mic | -0.070 |
iable | -0.067 |
no | -0.065 |
Token | O |
Token ID | 46 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
til | +0.024 |
ucks | +0.023 |
pret | +0.022 |
name | +0.020 |
ours | +0.020 |
Neg logit contributions | |
no | -0.020 |
unatt | -0.018 |
jected | -0.017 |
fore | -0.017 |
course | -0.017 |
Token | st |
Token ID | 301 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
til | +0.058 |
ucks | +0.057 |
pret | +0.055 |
name | +0.052 |
Tracy | +0.051 |
Neg logit contributions | |
no | -0.047 |
unatt | -0.042 |
jected | -0.041 |
course | -0.040 |
never | -0.039 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
til | +0.059 |
ucks | +0.056 |
pret | +0.053 |
Tracy | +0.047 |
spec | +0.045 |
Neg logit contributions | |
no | -0.064 |
asure | -0.054 |
fore | -0.054 |
never | -0.054 |
bar | -0.053 |
Token | hes |
Token ID | 956 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
til | +0.162 |
ucks | +0.157 |
name | +0.152 |
pret | +0.142 |
ours | +0.131 |
Neg logit contributions | |
unatt | -0.255 |
no | -0.248 |
Mic | -0.228 |
course | -0.228 |
jected | -0.226 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
ucks | +0.076 |
til | +0.075 |
name | +0.074 |
pret | +0.071 |
ours | +0.065 |
Neg logit contributions | |
unatt | -0.074 |
no | -0.070 |
jected | -0.068 |
Mic | -0.068 |
vern | -0.066 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
til | +0.002 |
ucks | +0.002 |
pret | +0.002 |
Tracy | +0.002 |
rig | +0.002 |
Neg logit contributions | |
no | -0.003 |
Jerry | -0.002 |
fore | -0.002 |
asure | -0.002 |
never | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
ucks | +0.020 |
til | +0.019 |
pret | +0.018 |
name | +0.017 |
Tracy | +0.017 |
Neg logit contributions | |
no | -0.018 |
unatt | -0.016 |
jected | -0.015 |
fore | -0.015 |
course | -0.015 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
til | +0.004 |
ucks | +0.004 |
pret | +0.004 |
name | +0.004 |
Tracy | +0.003 |
Neg logit contributions | |
no | -0.003 |
unatt | -0.003 |
jected | -0.002 |
fore | -0.002 |
vern | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -6.54e-04 |
Pos logit contributions | |
til | +0.062 |
pret | +0.058 |
name | +0.054 |
ucks | +0.051 |
smell | +0.050 |
Neg logit contributions | |
jected | -0.043 |
unatt | -0.042 |
Mic | -0.037 |
vern | -0.036 |
ross | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
unatt | +0.001 |
jected | +0.001 |
no | +0.001 |
vern | +0.001 |
course | +0.001 |
Neg logit contributions | |
til | -0.001 |
pret | -0.001 |
ucks | -0.001 |
name | -0.001 |
Tracy | -0.001 |
Token | You |
Token ID | 1639 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
ucks | +0.004 |
til | +0.004 |
pret | +0.004 |
name | +0.003 |
Tracy | +0.003 |
Neg logit contributions | |
no | -0.004 |
unatt | -0.004 |
fore | -0.003 |
jected | -0.003 |
vern | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
til | +0.011 |
name | +0.011 |
pret | +0.011 |
ucks | +0.011 |
smell | +0.010 |
Neg logit contributions | |
unatt | -0.011 |
no | -0.010 |
jected | -0.010 |
fore | -0.010 |
ross | -0.009 |
Token | under |
Token ID | 739 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
unatt | +0.055 |
side | +0.053 |
jected | +0.050 |
earned | +0.049 |
ross | +0.049 |
Neg logit contributions | |
til | -0.067 |
name | -0.066 |
smell | -0.062 |
pret | -0.061 |
Randy | -0.056 |
Token | arrest |
Token ID | 3251 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
jected | +0.033 |
iable | +0.031 |
vern | +0.031 |
unatt | +0.028 |
asure | +0.028 |
Neg logit contributions | |
til | -0.054 |
pret | -0.051 |
ucks | -0.050 |
name | -0.048 |
lands | -0.048 |
Token | for |
Token ID | 329 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
no | +0.148 |
unatt | +0.143 |
jected | +0.140 |
vern | +0.138 |
fore | +0.135 |
Neg logit contributions | |
til | -0.217 |
ucks | -0.214 |
pret | -0.204 |
name | -0.192 |
guesses | -0.180 |
Token | harassing |
Token ID | 34110 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
til | +0.003 |
pret | +0.003 |
ucks | +0.003 |
smell | +0.003 |
name | +0.003 |
Neg logit contributions | |
jected | -0.003 |
unatt | -0.002 |
iable | -0.002 |
vern | -0.002 |
ross | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -6.08e-03 |
Pos logit contributions | |
iable | +0.019 |
unatt | +0.019 |
jected | +0.019 |
no | +0.018 |
course | +0.018 |
Neg logit contributions | |
ucks | -0.026 |
til | -0.024 |
name | -0.024 |
pret | -0.023 |
Tracy | -0.022 |
Token | stealing |
Token ID | 16568 |
Feature activation | +5.47e-03 |
Pos logit contributions | |
no | +0.008 |
unatt | +0.007 |
jected | +0.007 |
fore | +0.007 |
vern | +0.007 |
Neg logit contributions | |
til | -0.010 |
ucks | -0.010 |
pret | -0.010 |
name | -0.009 |
Tracy | -0.009 |
Token | from |
Token ID | 422 |
Feature activation | -4.03e-03 |
Pos logit contributions | |
ucks | +0.009 |
pret | +0.008 |
til | +0.008 |
name | +0.008 |
Tracy | +0.007 |
Neg logit contributions | |
jected | -0.007 |
unatt | -0.007 |
no | -0.007 |
Mic | -0.007 |
iable | -0.006 |
Token | robber |
Token ID | 29979 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
unatt | +0.022 |
no | +0.022 |
jected | +0.021 |
fore | +0.020 |
vern | +0.020 |
Neg logit contributions | |
til | -0.028 |
ucks | -0.028 |
pret | -0.027 |
name | -0.026 |
Tracy | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
no | +0.058 |
unatt | +0.051 |
jected | +0.048 |
fore | +0.047 |
course | +0.045 |
Neg logit contributions | |
ucks | -0.101 |
til | -0.101 |
pret | -0.095 |
name | -0.091 |
Tracy | -0.088 |
Token | You |
Token ID | 921 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
no | +0.030 |
unatt | +0.027 |
jected | +0.026 |
fore | +0.026 |
course | +0.025 |
Neg logit contributions | |
til | -0.034 |
ucks | -0.034 |
pret | -0.032 |
name | -0.030 |
Tracy | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
unatt | +0.006 |
no | +0.006 |
jected | +0.005 |
ross | +0.005 |
fore | +0.005 |
Neg logit contributions | |
til | -0.006 |
name | -0.006 |
pret | -0.006 |
ucks | -0.006 |
smell | -0.005 |
Token | under |
Token ID | 739 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
unatt | +0.055 |
jected | +0.053 |
no | +0.053 |
course | +0.052 |
vern | +0.051 |
Neg logit contributions | |
til | -0.079 |
pret | -0.075 |
name | -0.071 |
ucks | -0.070 |
smell | -0.068 |
Token | arrest |
Token ID | 3251 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
jected | +0.042 |
iable | +0.040 |
vern | +0.039 |
asure | +0.036 |
unatt | +0.036 |
Neg logit contributions | |
til | -0.052 |
lands | -0.048 |
pret | -0.048 |
ucks | -0.047 |
name | -0.044 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
no | +0.164 |
unatt | +0.154 |
jected | +0.146 |
fore | +0.144 |
vern | +0.139 |
Neg logit contributions | |
til | -0.214 |
ucks | -0.212 |
pret | -0.199 |
name | -0.189 |
Tracy | -0.179 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ucks | +0.005 |
til | +0.005 |
pret | +0.005 |
ours | +0.004 |
name | +0.004 |
Neg logit contributions | |
no | -0.003 |
Jerry | -0.003 |
course | -0.002 |
never | -0.002 |
Once | -0.002 |
Token | shouts |
Token ID | 34757 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
no | +0.037 |
never | +0.032 |
Jerry | +0.031 |
jected | +0.031 |
fore | +0.031 |
Neg logit contributions | |
ucks | -0.026 |
enery | -0.020 |
til | -0.020 |
ora | -0.020 |
ours | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
til | +0.056 |
ucks | +0.055 |
pret | +0.052 |
name | +0.050 |
Tracy | +0.048 |
Neg logit contributions | |
no | -0.029 |
unatt | -0.027 |
jected | -0.025 |
fore | -0.025 |
course | -0.024 |
Token | holding |
Token ID | 4769 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
no | +0.006 |
unatt | +0.005 |
jected | +0.005 |
fore | +0.005 |
never | +0.005 |
Neg logit contributions | |
ucks | -0.006 |
til | -0.006 |
pret | -0.006 |
name | -0.005 |
Tracy | -0.005 |
Token | Bang |
Token ID | 9801 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
ucks | +0.028 |
name | +0.026 |
pret | +0.025 |
til | +0.025 |
Tracy | +0.022 |
Neg logit contributions | |
unatt | -0.028 |
jected | -0.026 |
vern | -0.026 |
no | -0.025 |
course | -0.025 |
Token | ! |
Token ID | 0 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ucks | +0.008 |
til | +0.008 |
pret | +0.008 |
name | +0.007 |
Tracy | +0.007 |
Neg logit contributions | |
no | -0.005 |
unatt | -0.005 |
fore | -0.004 |
jected | -0.004 |
vern | -0.004 |
Token | You |
Token ID | 921 |
Feature activation | +8.97e-03 |
Pos logit contributions | |
ucks | +0.021 |
name | +0.020 |
pret | +0.019 |
til | +0.018 |
Tracy | +0.016 |
Neg logit contributions | |
unatt | -0.021 |
vern | -0.020 |
jected | -0.019 |
iable | -0.019 |
no | -0.019 |
Token | 're |
Token ID | 821 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
name | +0.013 |
pret | +0.013 |
ucks | +0.013 |
til | +0.013 |
smell | +0.012 |
Neg logit contributions | |
unatt | -0.012 |
Mic | -0.011 |
vern | -0.011 |
ross | -0.011 |
jected | -0.011 |
Token | under |
Token ID | 739 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
unatt | +0.019 |
jected | +0.018 |
no | +0.018 |
course | +0.017 |
vern | +0.017 |
Neg logit contributions | |
til | -0.030 |
pret | -0.029 |
ucks | -0.028 |
name | -0.028 |
smell | -0.026 |
Token | arrest |
Token ID | 3251 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
jected | +0.030 |
iable | +0.028 |
vern | +0.028 |
unatt | +0.028 |
asure | +0.025 |
Neg logit contributions | |
til | -0.064 |
pret | -0.061 |
ucks | -0.061 |
name | -0.057 |
lands | -0.057 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
no | +0.168 |
unatt | +0.160 |
jected | +0.154 |
fore | +0.151 |
vern | +0.147 |
Neg logit contributions | |
til | -0.203 |
ucks | -0.201 |
pret | -0.190 |
name | -0.179 |
Tracy | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +3.51e-03 |
Pos logit contributions | |
ucks | +0.034 |
til | +0.034 |
pret | +0.032 |
name | +0.030 |
Tracy | +0.029 |
Neg logit contributions | |
no | -0.023 |
unatt | -0.020 |
fore | -0.019 |
jected | -0.019 |
Jerry | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
til | +0.007 |
ucks | +0.007 |
pret | +0.006 |
name | +0.006 |
Tracy | +0.006 |
Neg logit contributions | |
no | -0.004 |
unatt | -0.003 |
fore | -0.003 |
jected | -0.003 |
course | -0.003 |
Token | Their |
Token ID | 14574 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
ucks | +0.004 |
til | +0.003 |
pret | +0.003 |
Tracy | +0.003 |
name | +0.003 |
Neg logit contributions | |
no | -0.002 |
unatt | -0.002 |
jected | -0.002 |
fore | -0.002 |
iable | -0.002 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.57e-04 |
Pos logit contributions | |
no | +0.062 |
unatt | +0.058 |
jected | +0.055 |
fore | +0.054 |
course | +0.052 |
Neg logit contributions | |
til | -0.078 |
ucks | -0.078 |
pret | -0.073 |
name | -0.070 |
Tracy | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | +7.64e-03 |
Pos logit contributions | |
til | +0.051 |
ucks | +0.051 |
pret | +0.048 |
name | +0.046 |
Tracy | +0.044 |
Neg logit contributions | |
no | -0.038 |
unatt | -0.035 |
jected | -0.033 |
fore | -0.033 |
course | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +5.34e-03 |
Pos logit contributions | |
til | +0.015 |
pret | +0.015 |
ucks | +0.015 |
Tracy | +0.014 |
enery | +0.013 |
Neg logit contributions | |
no | -0.008 |
vern | -0.006 |
fore | -0.006 |
Jerry | -0.006 |
never | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
ucks | +0.010 |
til | +0.010 |
pret | +0.009 |
name | +0.009 |
ora | +0.009 |
Neg logit contributions | |
no | -0.006 |
unatt | -0.006 |
jected | -0.005 |
fore | -0.005 |
iable | -0.005 |
Token | What |
Token ID | 2061 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
no | +0.026 |
unatt | +0.023 |
jected | +0.023 |
fore | +0.023 |
course | +0.022 |
Neg logit contributions | |
til | -0.027 |
ucks | -0.027 |
pret | -0.025 |
name | -0.023 |
Tracy | -0.022 |
Token | are |
Token ID | 389 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
til | +0.060 |
pret | +0.060 |
name | +0.060 |
ucks | +0.059 |
ours | +0.048 |
Neg logit contributions | |
unatt | -0.100 |
jected | -0.095 |
no | -0.093 |
fore | -0.090 |
Mic | -0.087 |
Token | nations |
Token ID | 7027 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
no | +0.048 |
unatt | +0.046 |
jected | +0.043 |
fore | +0.041 |
vern | +0.037 |
Neg logit contributions | |
til | -0.115 |
ucks | -0.114 |
pret | -0.110 |
name | -0.107 |
Tracy | -0.104 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
no | +0.195 |
unatt | +0.180 |
jected | +0.176 |
fore | +0.174 |
vern | +0.169 |
Neg logit contributions | |
til | -0.177 |
ucks | -0.167 |
pret | -0.160 |
name | -0.154 |
Tracy | -0.139 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
ucks | +0.083 |
til | +0.083 |
pret | +0.078 |
name | +0.074 |
Tracy | +0.072 |
Neg logit contributions | |
no | -0.052 |
unatt | -0.047 |
jected | -0.044 |
fore | -0.043 |
course | -0.041 |
Token | wonders |
Token ID | 19294 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
no | +0.061 |
jected | +0.056 |
Jerry | +0.056 |
fore | +0.056 |
course | +0.055 |
Neg logit contributions | |
ucks | -0.028 |
til | -0.021 |
enery | -0.020 |
Tracy | -0.019 |
pret | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
til | +0.016 |
ucks | +0.016 |
pret | +0.015 |
name | +0.015 |
Tracy | +0.014 |
Neg logit contributions | |
no | -0.009 |
unatt | -0.008 |
jected | -0.007 |
fore | -0.007 |
course | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-03 |
Pos logit contributions | |
ucks | +0.022 |
til | +0.022 |
pret | +0.021 |
name | +0.019 |
Tracy | +0.019 |
Neg logit contributions | |
no | -0.013 |
unatt | -0.010 |
Jerry | -0.010 |
fore | -0.010 |
jected | -0.010 |
Token | It |
Token ID | 1026 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
no | +0.007 |
unatt | +0.006 |
jected | +0.006 |
never | +0.006 |
course | +0.006 |
Neg logit contributions | |
til | -0.011 |
ucks | -0.011 |
pret | -0.010 |
name | -0.010 |
Tracy | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ucks | +0.026 |
til | +0.025 |
pret | +0.024 |
name | +0.023 |
Tracy | +0.023 |
Neg logit contributions | |
no | -0.011 |
unatt | -0.009 |
jected | -0.009 |
fore | -0.009 |
never | -0.008 |
Token | used |
Token ID | 973 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
no | +0.019 |
unatt | +0.018 |
jected | +0.017 |
fore | +0.016 |
course | +0.016 |
Neg logit contributions | |
til | -0.030 |
ucks | -0.029 |
pret | -0.029 |
name | -0.028 |
Tracy | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
til | +0.026 |
name | +0.026 |
ucks | +0.026 |
pret | +0.026 |
Tracy | +0.023 |
Neg logit contributions | |
unatt | -0.021 |
jected | -0.021 |
no | -0.021 |
Mic | -0.019 |
iable | -0.019 |
Token | keep |
Token ID | 1394 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
name | +0.016 |
til | +0.015 |
pret | +0.014 |
ucks | +0.014 |
smell | +0.014 |
Neg logit contributions | |
unatt | -0.022 |
jected | -0.022 |
no | -0.021 |
fore | -0.020 |
ross | -0.020 |
Token | papers |
Token ID | 9473 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
no | +0.006 |
unatt | +0.005 |
jected | +0.005 |
fore | +0.005 |
vern | +0.005 |
Neg logit contributions | |
til | -0.006 |
ucks | -0.006 |
pret | -0.006 |
name | -0.006 |
Tracy | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
course | +0.173 |
jected | +0.170 |
Fred | +0.170 |
no | +0.168 |
fore | +0.165 |
Neg logit contributions | |
name | -0.168 |
til | -0.166 |
ucks | -0.161 |
pret | -0.160 |
smell | -0.150 |
Token | ." |
Token ID | 526 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
ucks | +0.026 |
pret | +0.026 |
name | +0.026 |
til | +0.026 |
wonder | +0.024 |
Neg logit contributions | |
jected | -0.028 |
unatt | -0.025 |
ross | -0.024 |
iable | -0.023 |
vern | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
til | +0.004 |
ucks | +0.004 |
pret | +0.004 |
name | +0.003 |
Tracy | +0.003 |
Neg logit contributions | |
no | -0.003 |
unatt | -0.002 |
fore | -0.002 |
jected | -0.002 |
course | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
no | +0.025 |
unatt | +0.021 |
fore | +0.020 |
course | +0.020 |
jected | +0.020 |
Neg logit contributions | |
til | -0.043 |
ucks | -0.042 |
pret | -0.041 |
name | -0.038 |
Tracy | -0.037 |
Token | J |
Token ID | 41 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
no | +0.025 |
unatt | +0.023 |
jected | +0.021 |
fore | +0.021 |
course | +0.019 |
Neg logit contributions | |
ucks | -0.047 |
til | -0.045 |
pret | -0.043 |
name | -0.042 |
ora | -0.041 |
Token | However |
Token ID | 2102 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
no | +0.022 |
unatt | +0.018 |
Jerry | +0.017 |
jected | +0.017 |
fore | +0.017 |
Neg logit contributions | |
ucks | -0.032 |
til | -0.032 |
pret | -0.030 |
name | -0.028 |
Tracy | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
unatt | +0.014 |
jected | +0.014 |
fore | +0.013 |
vern | +0.012 |
iable | +0.012 |
Neg logit contributions | |
til | -0.034 |
pret | -0.033 |
ucks | -0.032 |
name | -0.031 |
Tracy | -0.030 |
Token | there |
Token ID | 612 |
Feature activation | +9.68e-04 |
Pos logit contributions | |
unatt | +0.033 |
no | +0.032 |
jected | +0.032 |
fore | +0.032 |
vern | +0.031 |
Neg logit contributions | |
til | -0.047 |
pret | -0.044 |
ucks | -0.044 |
name | -0.042 |
Tracy | -0.040 |
Token | were |
Token ID | 547 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
ucks | +0.002 |
til | +0.002 |
pret | +0.002 |
enery | +0.001 |
Tracy | +0.001 |
Neg logit contributions | |
no | -0.001 |
never | -0.001 |
fore | -0.001 |
course | -0.001 |
unatt | -0.001 |
Token | no |
Token ID | 645 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
unatt | +0.062 |
vern | +0.059 |
jected | +0.059 |
ross | +0.056 |
fore | +0.054 |
Neg logit contributions | |
til | -0.113 |
pret | -0.107 |
ucks | -0.107 |
name | -0.103 |
Tracy | -0.101 |
Token | bicycles |
Token ID | 35426 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
no | +0.090 |
unatt | +0.076 |
course | +0.069 |
Jerry | +0.069 |
fore | +0.068 |
Neg logit contributions | |
ucks | -0.125 |
til | -0.123 |
pret | -0.113 |
Tracy | -0.112 |
ora | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
fore | +0.151 |
jected | +0.149 |
no | +0.149 |
Mic | +0.146 |
vern | +0.145 |
Neg logit contributions | |
til | -0.195 |
ucks | -0.184 |
pret | -0.182 |
name | -0.175 |
smell | -0.167 |
Token | be |
Token ID | 307 |
Feature activation | -3.64e-03 |
Pos logit contributions | |
til | +0.006 |
ucks | +0.006 |
pret | +0.006 |
name | +0.006 |
smell | +0.005 |
Neg logit contributions | |
no | -0.007 |
jected | -0.007 |
unatt | -0.007 |
fore | -0.007 |
vern | -0.007 |
Token | found |
Token ID | 1043 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
no | +0.005 |
unatt | +0.005 |
jected | +0.005 |
course | +0.005 |
fore | +0.004 |
Neg logit contributions | |
til | -0.006 |
ucks | -0.005 |
pret | -0.005 |
name | -0.005 |
Tracy | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
jected | +0.029 |
Mic | +0.028 |
vern | +0.027 |
no | +0.027 |
Fred | +0.027 |
Neg logit contributions | |
ucks | -0.032 |
til | -0.032 |
pret | -0.031 |
name | -0.030 |
lands | -0.028 |
Token | Then |
Token ID | 3244 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
no | +0.039 |
unatt | +0.037 |
jected | +0.035 |
fore | +0.035 |
vern | +0.033 |
Neg logit contributions | |
til | -0.050 |
ucks | -0.050 |
pret | -0.047 |
name | -0.046 |
Tracy | -0.044 |
Token | giant |
Token ID | 6175 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
unatt | +0.017 |
jected | +0.017 |
gh | +0.016 |
vern | +0.016 |
no | +0.016 |
Neg logit contributions | |
ucks | -0.020 |
til | -0.019 |
name | -0.019 |
pret | -0.019 |
smell | -0.018 |
Token | ! |
Token ID | 0 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
no | +0.019 |
unatt | +0.019 |
jected | +0.019 |
fore | +0.018 |
vern | +0.018 |
Neg logit contributions | |
til | -0.037 |
ucks | -0.036 |
pret | -0.036 |
name | -0.033 |
Randy | -0.032 |
Token | You |
Token ID | 921 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
unatt | +0.008 |
no | +0.008 |
vern | +0.008 |
fore | +0.008 |
jected | +0.008 |
Neg logit contributions | |
ucks | -0.008 |
til | -0.008 |
pret | -0.007 |
name | -0.007 |
ours | -0.006 |
Token | are |
Token ID | 389 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
name | +0.002 |
til | +0.002 |
pret | +0.002 |
ucks | +0.002 |
smell | +0.002 |
Neg logit contributions | |
unatt | -0.003 |
ross | -0.002 |
gh | -0.002 |
vern | -0.002 |
side | -0.002 |
Token | under |
Token ID | 739 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
side | +0.051 |
unatt | +0.051 |
earned | +0.048 |
vern | +0.048 |
course | +0.046 |
Neg logit contributions | |
til | -0.066 |
pret | -0.062 |
name | -0.060 |
smell | -0.059 |
ucks | -0.053 |
Token | arrest |
Token ID | 3251 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
jected | +0.029 |
iable | +0.028 |
vern | +0.028 |
asure | +0.025 |
unatt | +0.024 |
Neg logit contributions | |
til | -0.046 |
pret | -0.043 |
lands | -0.043 |
ucks | -0.042 |
smell | -0.040 |
Token | ! |
Token ID | 0 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
no | +0.149 |
unatt | +0.145 |
jected | +0.141 |
vern | +0.139 |
fore | +0.135 |
Neg logit contributions | |
til | -0.200 |
ucks | -0.200 |
pret | -0.188 |
name | -0.178 |
smell | -0.164 |
Token | You |
Token ID | 921 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
unatt | +0.012 |
no | +0.012 |
vern | +0.011 |
jected | +0.011 |
fore | +0.011 |
Neg logit contributions | |
ucks | -0.011 |
til | -0.010 |
pret | -0.010 |
name | -0.010 |
Tracy | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
til | +0.004 |
pret | +0.004 |
ucks | +0.004 |
name | +0.004 |
smell | +0.003 |
Neg logit contributions | |
unatt | -0.004 |
ross | -0.003 |
gh | -0.003 |
no | -0.003 |
vern | -0.003 |
Token | 't |
Token ID | 470 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
til | +0.019 |
ucks | +0.019 |
pret | +0.018 |
name | +0.017 |
Tracy | +0.016 |
Neg logit contributions | |
no | -0.011 |
unatt | -0.010 |
jected | -0.010 |
fore | -0.010 |
course | -0.009 |
Token | take |
Token ID | 1011 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
no | +0.058 |
unatt | +0.056 |
fore | +0.054 |
jected | +0.054 |
vern | +0.052 |
Neg logit contributions | |
til | -0.045 |
ucks | -0.044 |
pret | -0.041 |
name | -0.040 |
smell | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
til | +0.050 |
ucks | +0.048 |
pret | +0.046 |
name | +0.045 |
Tracy | +0.042 |
Neg logit contributions | |
no | -0.036 |
unatt | -0.035 |
jected | -0.033 |
fore | -0.033 |
vern | -0.032 |
Token | asked |
Token ID | 1965 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
no | +0.038 |
unatt | +0.034 |
jected | +0.033 |
fore | +0.032 |
never | +0.032 |
Neg logit contributions | |
ucks | -0.037 |
til | -0.035 |
pret | -0.033 |
name | -0.031 |
Tracy | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
til | +0.087 |
ucks | +0.085 |
pret | +0.083 |
name | +0.081 |
Tracy | +0.077 |
Neg logit contributions | |
no | -0.047 |
jected | -0.047 |
unatt | -0.047 |
fore | -0.043 |
course | -0.041 |
Token | " |
Token ID | 366 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
no | +0.040 |
unatt | +0.039 |
jected | +0.037 |
fore | +0.036 |
course | +0.035 |
Neg logit contributions | |
til | -0.049 |
ucks | -0.047 |
pret | -0.045 |
name | -0.043 |
Tracy | -0.041 |
Token | What |
Token ID | 2061 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
no | +0.040 |
unatt | +0.037 |
jected | +0.035 |
fore | +0.035 |
course | +0.034 |
Neg logit contributions | |
til | -0.031 |
ucks | -0.030 |
pret | -0.028 |
name | -0.026 |
Tracy | -0.025 |
Token | papers |
Token ID | 9473 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
name | +0.060 |
pret | +0.059 |
til | +0.057 |
ucks | +0.056 |
smell | +0.050 |
Neg logit contributions | |
unatt | -0.067 |
jected | -0.063 |
fore | -0.059 |
no | -0.059 |
ross | -0.058 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
no | +0.195 |
unatt | +0.183 |
jected | +0.179 |
fore | +0.176 |
vern | +0.172 |
Neg logit contributions | |
til | -0.160 |
ucks | -0.153 |
pret | -0.148 |
name | -0.145 |
smell | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
til | +0.036 |
ucks | +0.036 |
pret | +0.033 |
name | +0.032 |
Tracy | +0.031 |
Neg logit contributions | |
no | -0.028 |
unatt | -0.026 |
jected | -0.024 |
fore | -0.024 |
course | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
no | +0.033 |
unatt | +0.031 |
jected | +0.029 |
fore | +0.028 |
course | +0.027 |
Neg logit contributions | |
ucks | -0.041 |
til | -0.040 |
pret | -0.038 |
name | -0.037 |
Tracy | -0.035 |
Token | M |
Token ID | 44 |
Feature activation | +6.24e-03 |
Pos logit contributions | |
unatt | +0.025 |
no | +0.024 |
jected | +0.021 |
course | +0.020 |
fore | +0.019 |
Neg logit contributions | |
ucks | -0.053 |
name | -0.050 |
til | -0.049 |
ora | -0.047 |
pret | -0.046 |
Token | um |
Token ID | 388 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
ucks | +0.011 |
til | +0.011 |
name | +0.010 |
ora | +0.010 |
pret | +0.010 |
Neg logit contributions | |
no | -0.008 |
unatt | -0.007 |
jected | -0.007 |
fore | -0.006 |
Jerry | -0.006 |
Token | loved |
Token ID | 6151 |
Feature activation | -8.59e-03 |
Pos logit contributions | |
ucks | +0.014 |
til | +0.013 |
name | +0.012 |
Tracy | +0.012 |
pret | +0.012 |
Neg logit contributions | |
no | -0.009 |
never | -0.007 |
unatt | -0.007 |
jected | -0.006 |
fore | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
no | +0.009 |
unatt | +0.008 |
jected | +0.007 |
fore | +0.007 |
course | +0.007 |
Neg logit contributions | |
til | -0.017 |
ucks | -0.017 |
pret | -0.016 |
name | -0.015 |
Tracy | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
unatt | +0.014 |
no | +0.014 |
jected | +0.014 |
fore | +0.014 |
vern | +0.013 |
Neg logit contributions | |
til | -0.020 |
pret | -0.019 |
ucks | -0.019 |
name | -0.018 |
Tracy | -0.017 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
no | +0.014 |
never | +0.011 |
Jerry | +0.010 |
unatt | +0.010 |
course | +0.010 |
Neg logit contributions | |
ucks | -0.024 |
til | -0.023 |
pret | -0.020 |
name | -0.020 |
ora | -0.020 |
Token | making |
Token ID | 1642 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
til | +0.009 |
ucks | +0.009 |
pret | +0.008 |
name | +0.008 |
Tracy | +0.008 |
Neg logit contributions | |
no | -0.007 |
unatt | -0.006 |
jected | -0.006 |
fore | -0.006 |
vern | -0.005 |
Token | towers |
Token ID | 18028 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ucks | +0.049 |
til | +0.048 |
ora | +0.043 |
pret | +0.043 |
Tracy | +0.041 |
Neg logit contributions | |
no | -0.032 |
Jerry | -0.025 |
course | -0.025 |
much | -0.025 |
iable | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
no | +0.142 |
unatt | +0.136 |
jected | +0.133 |
fore | +0.128 |
course | +0.123 |
Neg logit contributions | |
til | -0.211 |
ucks | -0.210 |
pret | -0.198 |
name | -0.193 |
Tracy | -0.180 |
Token | He |
Token ID | 679 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
no | +0.035 |
unatt | +0.029 |
Jerry | +0.028 |
fore | +0.028 |
course | +0.028 |
Neg logit contributions | |
til | -0.051 |
ucks | -0.051 |
pret | -0.048 |
Tracy | -0.044 |
name | -0.044 |
Token | worked |
Token ID | 3111 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
ucks | +0.010 |
til | +0.009 |
name | +0.008 |
Tracy | +0.008 |
pret | +0.008 |
Neg logit contributions | |
no | -0.006 |
never | -0.005 |
unatt | -0.005 |
fore | -0.005 |
jected | -0.005 |
Token | carefully |
Token ID | 7773 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
til | +0.006 |
ucks | +0.006 |
pret | +0.006 |
name | +0.006 |
Tracy | +0.005 |
Neg logit contributions | |
no | -0.004 |
unatt | -0.003 |
jected | -0.003 |
fore | -0.003 |
course | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
no | +0.023 |
unatt | +0.022 |
jected | +0.021 |
vern | +0.020 |
fore | +0.020 |
Neg logit contributions | |
til | -0.031 |
ucks | -0.030 |
pret | -0.030 |
name | -0.028 |
Tracy | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
no | +0.026 |
unatt | +0.024 |
jected | +0.023 |
fore | +0.022 |
iable | +0.022 |
Neg logit contributions | |
til | -0.045 |
ucks | -0.044 |
pret | -0.042 |
name | -0.041 |
Tracy | -0.039 |
Token | He |
Token ID | 679 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
no | +0.024 |
Jerry | +0.020 |
unatt | +0.018 |
never | +0.018 |
Once | +0.018 |
Neg logit contributions | |
til | -0.050 |
ucks | -0.049 |
pret | -0.047 |
Tracy | -0.043 |
ora | -0.043 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
no | +0.002 |
never | +0.001 |
fore | +0.001 |
unatt | +0.001 |
gone | +0.001 |
Neg logit contributions | |
ucks | -0.003 |
til | -0.002 |
name | -0.002 |
enery | -0.002 |
ours | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
no | +0.013 |
unatt | +0.011 |
jected | +0.011 |
fore | +0.010 |
course | +0.010 |
Neg logit contributions | |
ucks | -0.026 |
til | -0.026 |
pret | -0.025 |
name | -0.023 |
Tracy | -0.023 |
Token | make |
Token ID | 787 |
Feature activation | +8.44e-03 |
Pos logit contributions | |
no | +0.025 |
unatt | +0.023 |
jected | +0.022 |
fore | +0.022 |
course | +0.021 |
Neg logit contributions | |
ucks | -0.020 |
til | -0.020 |
pret | -0.018 |
name | -0.017 |
Tracy | -0.016 |
Token | towers |
Token ID | 18028 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ucks | +0.018 |
til | +0.018 |
ora | +0.017 |
suit | +0.016 |
pret | +0.016 |
Neg logit contributions | |
no | -0.007 |
much | -0.005 |
his | -0.004 |
gh | -0.004 |
Jerry | -0.004 |
Token | out |
Token ID | 503 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
jected | +0.166 |
unatt | +0.163 |
no | +0.163 |
fore | +0.158 |
Mic | +0.154 |
Neg logit contributions | |
til | -0.181 |
ucks | -0.179 |
pret | -0.167 |
name | -0.166 |
smell | -0.154 |
Token | of |
Token ID | 286 |
Feature activation | -4.71e-04 |
Pos logit contributions | |
jected | +0.012 |
Mic | +0.012 |
vern | +0.012 |
Jerry | +0.011 |
Fred | +0.011 |
Neg logit contributions | |
ucks | -0.013 |
til | -0.013 |
pret | -0.012 |
lands | -0.011 |
name | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
jected | +0.001 |
ross | +0.001 |
vern | +0.001 |
unatt | +0.001 |
no | +0.001 |
Neg logit contributions | |
til | -0.001 |
pret | -0.001 |
ucks | -0.001 |
smell | -0.001 |
name | -0.001 |
Token | toy |
Token ID | 13373 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
no | +0.038 |
jected | +0.035 |
unatt | +0.035 |
iable | +0.033 |
Jerry | +0.033 |
Neg logit contributions | |
til | -0.033 |
ucks | -0.032 |
pret | -0.031 |
name | -0.030 |
Tracy | -0.026 |
Token | blocks |
Token ID | 7021 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
jected | +0.050 |
vern | +0.050 |
no | +0.048 |
ross | +0.048 |
fore | +0.048 |
Neg logit contributions | |
pret | -0.041 |
til | -0.039 |
ucks | -0.039 |
name | -0.036 |
lands | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -5.44e-03 |
Pos logit contributions | |
no | +0.004 |
unatt | +0.004 |
jected | +0.004 |
fore | +0.003 |
ross | +0.003 |
Neg logit contributions | |
til | -0.006 |
ucks | -0.006 |
pret | -0.006 |
name | -0.006 |
Tracy | -0.005 |
Token | know |
Token ID | 760 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
no | +0.009 |
unatt | +0.009 |
jected | +0.009 |
fore | +0.008 |
course | +0.008 |
Neg logit contributions | |
til | -0.007 |
ucks | -0.007 |
pret | -0.006 |
name | -0.006 |
Tracy | -0.005 |
Token | more |
Token ID | 517 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
jected | +0.030 |
unatt | +0.028 |
Mic | +0.028 |
ross | +0.027 |
P | +0.027 |
Neg logit contributions | |
til | -0.029 |
ucks | -0.027 |
pret | -0.027 |
name | -0.026 |
Tracy | -0.024 |
Token | about |
Token ID | 546 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
no | +0.035 |
unatt | +0.034 |
jected | +0.033 |
fore | +0.031 |
iable | +0.030 |
Neg logit contributions | |
til | -0.040 |
ucks | -0.039 |
pret | -0.037 |
name | -0.036 |
Tracy | -0.033 |
Token | other |
Token ID | 584 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
til | +0.039 |
ucks | +0.037 |
pret | +0.036 |
name | +0.035 |
Tracy | +0.033 |
Neg logit contributions | |
unatt | -0.035 |
jected | -0.035 |
no | -0.035 |
fore | -0.031 |
vern | -0.031 |
Token | nations |
Token ID | 7027 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
no | +0.118 |
jected | +0.118 |
unatt | +0.116 |
Mic | +0.108 |
fore | +0.108 |
Neg logit contributions | |
ucks | -0.099 |
til | -0.098 |
pret | -0.094 |
name | -0.091 |
guesses | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
jected | +0.143 |
unatt | +0.142 |
no | +0.139 |
Mic | +0.139 |
ross | +0.132 |
Neg logit contributions | |
til | -0.199 |
pret | -0.187 |
name | -0.187 |
ucks | -0.184 |
Tracy | -0.170 |
Token | They |
Token ID | 1119 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
til | +0.002 |
ucks | +0.002 |
pret | +0.002 |
enery | +0.001 |
glimps | +0.001 |
Neg logit contributions | |
no | -0.001 |
Jerry | -0.001 |
fore | -0.001 |
Once | -0.001 |
unatt | -0.001 |
Token | ask |
Token ID | 1265 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
ucks | +0.024 |
til | +0.022 |
pret | +0.020 |
Tracy | +0.018 |
ours | +0.018 |
Neg logit contributions | |
no | -0.032 |
never | -0.028 |
course | -0.027 |
fore | -0.027 |
jected | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
til | +0.097 |
ucks | +0.096 |
pret | +0.090 |
name | +0.088 |
Tracy | +0.084 |
Neg logit contributions | |
unatt | -0.094 |
no | -0.094 |
jected | -0.093 |
fore | -0.086 |
iable | -0.084 |
Token | teacher |
Token ID | 4701 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
unatt | +0.032 |
no | +0.031 |
jected | +0.030 |
gh | +0.029 |
iable | +0.028 |
Neg logit contributions | |
name | -0.031 |
ucks | -0.030 |
til | -0.029 |
pret | -0.028 |
ora | -0.027 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
ucks | +0.047 |
til | +0.047 |
pret | +0.044 |
name | +0.043 |
Tracy | +0.041 |
Neg logit contributions | |
no | -0.034 |
unatt | -0.031 |
jected | -0.030 |
fore | -0.030 |
course | -0.028 |
Token | s |
Token ID | 82 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
unatt | +0.039 |
no | +0.039 |
jected | +0.039 |
fore | +0.039 |
Mic | +0.037 |
Neg logit contributions | |
ucks | -0.033 |
til | -0.027 |
name | -0.026 |
ora | -0.026 |
oodle | -0.026 |
Token | pretend |
Token ID | 16614 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
no | +0.060 |
unatt | +0.056 |
jected | +0.054 |
fore | +0.053 |
course | +0.051 |
Neg logit contributions | |
til | -0.050 |
ucks | -0.050 |
pret | -0.046 |
name | -0.044 |
Tracy | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
no | +0.002 |
unatt | +0.002 |
jected | +0.002 |
fore | +0.002 |
vern | +0.002 |
Neg logit contributions | |
til | -0.004 |
ucks | -0.004 |
pret | -0.004 |
name | -0.004 |
Tracy | -0.004 |
Token | be |
Token ID | 307 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
no | +0.020 |
unatt | +0.019 |
jected | +0.018 |
fore | +0.018 |
course | +0.017 |
Neg logit contributions | |
til | -0.017 |
ucks | -0.017 |
pret | -0.016 |
name | -0.015 |
Tracy | -0.014 |
Token | aer |
Token ID | 9551 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
no | +0.016 |
unatt | +0.015 |
jected | +0.014 |
fore | +0.013 |
course | +0.013 |
Neg logit contributions | |
til | -0.025 |
ucks | -0.025 |
pret | -0.023 |
name | -0.022 |
Tracy | -0.022 |
Token | opl |
Token ID | 20106 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
no | +0.150 |
unatt | +0.116 |
fore | +0.114 |
Jerry | +0.110 |
never | +0.105 |
Neg logit contributions | |
ucks | -0.226 |
til | -0.222 |
rig | -0.192 |
pret | -0.190 |
ora | -0.181 |
Token | anes |
Token ID | 7305 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
no | +0.131 |
unatt | +0.119 |
fore | +0.118 |
never | +0.111 |
gone | +0.107 |
Neg logit contributions | |
ucks | -0.147 |
til | -0.126 |
name | -0.115 |
pret | -0.113 |
Tracy | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
no | +0.063 |
unatt | +0.059 |
fore | +0.058 |
jected | +0.056 |
vern | +0.054 |
Neg logit contributions | |
til | -0.090 |
ucks | -0.086 |
pret | -0.083 |
name | -0.079 |
Tracy | -0.075 |
Token | â |
Token ID | 22940 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.028 |
fore | +0.026 |
jected | +0.026 |
course | +0.026 |
Neg logit contributions | |
ucks | -0.039 |
til | -0.039 |
pret | -0.036 |
name | -0.033 |
Tracy | -0.033 |
Token | € |
Token ID | 26391 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
til | +0.017 |
ucks | +0.017 |
pret | +0.016 |
name | +0.015 |
Tracy | +0.014 |
Neg logit contributions | |
no | -0.016 |
unatt | -0.014 |
fore | -0.014 |
jected | -0.013 |
vern | -0.013 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.32e-03 |
Pos logit contributions | |
no | +0.035 |
unatt | +0.029 |
fore | +0.028 |
never | +0.027 |
Jerry | +0.027 |
Neg logit contributions | |
ucks | -0.052 |
til | -0.051 |
pret | -0.048 |
name | -0.044 |
Tracy | -0.043 |
Token | my |
Token ID | 1820 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
no | +0.011 |
unatt | +0.010 |
jected | +0.010 |
fore | +0.009 |
vern | +0.009 |
Neg logit contributions | |
ucks | -0.014 |
til | -0.014 |
pret | -0.013 |
name | -0.013 |
Tracy | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
til | +0.033 |
ucks | +0.033 |
pret | +0.031 |
name | +0.030 |
Tracy | +0.029 |
Neg logit contributions | |
no | -0.023 |
unatt | -0.021 |
jected | -0.021 |
fore | -0.020 |
course | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
til | +0.012 |
ucks | +0.011 |
pret | +0.011 |
name | +0.011 |
Tracy | +0.010 |
Neg logit contributions | |
no | -0.011 |
jected | -0.011 |
unatt | -0.011 |
fore | -0.010 |
vern | -0.010 |
Token | Are |
Token ID | 8491 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
no | +0.003 |
unatt | +0.003 |
jected | +0.003 |
fore | +0.003 |
course | +0.003 |
Neg logit contributions | |
til | -0.003 |
ucks | -0.002 |
pret | -0.002 |
name | -0.002 |
Tracy | -0.002 |
Token | grapes |
Token ID | 36656 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
til | +0.060 |
pret | +0.057 |
ucks | +0.057 |
name | +0.055 |
Tracy | +0.054 |
Neg logit contributions | |
unatt | -0.024 |
jected | -0.022 |
no | -0.022 |
fore | -0.021 |
vern | -0.021 |
Token | really |
Token ID | 1107 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
jected | +0.139 |
vern | +0.123 |
fore | +0.122 |
unatt | +0.122 |
His | +0.120 |
Neg logit contributions | |
name | -0.201 |
smell | -0.200 |
til | -0.195 |
pret | -0.179 |
ucks | -0.171 |
Token | real |
Token ID | 1103 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
til | +0.014 |
ucks | +0.014 |
pret | +0.013 |
name | +0.013 |
Tracy | +0.012 |
Neg logit contributions | |
no | -0.011 |
unatt | -0.010 |
jected | -0.010 |
fore | -0.009 |
course | -0.009 |
Token | ?". |
Token ID | 43634 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
no | +0.060 |
jected | +0.060 |
unatt | +0.058 |
fore | +0.054 |
vern | +0.054 |
Neg logit contributions | |
til | -0.093 |
ucks | -0.092 |
name | -0.090 |
pret | -0.089 |
smell | -0.082 |
Token | Her |
Token ID | 2332 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
til | +0.040 |
ucks | +0.040 |
pret | +0.037 |
name | +0.037 |
Tracy | +0.035 |
Neg logit contributions | |
no | -0.024 |
unatt | -0.022 |
jected | -0.021 |
fore | -0.020 |
vern | -0.019 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ucks | +0.043 |
til | +0.042 |
pret | +0.040 |
ora | +0.037 |
Tracy | +0.037 |
Neg logit contributions | |
no | -0.024 |
unatt | -0.018 |
fore | -0.018 |
never | -0.016 |
Jerry | -0.016 |
Token | ! |
Token ID | 0 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
unatt | +0.043 |
jected | +0.042 |
no | +0.042 |
fore | +0.038 |
Mic | +0.038 |
Neg logit contributions | |
til | -0.067 |
pret | -0.063 |
ucks | -0.063 |
name | -0.059 |
Tracy | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
no | +0.039 |
unatt | +0.036 |
jected | +0.034 |
fore | +0.033 |
course | +0.032 |
Neg logit contributions | |
til | -0.049 |
ucks | -0.049 |
pret | -0.046 |
name | -0.044 |
Tracy | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
no | +0.038 |
unatt | +0.035 |
jected | +0.033 |
fore | +0.033 |
course | +0.031 |
Neg logit contributions | |
ucks | -0.051 |
til | -0.051 |
pret | -0.047 |
name | -0.045 |
Tracy | -0.043 |
Token | " |
Token ID | 1 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
unatt | +0.038 |
no | +0.037 |
asure | +0.032 |
fore | +0.032 |
iable | +0.031 |
Neg logit contributions | |
ucks | -0.048 |
til | -0.046 |
Tracy | -0.043 |
name | -0.043 |
pret | -0.042 |
Token | H |
Token ID | 39 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
no | +0.057 |
unatt | +0.052 |
jected | +0.050 |
fore | +0.049 |
course | +0.047 |
Neg logit contributions | |
til | -0.074 |
ucks | -0.074 |
pret | -0.069 |
name | -0.066 |
Tracy | -0.063 |
Token | oor |
Token ID | 2675 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ucks | +0.031 |
til | +0.030 |
pret | +0.028 |
name | +0.027 |
ora | +0.026 |
Neg logit contributions | |
no | -0.024 |
unatt | -0.023 |
fore | -0.021 |
jected | -0.020 |
course | -0.020 |
Token | ay |
Token ID | 323 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
no | +0.135 |
unatt | +0.119 |
fore | +0.108 |
never | +0.103 |
jected | +0.103 |
Neg logit contributions | |
ucks | -0.223 |
til | -0.214 |
name | -0.201 |
pret | -0.200 |
Tracy | -0.188 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
unatt | +0.075 |
no | +0.070 |
fore | +0.067 |
Mic | +0.065 |
vern | +0.064 |
Neg logit contributions | |
til | -0.082 |
ucks | -0.080 |
pret | -0.077 |
name | -0.072 |
Tracy | -0.066 |
Token | shouted |
Token ID | 17293 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
no | +0.017 |
unatt | +0.016 |
jected | +0.015 |
fore | +0.015 |
course | +0.015 |
Neg logit contributions | |
ucks | -0.016 |
til | -0.016 |
pret | -0.015 |
name | -0.013 |
Tracy | -0.013 |
Token | Ted |
Token ID | 11396 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
no | +0.020 |
unatt | +0.017 |
jected | +0.016 |
fore | +0.016 |
Jerry | +0.015 |
Neg logit contributions | |
ucks | -0.032 |
til | -0.031 |
pret | -0.029 |
name | -0.028 |
Tracy | -0.027 |
Token | as |
Token ID | 355 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
ucks | +0.007 |
til | +0.007 |
pret | +0.006 |
name | +0.006 |
Tracy | +0.006 |
Neg logit contributions | |
no | -0.004 |
unatt | -0.003 |
jected | -0.003 |
fore | -0.003 |
course | -0.003 |
Token | Elsa |
Token ID | 49050 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
no | +0.014 |
unatt | +0.013 |
jected | +0.012 |
fore | +0.012 |
iable | +0.010 |
Neg logit contributions | |
ucks | -0.031 |
til | -0.030 |
pret | -0.029 |
name | -0.028 |
Tracy | -0.027 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
ucks | +0.034 |
til | +0.032 |
pret | +0.030 |
name | +0.029 |
Tracy | +0.028 |
Neg logit contributions | |
no | -0.028 |
fore | -0.025 |
unatt | -0.024 |
jected | -0.024 |
never | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
no | +0.035 |
unatt | +0.034 |
jected | +0.033 |
course | +0.032 |
fore | +0.032 |
Neg logit contributions | |
til | -0.049 |
ucks | -0.047 |
name | -0.044 |
pret | -0.044 |
Tracy | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
til | +0.011 |
ucks | +0.011 |
pret | +0.010 |
name | +0.010 |
Tracy | +0.009 |
Neg logit contributions | |
no | -0.008 |
unatt | -0.007 |
jected | -0.007 |
fore | -0.007 |
course | -0.007 |
Token | H |
Token ID | 39 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
no | +0.004 |
unatt | +0.004 |
fore | +0.004 |
jected | +0.004 |
course | +0.004 |
Neg logit contributions | |
ucks | -0.006 |
til | -0.006 |
pret | -0.005 |
name | -0.005 |
Tracy | -0.005 |
Token | oor |
Token ID | 2675 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ucks | +0.020 |
til | +0.019 |
pret | +0.017 |
ora | +0.017 |
name | +0.017 |
Neg logit contributions | |
no | -0.020 |
unatt | -0.018 |
fore | -0.018 |
jected | -0.017 |
Jerry | -0.016 |
Token | ay |
Token ID | 323 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
no | +0.136 |
unatt | +0.117 |
fore | +0.107 |
never | +0.104 |
jected | +0.103 |
Neg logit contributions | |
ucks | -0.224 |
til | -0.215 |
name | -0.202 |
pret | -0.199 |
ora | -0.190 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
unatt | +0.064 |
no | +0.058 |
Mic | +0.057 |
fore | +0.055 |
Fred | +0.054 |
Neg logit contributions | |
til | -0.080 |
ucks | -0.078 |
pret | -0.077 |
name | -0.072 |
guesses | -0.065 |
Token | we |
Token ID | 356 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
no | +0.019 |
unatt | +0.018 |
jected | +0.018 |
fore | +0.017 |
vern | +0.016 |
Neg logit contributions | |
til | -0.028 |
ucks | -0.028 |
pret | -0.027 |
name | -0.026 |
Tracy | -0.025 |
Token | took |
Token ID | 1718 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
no | +0.064 |
unatt | +0.056 |
jected | +0.054 |
fore | +0.053 |
course | +0.052 |
Neg logit contributions | |
ucks | -0.090 |
til | -0.089 |
pret | -0.083 |
name | -0.076 |
Tracy | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
unatt | +0.021 |
no | +0.021 |
jected | +0.020 |
ross | +0.019 |
vern | +0.019 |
Neg logit contributions | |
ucks | -0.023 |
til | -0.023 |
pret | -0.022 |
name | -0.022 |
Tracy | -0.020 |
Token | went |
Token ID | 1816 |
Feature activation | -4.82e-03 |
Pos logit contributions | |
ucks | +0.037 |
til | +0.036 |
pret | +0.032 |
name | +0.032 |
Tracy | +0.032 |
Neg logit contributions | |
no | -0.016 |
unatt | -0.014 |
never | -0.014 |
jected | -0.013 |
fore | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
no | +0.004 |
unatt | +0.003 |
jected | +0.003 |
fore | +0.003 |
vern | +0.003 |
Neg logit contributions | |
til | -0.010 |
ucks | -0.010 |
pret | -0.010 |
name | -0.010 |
Tracy | -0.009 |
Token | searched |
Token ID | 16499 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
no | +0.002 |
never | +0.002 |
unatt | +0.002 |
fore | +0.002 |
jected | +0.002 |
Neg logit contributions | |
ucks | -0.004 |
til | -0.004 |
name | -0.003 |
Tracy | -0.003 |
rig | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
til | +0.083 |
ucks | +0.082 |
pret | +0.078 |
name | +0.075 |
Tracy | +0.072 |
Neg logit contributions | |
no | -0.051 |
unatt | -0.046 |
jected | -0.045 |
fore | -0.043 |
course | -0.040 |
Token | or |
Token ID | 393 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
jected | +0.010 |
no | +0.009 |
unatt | +0.009 |
ross | +0.009 |
iable | +0.008 |
Neg logit contributions | |
til | -0.009 |
pret | -0.008 |
ucks | -0.008 |
name | -0.008 |
smell | -0.007 |
Token | nam |
Token ID | 7402 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
no | +0.040 |
unatt | +0.036 |
jected | +0.033 |
fore | +0.033 |
course | +0.031 |
Neg logit contributions | |
ucks | -0.076 |
til | -0.075 |
pret | -0.071 |
name | -0.068 |
Tracy | -0.066 |
Token | ents |
Token ID | 658 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
no | +0.146 |
unatt | +0.134 |
fore | +0.131 |
jected | +0.126 |
course | +0.126 |
Neg logit contributions | |
ucks | -0.206 |
til | -0.198 |
pret | -0.181 |
name | -0.178 |
Tracy | -0.172 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
jected | +0.073 |
Mic | +0.073 |
no | +0.066 |
fore | +0.066 |
P | +0.066 |
Neg logit contributions | |
til | -0.084 |
pret | -0.078 |
ucks | -0.076 |
name | -0.073 |
smell | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
no | +0.016 |
unatt | +0.015 |
jected | +0.015 |
fore | +0.014 |
vern | +0.014 |
Neg logit contributions | |
til | -0.020 |
ucks | -0.020 |
pret | -0.019 |
name | -0.018 |
Tracy | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -4.03e-03 |
Pos logit contributions | |
no | +0.027 |
unatt | +0.026 |
jected | +0.025 |
fore | +0.024 |
vern | +0.024 |
Neg logit contributions | |
til | -0.039 |
ucks | -0.037 |
pret | -0.037 |
name | -0.034 |
Tracy | -0.034 |
Token | more |
Token ID | 517 |
Feature activation | -7.58e-03 |
Pos logit contributions | |
jected | +0.006 |
vern | +0.006 |
ful | +0.006 |
no | +0.006 |
ross | +0.006 |
Neg logit contributions | |
til | -0.005 |
name | -0.005 |
pret | -0.005 |
smell | -0.005 |
ucks | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
no | +0.009 |
unatt | +0.008 |
jected | +0.008 |
fore | +0.008 |
iable | +0.007 |
Neg logit contributions | |
til | -0.012 |
ucks | -0.012 |
pret | -0.012 |
name | -0.011 |
Tracy | -0.011 |
Token | perfect |
Token ID | 2818 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
no | +0.022 |
unatt | +0.020 |
fore | +0.019 |
jected | +0.019 |
course | +0.019 |
Neg logit contributions | |
ucks | -0.028 |
til | -0.027 |
pret | -0.025 |
name | -0.024 |
Tracy | -0.023 |
Token | treasure |
Token ID | 14068 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
til | +0.022 |
ucks | +0.022 |
pret | +0.021 |
name | +0.020 |
Tracy | +0.019 |
Neg logit contributions | |
no | -0.020 |
unatt | -0.019 |
jected | -0.018 |
fore | -0.017 |
course | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
no | +0.048 |
jected | +0.047 |
unatt | +0.045 |
Mic | +0.044 |
fore | +0.043 |
Neg logit contributions | |
til | -0.063 |
pret | -0.061 |
ucks | -0.060 |
name | -0.059 |
Tracy | -0.056 |
Token | After |
Token ID | 2293 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
no | +0.028 |
unatt | +0.024 |
jected | +0.023 |
fore | +0.023 |
Jerry | +0.023 |
Neg logit contributions | |
til | -0.042 |
ucks | -0.042 |
pret | -0.039 |
name | -0.036 |
ours | -0.035 |
Token | days |
Token ID | 1528 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
unatt | +0.007 |
jected | +0.007 |
no | +0.007 |
iable | +0.007 |
vern | +0.006 |
Neg logit contributions | |
til | -0.010 |
pret | -0.010 |
ucks | -0.009 |
Tracy | -0.009 |
name | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
no | +0.089 |
unatt | +0.084 |
jected | +0.078 |
fore | +0.071 |
vern | +0.070 |
Neg logit contributions | |
til | -0.253 |
ucks | -0.246 |
pret | -0.241 |
Tracy | -0.229 |
name | -0.226 |
Token | searching |
Token ID | 10342 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
no | +0.037 |
unatt | +0.034 |
jected | +0.033 |
fore | +0.032 |
iable | +0.030 |
Neg logit contributions | |
til | -0.043 |
ucks | -0.042 |
pret | -0.040 |
name | -0.037 |
Tracy | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
til | +0.056 |
ucks | +0.054 |
pret | +0.053 |
name | +0.051 |
Tracy | +0.050 |
Neg logit contributions | |
no | -0.029 |
jected | -0.027 |
unatt | -0.027 |
fore | -0.025 |
asure | -0.024 |
Token | she |
Token ID | 673 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
no | +0.037 |
unatt | +0.032 |
fore | +0.030 |
jected | +0.029 |
Jerry | +0.029 |
Neg logit contributions | |
ucks | -0.057 |
til | -0.055 |
pret | -0.052 |
name | -0.049 |
ours | -0.047 |
Token | found |
Token ID | 1043 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
no | +0.037 |
never | +0.031 |
unatt | +0.031 |
fore | +0.031 |
jected | +0.030 |
Neg logit contributions | |
ucks | -0.051 |
til | -0.048 |
pret | -0.045 |
name | -0.043 |
Tracy | -0.042 |
Token | up |
Token ID | 510 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
no | +0.035 |
Jerry | +0.032 |
unatt | +0.030 |
iable | +0.030 |
never | +0.030 |
Neg logit contributions | |
ucks | -0.028 |
til | -0.026 |
pret | -0.025 |
Tracy | -0.021 |
ora | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
til | +0.065 |
ucks | +0.062 |
pret | +0.061 |
name | +0.058 |
Tracy | +0.055 |
Neg logit contributions | |
no | -0.039 |
jected | -0.037 |
unatt | -0.036 |
fore | -0.034 |
Mic | -0.032 |
Token | Finally |
Token ID | 9461 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
no | +0.036 |
unatt | +0.033 |
jected | +0.031 |
fore | +0.031 |
course | +0.030 |
Neg logit contributions | |
til | -0.047 |
ucks | -0.047 |
pret | -0.044 |
name | -0.041 |
Tracy | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
unatt | +0.017 |
jected | +0.017 |
Mic | +0.016 |
vern | +0.016 |
asure | +0.015 |
Neg logit contributions | |
til | -0.024 |
pret | -0.023 |
Tracy | -0.022 |
name | -0.022 |
Randy | -0.021 |
Token | after |
Token ID | 706 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
no | +0.049 |
unatt | +0.046 |
jected | +0.045 |
fore | +0.044 |
vern | +0.042 |
Neg logit contributions | |
til | -0.069 |
ucks | -0.067 |
pret | -0.064 |
name | -0.061 |
Tracy | -0.060 |
Token | days |
Token ID | 1528 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
no | +0.071 |
unatt | +0.067 |
jected | +0.064 |
fore | +0.061 |
vern | +0.059 |
Neg logit contributions | |
til | -0.110 |
ucks | -0.108 |
pret | -0.104 |
name | -0.098 |
Tracy | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
no | +0.098 |
unatt | +0.096 |
jected | +0.094 |
vern | +0.090 |
fore | +0.084 |
Neg logit contributions | |
til | -0.236 |
ucks | -0.230 |
pret | -0.225 |
name | -0.211 |
Tracy | -0.211 |
Token | days |
Token ID | 1528 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
no | +0.035 |
unatt | +0.033 |
jected | +0.032 |
fore | +0.030 |
vern | +0.030 |
Neg logit contributions | |
til | -0.047 |
ucks | -0.046 |
pret | -0.044 |
name | -0.042 |
Tracy | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
no | +0.090 |
unatt | +0.086 |
jected | +0.082 |
vern | +0.078 |
fore | +0.077 |
Neg logit contributions | |
til | -0.187 |
ucks | -0.183 |
pret | -0.178 |
name | -0.167 |
Tracy | -0.166 |
Token | walking |
Token ID | 6155 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
no | +0.022 |
unatt | +0.019 |
fore | +0.018 |
jected | +0.018 |
course | +0.018 |
Neg logit contributions | |
ucks | -0.030 |
til | -0.030 |
pret | -0.028 |
name | -0.027 |
Tracy | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
til | +0.068 |
ucks | +0.067 |
name | +0.063 |
pret | +0.062 |
Tracy | +0.060 |
Neg logit contributions | |
no | -0.049 |
unatt | -0.048 |
jected | -0.047 |
fore | -0.046 |
vern | -0.044 |
Token | flew |
Token ID | 13112 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
no | +0.019 |
unatt | +0.017 |
jected | +0.016 |
fore | +0.016 |
course | +0.015 |
Neg logit contributions | |
til | -0.023 |
ucks | -0.023 |
pret | -0.022 |
name | -0.021 |
Tracy | -0.020 |
Token | away |
Token ID | 1497 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
til | +0.022 |
ucks | +0.021 |
pret | +0.020 |
name | +0.019 |
Tracy | +0.019 |
Neg logit contributions | |
no | -0.015 |
unatt | -0.014 |
jected | -0.013 |
fore | -0.013 |
course | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -8.09e-03 |
Pos logit contributions | |
no | +0.036 |
jected | +0.035 |
unatt | +0.035 |
Mic | +0.034 |
course | +0.033 |
Neg logit contributions | |
til | -0.054 |
ucks | -0.049 |
pret | -0.048 |
name | -0.047 |
Tracy | -0.045 |
Token | " |
Token ID | 366 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
no | +0.010 |
unatt | +0.009 |
jected | +0.009 |
fore | +0.009 |
course | +0.008 |
Neg logit contributions | |
til | -0.014 |
ucks | -0.014 |
pret | -0.013 |
name | -0.013 |
Tracy | -0.012 |
Token | H |
Token ID | 39 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
no | +0.017 |
unatt | +0.016 |
fore | +0.015 |
jected | +0.015 |
vern | +0.015 |
Neg logit contributions | |
ucks | -0.022 |
til | -0.022 |
pret | -0.021 |
name | -0.020 |
Tracy | -0.019 |
Token | oor |
Token ID | 2675 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ucks | +0.019 |
til | +0.019 |
ora | +0.018 |
name | +0.017 |
pret | +0.017 |
Neg logit contributions | |
no | -0.016 |
unatt | -0.015 |
fore | -0.014 |
jected | -0.013 |
Mic | -0.013 |
Token | ay |
Token ID | 323 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
no | +0.135 |
unatt | +0.116 |
fore | +0.109 |
jected | +0.102 |
never | +0.102 |
Neg logit contributions | |
ucks | -0.218 |
til | -0.212 |
name | -0.196 |
pret | -0.192 |
ora | -0.187 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
unatt | +0.059 |
no | +0.055 |
fore | +0.053 |
Mic | +0.053 |
vern | +0.051 |
Neg logit contributions | |
til | -0.072 |
ucks | -0.068 |
pret | -0.065 |
name | -0.063 |
Tracy | -0.057 |
Token | Jane |
Token ID | 12091 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
no | +0.008 |
unatt | +0.007 |
jected | +0.006 |
fore | +0.006 |
Jerry | +0.006 |
Neg logit contributions | |
ucks | -0.010 |
til | -0.010 |
pret | -0.010 |
name | -0.009 |
Tracy | -0.009 |
Token | shouted |
Token ID | 17293 |
Feature activation | -7.20e-03 |
Pos logit contributions | |
no | +0.039 |
unatt | +0.035 |
jected | +0.034 |
fore | +0.034 |
never | +0.033 |
Neg logit contributions | |
ucks | -0.040 |
til | -0.039 |
pret | -0.037 |
name | -0.034 |
Tracy | -0.033 |
Token | with |
Token ID | 351 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
no | +0.008 |
unatt | +0.008 |
course | +0.008 |
jected | +0.008 |
fore | +0.007 |
Neg logit contributions | |
til | -0.013 |
ucks | -0.012 |
pret | -0.012 |
name | -0.012 |
Tracy | -0.011 |
Token | magic |
Token ID | 5536 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
ucks | +0.013 |
til | +0.012 |
pret | +0.011 |
ours | +0.010 |
Tracy | +0.010 |
Neg logit contributions | |
no | -0.008 |
unatt | -0.007 |
fore | -0.007 |
course | -0.006 |
never | -0.006 |
Token | kingdom |
Token ID | 13239 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
no | +0.003 |
unatt | +0.003 |
fore | +0.003 |
course | +0.003 |
jected | +0.003 |
Neg logit contributions | |
ucks | -0.004 |
til | -0.003 |
pret | -0.003 |
Tracy | -0.003 |
name | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
no | +0.034 |
jected | +0.033 |
Mic | +0.032 |
unatt | +0.032 |
iable | +0.031 |
Neg logit contributions | |
til | -0.047 |
pret | -0.044 |
ucks | -0.044 |
name | -0.043 |
Tracy | -0.040 |
Token | There |
Token ID | 1318 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
no | +0.027 |
unatt | +0.024 |
jected | +0.023 |
fore | +0.023 |
Jerry | +0.022 |
Neg logit contributions | |
til | -0.037 |
ucks | -0.037 |
pret | -0.035 |
name | -0.032 |
Tracy | -0.031 |
Token | were |
Token ID | 547 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
til | +0.027 |
ucks | +0.026 |
pret | +0.025 |
name | +0.024 |
Tracy | +0.024 |
Neg logit contributions | |
unatt | -0.019 |
no | -0.019 |
jected | -0.018 |
fore | -0.017 |
vern | -0.017 |
Token | towers |
Token ID | 18028 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
unatt | +0.067 |
no | +0.065 |
jected | +0.065 |
vern | +0.060 |
iable | +0.059 |
Neg logit contributions | |
til | -0.109 |
ucks | -0.105 |
pret | -0.103 |
name | -0.099 |
Tracy | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
Mic | +0.172 |
jected | +0.167 |
unatt | +0.165 |
vern | +0.162 |
Fred | +0.161 |
Neg logit contributions | |
til | -0.163 |
ucks | -0.152 |
name | -0.147 |
pret | -0.146 |
smell | -0.142 |
Token | and |
Token ID | 290 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
no | +0.013 |
unatt | +0.013 |
jected | +0.013 |
vern | +0.012 |
iable | +0.012 |
Neg logit contributions | |
til | -0.012 |
ucks | -0.012 |
pret | -0.012 |
name | -0.011 |
Tracy | -0.010 |
Token | knights |
Token ID | 27536 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
no | +0.018 |
unatt | +0.017 |
jected | +0.017 |
fore | +0.016 |
vern | +0.016 |
Neg logit contributions | |
til | -0.020 |
ucks | -0.019 |
pret | -0.019 |
name | -0.017 |
Tracy | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.029 |
jected | +0.028 |
fore | +0.027 |
iable | +0.025 |
Neg logit contributions | |
til | -0.050 |
ucks | -0.049 |
pret | -0.047 |
name | -0.045 |
Tracy | -0.043 |
Token | princess |
Token ID | 21752 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
til | +0.020 |
pret | +0.020 |
ucks | +0.019 |
name | +0.018 |
Tracy | +0.018 |
Neg logit contributions | |
jected | -0.019 |
vern | -0.018 |
unatt | -0.018 |
no | -0.018 |
gh | -0.018 |
Token | The |
Token ID | 464 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
no | +0.012 |
unatt | +0.011 |
jected | +0.009 |
fore | +0.009 |
gone | +0.009 |
Neg logit contributions | |
ucks | -0.022 |
til | -0.021 |
pret | -0.020 |
Tracy | -0.019 |
name | -0.019 |
Token | old |
Token ID | 1468 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
no | +0.006 |
fore | +0.005 |
unatt | +0.005 |
jected | +0.005 |
course | +0.005 |
Neg logit contributions | |
ucks | -0.007 |
til | -0.006 |
pret | -0.006 |
Tracy | -0.005 |
ours | -0.005 |
Token | man |
Token ID | 582 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
ucks | +0.050 |
til | +0.047 |
pret | +0.043 |
ours | +0.043 |
ashes | +0.041 |
Neg logit contributions | |
no | -0.044 |
fore | -0.039 |
course | -0.039 |
Jerry | -0.037 |
His | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +5.96e-04 |
Pos logit contributions | |
til | +0.026 |
ucks | +0.024 |
pret | +0.023 |
name | +0.022 |
Tracy | +0.021 |
Neg logit contributions | |
no | -0.023 |
unatt | -0.022 |
jected | -0.021 |
vern | -0.020 |
fore | -0.020 |
Token | whose |
Token ID | 3025 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
til | +0.001 |
ucks | +0.001 |
pret | +0.001 |
name | +0.001 |
Tracy | +0.001 |
Neg logit contributions | |
no | -0.001 |
unatt | -0.001 |
jected | -0.001 |
fore | -0.001 |
vern | -0.001 |
Token | name |
Token ID | 1438 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ucks | +0.063 |
til | +0.062 |
pret | +0.055 |
ours | +0.050 |
Tracy | +0.050 |
Neg logit contributions | |
no | -0.069 |
fore | -0.058 |
unatt | -0.057 |
course | -0.056 |
never | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
til | +0.144 |
ucks | +0.137 |
pret | +0.131 |
name | +0.125 |
Tracy | +0.118 |
Neg logit contributions | |
no | -0.164 |
unatt | -0.162 |
jected | -0.149 |
vern | -0.146 |
fore | -0.146 |
Token | Tom |
Token ID | 4186 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
til | +0.025 |
ucks | +0.025 |
pret | +0.024 |
name | +0.023 |
Tracy | +0.022 |
Neg logit contributions | |
no | -0.018 |
unatt | -0.017 |
jected | -0.016 |
fore | -0.016 |
vern | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
no | +0.033 |
unatt | +0.029 |
jected | +0.027 |
fore | +0.027 |
course | +0.025 |
Neg logit contributions | |
til | -0.066 |
ucks | -0.066 |
pret | -0.062 |
name | -0.060 |
Tracy | -0.058 |
Token | said |
Token ID | 531 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
no | +0.005 |
unatt | +0.004 |
jected | +0.004 |
fore | +0.004 |
course | +0.004 |
Neg logit contributions | |
til | -0.007 |
ucks | -0.007 |
pret | -0.006 |
name | -0.006 |
Tracy | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | -1.46e-06 |
Pos logit contributions | |
til | +0.044 |
name | +0.042 |
pret | +0.042 |
ucks | +0.040 |
Tracy | +0.040 |
Neg logit contributions | |
unatt | -0.023 |
jected | -0.022 |
Mic | -0.022 |
P | -0.019 |
iable | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
no | +0.029 |
Once | +0.021 |
Jerry | +0.021 |
never | +0.020 |
course | +0.020 |
Neg logit contributions | |
ucks | -0.054 |
til | -0.049 |
pret | -0.047 |
rig | -0.045 |
enery | -0.044 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.08e-03 |
Pos logit contributions | |
no | +0.032 |
unatt | +0.031 |
jected | +0.030 |
course | +0.029 |
iable | +0.029 |
Neg logit contributions | |
til | -0.034 |
ucks | -0.033 |
name | -0.032 |
pret | -0.032 |
Tracy | -0.029 |
Token | my |
Token ID | 1820 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
no | +0.010 |
unatt | +0.009 |
jected | +0.009 |
fore | +0.009 |
course | +0.008 |
Neg logit contributions | |
til | -0.011 |
ucks | -0.011 |
pret | -0.010 |
name | -0.010 |
Tracy | -0.009 |
Token | called |
Token ID | 1444 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
ucks | +0.032 |
til | +0.032 |
pret | +0.030 |
name | +0.028 |
Tracy | +0.027 |
Neg logit contributions | |
no | -0.030 |
unatt | -0.026 |
fore | -0.025 |
jected | -0.025 |
never | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ucks | +0.112 |
til | +0.112 |
pret | +0.105 |
name | +0.097 |
ora | +0.095 |
Neg logit contributions | |
no | -0.068 |
unatt | -0.057 |
fore | -0.054 |
Jerry | -0.052 |
never | -0.051 |
Token | name |
Token ID | 1438 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ucks | +0.022 |
til | +0.022 |
pret | +0.020 |
Tracy | +0.019 |
ora | +0.018 |
Neg logit contributions | |
no | -0.014 |
fore | -0.011 |
unatt | -0.011 |
jected | -0.011 |
Jerry | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
til | +0.160 |
name | +0.156 |
ucks | +0.151 |
pret | +0.150 |
smell | +0.145 |
Neg logit contributions | |
unatt | -0.198 |
vern | -0.197 |
iable | -0.186 |
jected | -0.182 |
arrest | -0.178 |
Token |
|
Token ID | 198 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
no | +0.021 |
Jerry | +0.017 |
Once | +0.017 |
Fred | +0.015 |
never | +0.015 |
Neg logit contributions | |
ucks | -0.035 |
til | -0.032 |
pret | -0.032 |
enery | -0.030 |
ora | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
no | +0.029 |
Once | +0.028 |
never | +0.023 |
The | +0.022 |
Fred | +0.022 |
Neg logit contributions | |
til | -0.081 |
ucks | -0.081 |
pret | -0.079 |
enery | -0.076 |
ours | -0.072 |
Token | â |
Token ID | 22940 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
no | +0.046 |
unatt | +0.041 |
jected | +0.039 |
fore | +0.038 |
course | +0.037 |
Neg logit contributions | |
ucks | -0.067 |
til | -0.067 |
pret | -0.063 |
name | -0.060 |
Tracy | -0.058 |
Token | € |
Token ID | 26391 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
til | +0.022 |
ucks | +0.022 |
pret | +0.021 |
name | +0.020 |
Tracy | +0.019 |
Neg logit contributions | |
no | -0.023 |
unatt | -0.020 |
fore | -0.019 |
vern | -0.018 |
Jerry | -0.018 |
Token | pet |
Token ID | 4273 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
no | +0.018 |
jected | +0.018 |
unatt | +0.018 |
fore | +0.017 |
ross | +0.017 |
Neg logit contributions | |
til | -0.013 |
ucks | -0.013 |
name | -0.012 |
pret | -0.012 |
Tracy | -0.011 |
Token | my |
Token ID | 616 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
til | +0.037 |
ucks | +0.037 |
pret | +0.035 |
name | +0.033 |
Tracy | +0.032 |
Neg logit contributions | |
no | -0.027 |
unatt | -0.024 |
course | -0.023 |
jected | -0.022 |
fore | -0.022 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
til | +0.013 |
ucks | +0.013 |
pret | +0.012 |
Tracy | +0.011 |
ours | +0.011 |
Neg logit contributions | |
no | -0.011 |
unatt | -0.009 |
course | -0.009 |
fore | -0.009 |
Jerry | -0.008 |
Token | ? |
Token ID | 30 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
til | +0.023 |
ucks | +0.023 |
pret | +0.022 |
name | +0.021 |
Tracy | +0.020 |
Neg logit contributions | |
no | -0.021 |
unatt | -0.019 |
jected | -0.018 |
fore | -0.018 |
course | -0.017 |
Token | His |
Token ID | 2399 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
til | +0.048 |
ucks | +0.048 |
pret | +0.045 |
ora | +0.042 |
enery | +0.041 |
Neg logit contributions | |
no | -0.029 |
Jerry | -0.023 |
His | -0.022 |
course | -0.021 |
never | -0.020 |
Token | name |
Token ID | 1438 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ucks | +0.011 |
til | +0.011 |
pret | +0.008 |
Tracy | +0.007 |
ours | +0.006 |
Neg logit contributions | |
no | -0.044 |
unatt | -0.039 |
fore | -0.039 |
Jerry | -0.038 |
never | -0.038 |
Token | is |
Token ID | 318 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
til | +0.136 |
ucks | +0.134 |
pret | +0.129 |
name | +0.125 |
Tracy | +0.103 |
Neg logit contributions | |
unatt | -0.222 |
no | -0.214 |
jected | -0.209 |
Mic | -0.205 |
fore | -0.205 |
Token | Rex |
Token ID | 17853 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ucks | +0.048 |
til | +0.047 |
pret | +0.044 |
name | +0.041 |
Tracy | +0.039 |
Neg logit contributions | |
no | -0.042 |
unatt | -0.037 |
fore | -0.036 |
jected | -0.035 |
Jerry | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ucks | +0.076 |
til | +0.075 |
pret | +0.070 |
name | +0.066 |
Tracy | +0.066 |
Neg logit contributions | |
no | -0.034 |
unatt | -0.027 |
fore | -0.025 |
jected | -0.025 |
course | -0.024 |
Token | He |
Token ID | 679 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
til | +0.043 |
ucks | +0.042 |
pret | +0.039 |
ora | +0.037 |
ours | +0.036 |
Neg logit contributions | |
no | -0.029 |
Jerry | -0.022 |
unatt | -0.022 |
His | -0.022 |
fore | -0.021 |
Token | is |
Token ID | 318 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
ucks | +0.062 |
til | +0.055 |
Tracy | +0.050 |
ours | +0.049 |
pret | +0.048 |
Neg logit contributions | |
no | -0.052 |
never | -0.046 |
fore | -0.043 |
course | -0.043 |
jected | -0.040 |
Token | notebook |
Token ID | 20922 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
til | +0.042 |
ucks | +0.042 |
pret | +0.040 |
name | +0.038 |
Tracy | +0.036 |
Neg logit contributions | |
no | -0.038 |
unatt | -0.035 |
jected | -0.034 |
fore | -0.033 |
iable | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
arrest | +0.051 |
Fred | +0.050 |
fore | +0.050 |
jected | +0.050 |
Jerry | +0.050 |
Neg logit contributions | |
til | -0.050 |
name | -0.049 |
pret | -0.047 |
ucks | -0.046 |
idea | -0.043 |
Token | She |
Token ID | 1375 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
no | +0.014 |
unatt | +0.012 |
jected | +0.011 |
fore | +0.011 |
course | +0.011 |
Neg logit contributions | |
til | -0.019 |
ucks | -0.019 |
pret | -0.017 |
name | -0.016 |
Tracy | -0.016 |
Token | writes |
Token ID | 6797 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ucks | +0.049 |
til | +0.044 |
Tracy | +0.041 |
Randy | +0.041 |
rig | +0.041 |
Neg logit contributions | |
no | -0.039 |
never | -0.035 |
fore | -0.032 |
jected | -0.030 |
course | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
til | +0.029 |
ucks | +0.029 |
pret | +0.027 |
name | +0.026 |
Tracy | +0.025 |
Neg logit contributions | |
no | -0.019 |
unatt | -0.018 |
jected | -0.017 |
fore | -0.016 |
course | -0.016 |
Token | name |
Token ID | 1438 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ucks | +0.023 |
til | +0.021 |
pret | +0.018 |
Tracy | +0.017 |
ora | +0.016 |
Neg logit contributions | |
no | -0.040 |
fore | -0.035 |
unatt | -0.035 |
course | -0.034 |
never | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
til | +0.243 |
name | +0.234 |
ucks | +0.232 |
pret | +0.232 |
Tracy | +0.214 |
Neg logit contributions | |
unatt | -0.149 |
no | -0.142 |
jected | -0.137 |
vern | -0.137 |
fore | -0.134 |
Token | her |
Token ID | 607 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
ucks | +0.050 |
til | +0.048 |
pret | +0.045 |
name | +0.043 |
Tracy | +0.042 |
Neg logit contributions | |
no | -0.036 |
unatt | -0.031 |
fore | -0.029 |
Jerry | -0.029 |
course | -0.028 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ucks | +0.047 |
til | +0.045 |
pret | +0.042 |
Tracy | +0.040 |
ora | +0.039 |
Neg logit contributions | |
no | -0.031 |
unatt | -0.025 |
fore | -0.024 |
course | -0.024 |
Jerry | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
til | +0.072 |
name | +0.071 |
pret | +0.070 |
ucks | +0.068 |
Tracy | +0.064 |
Neg logit contributions | |
unatt | -0.038 |
vern | -0.038 |
jected | -0.036 |
fore | -0.035 |
no | -0.034 |
Token | name |
Token ID | 1438 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ucks | +0.054 |
til | +0.051 |
pret | +0.046 |
Tracy | +0.041 |
ours | +0.040 |
Neg logit contributions | |
no | -0.079 |
unatt | -0.070 |
fore | -0.069 |
course | -0.066 |
asure | -0.066 |
Token | you |
Token ID | 345 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
til | +0.054 |
ucks | +0.053 |
pret | +0.050 |
name | +0.049 |
Tracy | +0.048 |
Neg logit contributions | |
unatt | -0.032 |
jected | -0.031 |
no | -0.030 |
fore | -0.030 |
vern | -0.029 |
Token | count |
Token ID | 954 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
no | +0.100 |
unatt | +0.095 |
jected | +0.091 |
fore | +0.090 |
course | +0.086 |
Neg logit contributions | |
til | -0.075 |
ucks | -0.074 |
pret | -0.068 |
name | -0.065 |
Tracy | -0.060 |
Token | how |
Token ID | 703 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
no | +0.016 |
unatt | +0.015 |
jected | +0.014 |
fore | +0.014 |
course | +0.013 |
Neg logit contributions | |
til | -0.024 |
ucks | -0.024 |
pret | -0.023 |
name | -0.021 |
Tracy | -0.021 |
Token | many |
Token ID | 867 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ucks | +0.155 |
til | +0.152 |
pret | +0.144 |
name | +0.142 |
Tracy | +0.136 |
Neg logit contributions | |
no | -0.083 |
unatt | -0.083 |
jected | -0.079 |
fore | -0.074 |
course | -0.071 |
Token | ost |
Token ID | 23619 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
no | +0.108 |
unatt | +0.102 |
jected | +0.099 |
fore | +0.096 |
Jerry | +0.093 |
Neg logit contributions | |
til | -0.087 |
ucks | -0.086 |
pret | -0.080 |
name | -0.075 |
Tracy | -0.071 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
no | +0.047 |
unatt | +0.045 |
jected | +0.043 |
fore | +0.043 |
Jerry | +0.042 |
Neg logit contributions | |
ucks | -0.013 |
til | -0.013 |
pret | -0.009 |
name | -0.009 |
ours | -0.007 |
Token | hes |
Token ID | 956 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
til | +0.172 |
ucks | +0.169 |
pret | +0.155 |
name | +0.148 |
ours | +0.134 |
Neg logit contributions | |
no | -0.215 |
unatt | -0.207 |
fore | -0.193 |
jected | -0.192 |
course | -0.185 |
Token | there |
Token ID | 612 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
til | +0.086 |
ucks | +0.086 |
pret | +0.081 |
name | +0.079 |
Tracy | +0.073 |
Neg logit contributions | |
no | -0.062 |
unatt | -0.062 |
jected | -0.060 |
Mic | -0.057 |
fore | -0.056 |
Token | are |
Token ID | 389 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
til | +0.039 |
ucks | +0.037 |
pret | +0.036 |
name | +0.036 |
smell | +0.032 |
Neg logit contributions | |
jected | -0.041 |
no | -0.041 |
unatt | -0.040 |
fore | -0.040 |
ross | -0.038 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
no | +0.039 |
unatt | +0.037 |
jected | +0.036 |
fore | +0.034 |
course | +0.033 |
Neg logit contributions | |
til | -0.051 |
ucks | -0.050 |
pret | -0.048 |
name | -0.046 |
Tracy | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -5.11e-03 |
Pos logit contributions | |
ucks | +0.076 |
pret | +0.076 |
enery | +0.074 |
til | +0.073 |
exception | +0.070 |
Neg logit contributions | |
no | -0.045 |
Once | -0.036 |
Fred | -0.034 |
course | -0.033 |
Jerry | -0.033 |
Token | spider |
Token ID | 19230 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
no | +0.029 |
unatt | +0.025 |
fore | +0.023 |
course | +0.023 |
never | +0.022 |
Neg logit contributions | |
ucks | -0.038 |
til | -0.034 |
pret | -0.032 |
ours | -0.031 |
Tracy | -0.030 |
Token | crawling |
Token ID | 34499 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
ucks | +0.042 |
til | +0.039 |
pret | +0.038 |
name | +0.036 |
Tracy | +0.035 |
Neg logit contributions | |
no | -0.028 |
unatt | -0.025 |
fore | -0.023 |
never | -0.022 |
course | -0.022 |
Token | towards |
Token ID | 3371 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
til | +0.069 |
ucks | +0.066 |
pret | +0.061 |
name | +0.059 |
Tracy | +0.055 |
Neg logit contributions | |
no | -0.079 |
unatt | -0.077 |
jected | -0.075 |
vern | -0.075 |
iable | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
ucks | +0.020 |
til | +0.019 |
pret | +0.018 |
name | +0.017 |
ours | +0.016 |
Neg logit contributions | |
no | -0.020 |
unatt | -0.016 |
fore | -0.016 |
never | -0.016 |
course | -0.016 |
Token | hole |
Token ID | 7604 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
ucks | +0.059 |
til | +0.058 |
pret | +0.054 |
name | +0.051 |
Tracy | +0.049 |
Neg logit contributions | |
no | -0.045 |
unatt | -0.041 |
fore | -0.038 |
jected | -0.037 |
course | -0.037 |
Token | in |
Token ID | 287 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
til | +0.009 |
ucks | +0.009 |
pret | +0.008 |
name | +0.008 |
smell | +0.008 |
Neg logit contributions | |
Mic | -0.007 |
no | -0.007 |
unatt | -0.007 |
jected | -0.007 |
iable | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
til | +0.058 |
ucks | +0.057 |
pret | +0.054 |
name | +0.052 |
Tracy | +0.051 |
Neg logit contributions | |
unatt | -0.042 |
no | -0.042 |
jected | -0.041 |
iable | -0.039 |
fore | -0.038 |
Token | fence |
Token ID | 13990 |
Feature activation | -1.20e-04 |
Pos logit contributions | |
til | +0.026 |
name | +0.025 |
pret | +0.025 |
smell | +0.024 |
lands | +0.023 |
Neg logit contributions | |
vern | -0.029 |
iable | -0.028 |
jected | -0.027 |
no | -0.027 |
ross | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
Mic | +0.000 |
vern | +0.000 |
jected | +0.000 |
iable | +0.000 |
P | +0.000 |
Neg logit contributions | |
til | -0.000 |
ucks | -0.000 |
name | -0.000 |
smell | -0.000 |
pret | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
til | +0.009 |
ucks | +0.009 |
pret | +0.009 |
name | +0.008 |
Tracy | +0.007 |
Neg logit contributions | |
no | -0.006 |
Jerry | -0.005 |
fore | -0.005 |
unatt | -0.005 |
jected | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
no | +0.010 |
never | +0.008 |
Once | +0.008 |
Jerry | +0.008 |
fore | +0.008 |
Neg logit contributions | |
til | -0.023 |
ucks | -0.022 |
pret | -0.022 |
enery | -0.020 |
smell | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
no | +0.023 |
unatt | +0.021 |
jected | +0.019 |
fore | +0.019 |
course | +0.017 |
Neg logit contributions | |
ucks | -0.050 |
til | -0.050 |
pret | -0.047 |
name | -0.046 |
Tracy | -0.044 |
Token | thought |
Token ID | 1807 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
ucks | +0.027 |
til | +0.026 |
pret | +0.024 |
Tracy | +0.022 |
name | +0.022 |
Neg logit contributions | |
no | -0.023 |
never | -0.019 |
fore | -0.019 |
jected | -0.019 |
unatt | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
til | +0.012 |
ucks | +0.011 |
pret | +0.011 |
name | +0.011 |
Tracy | +0.010 |
Neg logit contributions | |
no | -0.013 |
unatt | -0.013 |
jected | -0.013 |
fore | -0.012 |
course | -0.012 |
Token | � |
Token ID | 6184 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
no | +0.027 |
unatt | +0.024 |
fore | +0.023 |
jected | +0.023 |
course | +0.022 |
Neg logit contributions | |
ucks | -0.033 |
til | -0.033 |
pret | -0.030 |
name | -0.028 |
Tracy | -0.028 |
Token | � |
Token ID | 95 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
ucks | +0.035 |
til | +0.034 |
pret | +0.031 |
name | +0.029 |
Tracy | +0.027 |
Neg logit contributions | |
no | -0.031 |
unatt | -0.028 |
jected | -0.027 |
course | -0.027 |
iable | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
til | +0.055 |
ucks | +0.055 |
pret | +0.051 |
name | +0.048 |
Tracy | +0.047 |
Neg logit contributions | |
no | -0.046 |
unatt | -0.042 |
jected | -0.040 |
fore | -0.039 |
course | -0.038 |
Token | � |
Token ID | 129 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
til | +0.093 |
ucks | +0.092 |
pret | +0.088 |
name | +0.085 |
Tracy | +0.081 |
Neg logit contributions | |
no | -0.066 |
unatt | -0.062 |
jected | -0.058 |
fore | -0.058 |
course | -0.055 |
Token | � |
Token ID | 241 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
ucks | +0.002 |
til | +0.002 |
pret | +0.002 |
Tracy | +0.002 |
name | +0.002 |
Neg logit contributions | |
no | -0.002 |
jected | -0.002 |
unatt | -0.002 |
fore | -0.002 |
never | -0.002 |
Token | Oh |
Token ID | 5812 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
til | +0.098 |
ucks | +0.096 |
pret | +0.087 |
ours | +0.082 |
enery | +0.079 |
Neg logit contributions | |
no | -0.068 |
never | -0.056 |
Once | -0.051 |
fore | -0.051 |
His | -0.049 |
Token | no |
Token ID | 645 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
til | +0.033 |
pret | +0.032 |
ucks | +0.031 |
name | +0.031 |
Tracy | +0.030 |
Neg logit contributions | |
unatt | -0.023 |
jected | -0.021 |
Mic | -0.020 |
fore | -0.020 |
no | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
no | +0.057 |
unatt | +0.044 |
fore | +0.041 |
jected | +0.040 |
course | +0.040 |
Neg logit contributions | |
ucks | -0.154 |
til | -0.153 |
pret | -0.143 |
name | -0.138 |
Tracy | -0.135 |
Token | caught |
Token ID | 4978 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
til | +0.003 |
ucks | +0.003 |
pret | +0.002 |
name | +0.002 |
Tracy | +0.002 |
Neg logit contributions | |
no | -0.002 |
unatt | -0.002 |
jected | -0.002 |
fore | -0.002 |
vern | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
ucks | +0.031 |
til | +0.031 |
pret | +0.029 |
name | +0.028 |
Tracy | +0.027 |
Neg logit contributions | |
no | -0.021 |
unatt | -0.018 |
fore | -0.017 |
course | -0.016 |
jected | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
til | +0.010 |
pret | +0.009 |
ucks | +0.009 |
name | +0.009 |
Tracy | +0.008 |
Neg logit contributions | |
no | -0.009 |
jected | -0.009 |
iable | -0.008 |
unatt | -0.008 |
course | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ucks | +0.003 |
til | +0.003 |
pret | +0.002 |
name | +0.002 |
Tracy | +0.002 |
Neg logit contributions | |
no | -0.002 |
unatt | -0.002 |
jected | -0.002 |
fore | -0.002 |
course | -0.002 |
Token | woke |
Token ID | 19092 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
til | +0.029 |
ucks | +0.028 |
pret | +0.027 |
name | +0.025 |
Tracy | +0.024 |
Neg logit contributions | |
no | -0.028 |
unatt | -0.027 |
jected | -0.026 |
fore | -0.026 |
vern | -0.025 |
Token | up |
Token ID | 510 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
no | +0.080 |
unatt | +0.073 |
never | +0.069 |
iable | +0.068 |
jected | +0.068 |
Neg logit contributions | |
ucks | -0.061 |
pret | -0.053 |
name | -0.053 |
til | -0.052 |
ora | -0.047 |
Token | screaming |
Token ID | 14788 |
Feature activation | -7.01e-04 |
Pos logit contributions | |
til | +0.066 |
ucks | +0.064 |
pret | +0.061 |
name | +0.058 |
Tracy | +0.056 |
Neg logit contributions | |
no | -0.044 |
unatt | -0.041 |
jected | -0.040 |
fore | -0.038 |
course | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Mic | +0.001 |
vern | +0.001 |
no | +0.001 |
jected | +0.001 |
unatt | +0.001 |
Neg logit contributions | |
til | -0.001 |
pret | -0.001 |
ucks | -0.001 |
name | -0.001 |
smell | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
no | +0.030 |
unatt | +0.027 |
jected | +0.026 |
fore | +0.026 |
course | +0.025 |
Neg logit contributions | |
ucks | -0.039 |
til | -0.039 |
pret | -0.036 |
name | -0.034 |
Tracy | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ucks | +0.018 |
til | +0.016 |
name | +0.015 |
pret | +0.015 |
Tracy | +0.015 |
Neg logit contributions | |
no | -0.013 |
never | -0.012 |
fore | -0.011 |
unatt | -0.011 |
jected | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
no | +0.020 |
unatt | +0.018 |
jected | +0.017 |
fore | +0.017 |
course | +0.016 |
Neg logit contributions | |
til | -0.023 |
ucks | -0.023 |
pret | -0.021 |
name | -0.020 |
Tracy | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
til | +0.081 |
ucks | +0.080 |
pret | +0.076 |
name | +0.074 |
Tracy | +0.069 |
Neg logit contributions | |
no | -0.067 |
unatt | -0.063 |
jected | -0.061 |
fore | -0.060 |
course | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.029 |
jected | +0.027 |
fore | +0.027 |
iable | +0.026 |
Neg logit contributions | |
ucks | -0.035 |
til | -0.035 |
pret | -0.032 |
name | -0.032 |
Tracy | -0.031 |
Token | Em |
Token ID | 10161 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
no | +0.035 |
unatt | +0.032 |
jected | +0.028 |
asure | +0.028 |
fore | +0.028 |
Neg logit contributions | |
ucks | -0.041 |
til | -0.039 |
Tracy | -0.038 |
Would | -0.038 |
ora | -0.037 |
Token | my |
Token ID | 1820 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
no | +0.018 |
unatt | +0.016 |
jected | +0.015 |
fore | +0.015 |
Jerry | +0.014 |
Neg logit contributions | |
ucks | -0.036 |
til | -0.036 |
pret | -0.034 |
name | -0.033 |
Tracy | -0.032 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
no | +0.010 |
unatt | +0.009 |
jected | +0.009 |
fore | +0.009 |
course | +0.009 |
Neg logit contributions | |
til | -0.010 |
ucks | -0.010 |
pret | -0.010 |
name | -0.009 |
Tracy | -0.009 |
Token | up |
Token ID | 510 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.029 |
jected | +0.028 |
course | +0.027 |
fore | +0.027 |
Neg logit contributions | |
til | -0.042 |
ucks | -0.042 |
name | -0.039 |
pret | -0.039 |
Tracy | -0.036 |
Token | at |
Token ID | 379 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
til | +0.128 |
ucks | +0.121 |
name | +0.118 |
pret | +0.110 |
ora | +0.106 |
Neg logit contributions | |
no | -0.102 |
unatt | -0.101 |
iable | -0.097 |
jected | -0.096 |
Mic | -0.096 |
Token | her |
Token ID | 607 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
no | +0.022 |
unatt | +0.019 |
fore | +0.018 |
jected | +0.018 |
course | +0.017 |
Neg logit contributions | |
ucks | -0.034 |
til | -0.034 |
pret | -0.032 |
name | -0.030 |
Tracy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
no | +0.020 |
unatt | +0.018 |
fore | +0.017 |
jected | +0.017 |
course | +0.016 |
Neg logit contributions | |
ucks | -0.025 |
til | -0.025 |
pret | -0.023 |
name | -0.022 |
Tracy | -0.021 |
Token | � |
Token ID | 6184 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
no | +0.011 |
unatt | +0.010 |
jected | +0.010 |
fore | +0.009 |
course | +0.009 |
Neg logit contributions | |
ucks | -0.012 |
til | -0.012 |
pret | -0.011 |
name | -0.011 |
Tracy | -0.011 |
Token | � |
Token ID | 95 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
til | +0.036 |
ucks | +0.036 |
pret | +0.033 |
name | +0.031 |
Tracy | +0.030 |
Neg logit contributions | |
no | -0.036 |
unatt | -0.033 |
jected | -0.031 |
fore | -0.031 |
course | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
til | +0.008 |
pret | +0.008 |
ucks | +0.008 |
name | +0.007 |
smell | +0.007 |
Neg logit contributions | |
jected | -0.008 |
Mic | -0.008 |
asure | -0.007 |
no | -0.007 |
P | -0.007 |
Token | quickly |
Token ID | 2952 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
no | +0.030 |
unatt | +0.028 |
jected | +0.027 |
fore | +0.027 |
course | +0.026 |
Neg logit contributions | |
til | -0.035 |
ucks | -0.034 |
pret | -0.032 |
name | -0.030 |
Tracy | -0.029 |
Token | passed |
Token ID | 3804 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
jected | +0.016 |
unatt | +0.015 |
Mic | +0.015 |
no | +0.015 |
vern | +0.015 |
Neg logit contributions | |
til | -0.016 |
pret | -0.014 |
nud | -0.013 |
smell | -0.013 |
name | -0.013 |
Token | out |
Token ID | 503 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
no | +0.023 |
unatt | +0.021 |
jected | +0.021 |
fore | +0.020 |
vern | +0.020 |
Neg logit contributions | |
til | -0.033 |
ucks | -0.033 |
pret | -0.031 |
name | -0.029 |
Tracy | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -8.96e-03 |
Pos logit contributions | |
no | +0.008 |
jected | +0.008 |
unatt | +0.008 |
iable | +0.008 |
Mic | +0.008 |
Neg logit contributions | |
til | -0.014 |
ucks | -0.013 |
pret | -0.013 |
name | -0.013 |
Tracy | -0.012 |
Token | When |
Token ID | 1649 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
no | +0.013 |
unatt | +0.012 |
jected | +0.012 |
fore | +0.011 |
iable | +0.011 |
Neg logit contributions | |
til | -0.014 |
ucks | -0.014 |
pret | -0.013 |
name | -0.012 |
Tracy | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
til | +0.081 |
ucks | +0.075 |
pret | +0.074 |
Tracy | +0.071 |
name | +0.071 |
Neg logit contributions | |
unatt | -0.066 |
jected | -0.064 |
no | -0.063 |
vern | -0.060 |
iable | -0.060 |
Token | woke |
Token ID | 19092 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
no | +0.048 |
unatt | +0.046 |
vern | +0.045 |
jected | +0.044 |
iable | +0.043 |
Neg logit contributions | |
til | -0.050 |
ucks | -0.047 |
pret | -0.046 |
name | -0.043 |
Tracy | -0.041 |
Token | up |
Token ID | 510 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
no | +0.117 |
unatt | +0.107 |
Jerry | +0.103 |
never | +0.102 |
iable | +0.101 |
Neg logit contributions | |
ucks | -0.069 |
til | -0.061 |
pret | -0.060 |
name | -0.053 |
ora | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
til | +0.047 |
ucks | +0.045 |
pret | +0.044 |
name | +0.042 |
Tracy | +0.041 |
Neg logit contributions | |
no | -0.017 |
jected | -0.015 |
unatt | -0.015 |
fore | -0.014 |
vern | -0.013 |
Token | next |
Token ID | 1306 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
no | +0.032 |
unatt | +0.029 |
jected | +0.028 |
fore | +0.027 |
course | +0.026 |
Neg logit contributions | |
til | -0.037 |
ucks | -0.037 |
pret | -0.035 |
name | -0.033 |
Tracy | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
jected | +0.027 |
unatt | +0.025 |
Mic | +0.024 |
ross | +0.023 |
no | +0.023 |
Neg logit contributions | |
til | -0.031 |
ucks | -0.030 |
name | -0.030 |
pret | -0.029 |
Tracy | -0.028 |
Token | go |
Token ID | 467 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
no | +0.037 |
unatt | +0.037 |
jected | +0.036 |
fore | +0.034 |
Mic | +0.033 |
Neg logit contributions | |
til | -0.032 |
ucks | -0.031 |
name | -0.030 |
pret | -0.029 |
smell | -0.026 |
Token | fast |
Token ID | 3049 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
no | +0.020 |
unatt | +0.017 |
never | +0.015 |
fore | +0.015 |
course | +0.015 |
Neg logit contributions | |
til | -0.035 |
ucks | -0.035 |
pret | -0.033 |
name | -0.031 |
ours | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
no | +0.026 |
unatt | +0.022 |
fore | +0.020 |
jected | +0.019 |
course | +0.019 |
Neg logit contributions | |
ucks | -0.054 |
til | -0.053 |
pret | -0.050 |
name | -0.048 |
Tracy | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
no | +0.027 |
unatt | +0.023 |
fore | +0.022 |
jected | +0.022 |
never | +0.021 |
Neg logit contributions | |
til | -0.040 |
ucks | -0.039 |
pret | -0.038 |
name | -0.034 |
Tracy | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
no | +0.041 |
unatt | +0.037 |
jected | +0.035 |
fore | +0.035 |
course | +0.033 |
Neg logit contributions | |
ucks | -0.056 |
til | -0.056 |
pret | -0.052 |
name | -0.050 |
Tracy | -0.048 |
Token | Her |
Token ID | 9360 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
unatt | +0.037 |
no | +0.037 |
jected | +0.034 |
fore | +0.033 |
course | +0.031 |
Neg logit contributions | |
ucks | -0.058 |
til | -0.055 |
name | -0.053 |
pret | -0.050 |
Tracy | -0.049 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
no | +0.014 |
unatt | +0.013 |
jected | +0.013 |
fore | +0.012 |
course | +0.012 |
Neg logit contributions | |
til | -0.018 |
ucks | -0.017 |
pret | -0.016 |
name | -0.016 |
Tracy | -0.015 |
Token | pointed |
Token ID | 6235 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
no | +0.011 |
unatt | +0.011 |
jected | +0.010 |
fore | +0.010 |
course | +0.010 |
Neg logit contributions | |
til | -0.010 |
ucks | -0.010 |
pret | -0.009 |
name | -0.009 |
Tracy | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
ucks | +0.010 |
til | +0.010 |
pret | +0.010 |
Tracy | +0.009 |
name | +0.009 |
Neg logit contributions | |
no | -0.004 |
unatt | -0.003 |
fore | -0.003 |
Jerry | -0.003 |
course | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -7.57e-03 |
Pos logit contributions | |
ucks | +0.054 |
til | +0.054 |
pret | +0.051 |
Tracy | +0.047 |
name | +0.047 |
Neg logit contributions | |
no | -0.027 |
course | -0.020 |
never | -0.020 |
fore | -0.020 |
unatt | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
no | +0.061 |
unatt | +0.056 |
jected | +0.053 |
fore | +0.052 |
course | +0.051 |
Neg logit contributions | |
til | -0.075 |
ucks | -0.074 |
pret | -0.070 |
name | -0.066 |
Tracy | -0.064 |
Token | home |
Token ID | 1363 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
no | +0.037 |
unatt | +0.035 |
jected | +0.033 |
fore | +0.033 |
course | +0.033 |
Neg logit contributions | |
til | -0.045 |
ucks | -0.044 |
pret | -0.042 |
name | -0.040 |
Tracy | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
jected | +0.051 |
no | +0.050 |
Mic | +0.050 |
course | +0.049 |
unatt | +0.048 |
Neg logit contributions | |
til | -0.083 |
ucks | -0.080 |
pret | -0.076 |
name | -0.075 |
Tracy | -0.072 |
Token | The |
Token ID | 383 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
no | +0.025 |
unatt | +0.024 |
jected | +0.023 |
fore | +0.022 |
vern | +0.022 |
Neg logit contributions | |
ucks | -0.025 |
til | -0.025 |
name | -0.024 |
pret | -0.023 |
Tracy | -0.021 |
Token | lady |
Token ID | 10846 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
no | +0.014 |
unatt | +0.013 |
jected | +0.012 |
fore | +0.012 |
Jerry | +0.012 |
Neg logit contributions | |
til | -0.015 |
ucks | -0.015 |
pret | -0.014 |
name | -0.013 |
Tracy | -0.012 |
Token | gave |
Token ID | 2921 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
no | +0.007 |
unatt | +0.006 |
jected | +0.006 |
fore | +0.006 |
never | +0.005 |
Neg logit contributions | |
ucks | -0.008 |
til | -0.008 |
pret | -0.007 |
name | -0.007 |
Tracy | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
til | +0.009 |
ucks | +0.009 |
pret | +0.008 |
name | +0.008 |
Tracy | +0.007 |
Neg logit contributions | |
no | -0.007 |
unatt | -0.007 |
jected | -0.007 |
fore | -0.006 |
vern | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ucks | +0.033 |
til | +0.032 |
name | +0.031 |
pret | +0.030 |
Tracy | +0.029 |
Neg logit contributions | |
unatt | -0.024 |
no | -0.023 |
jected | -0.023 |
gh | -0.021 |
fore | -0.021 |
Token | hug |
Token ID | 16225 |
Feature activation | -6.38e-03 |
Pos logit contributions | |
ucks | +0.062 |
til | +0.061 |
pret | +0.057 |
name | +0.054 |
Tracy | +0.053 |
Neg logit contributions | |
no | -0.043 |
unatt | -0.038 |
fore | -0.036 |
jected | -0.036 |
course | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
unatt | +0.009 |
Mic | +0.009 |
vern | +0.009 |
jected | +0.009 |
no | +0.009 |
Neg logit contributions | |
til | -0.009 |
ucks | -0.008 |
pret | -0.008 |
name | -0.008 |
Tracy | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
til | +0.018 |
ucks | +0.016 |
pret | +0.016 |
name | +0.015 |
Tracy | +0.014 |
Neg logit contributions | |
unatt | -0.020 |
no | -0.020 |
jected | -0.019 |
vern | -0.018 |
iable | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
ucks | +0.016 |
til | +0.016 |
pret | +0.015 |
name | +0.014 |
Tracy | +0.014 |
Neg logit contributions | |
no | -0.010 |
unatt | -0.009 |
fore | -0.008 |
jected | -0.008 |
course | -0.008 |
Token | cake |
Token ID | 12187 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
no | +0.041 |
unatt | +0.037 |
jected | +0.035 |
fore | +0.034 |
course | +0.033 |
Neg logit contributions | |
ucks | -0.069 |
til | -0.069 |
pret | -0.065 |
name | -0.062 |
Tracy | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
jected | +0.063 |
no | +0.063 |
vern | +0.061 |
unatt | +0.060 |
Mic | +0.060 |
Neg logit contributions | |
til | -0.070 |
ucks | -0.066 |
pret | -0.066 |
name | -0.065 |
smell | -0.062 |
Token | thank |
Token ID | 5875 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ucks | +0.035 |
til | +0.033 |
pret | +0.029 |
Tracy | +0.028 |
ora | +0.028 |
Neg logit contributions | |
no | -0.034 |
unatt | -0.028 |
fore | -0.028 |
never | -0.028 |
course | -0.027 |
Token | Mom |
Token ID | 11254 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
no | +0.019 |
unatt | +0.019 |
jected | +0.018 |
vern | +0.017 |
fore | +0.017 |
Neg logit contributions | |
ucks | -0.020 |
til | -0.020 |
name | -0.018 |
pret | -0.018 |
Tracy | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
ucks | +0.073 |
til | +0.073 |
pret | +0.069 |
name | +0.066 |
Tracy | +0.063 |
Neg logit contributions | |
no | -0.047 |
unatt | -0.043 |
jected | -0.040 |
fore | -0.039 |
course | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
ucks | +0.032 |
til | +0.032 |
pret | +0.029 |
name | +0.028 |
Tracy | +0.026 |
Neg logit contributions | |
no | -0.039 |
unatt | -0.037 |
jected | -0.035 |
fore | -0.035 |
course | -0.034 |
Token | want |
Token ID | 765 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
ucks | +0.052 |
til | +0.051 |
pret | +0.047 |
Tracy | +0.043 |
name | +0.043 |
Neg logit contributions | |
no | -0.051 |
unatt | -0.045 |
fore | -0.044 |
jected | -0.043 |
course | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +4.58e-03 |
Pos logit contributions | |
til | +0.017 |
ucks | +0.017 |
pret | +0.016 |
name | +0.015 |
Tracy | +0.015 |
Neg logit contributions | |
no | -0.009 |
unatt | -0.009 |
jected | -0.008 |
fore | -0.008 |
course | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ucks | +0.006 |
til | +0.006 |
pret | +0.006 |
name | +0.006 |
Tracy | +0.005 |
Neg logit contributions | |
no | -0.007 |
unatt | -0.007 |
jected | -0.006 |
fore | -0.006 |
course | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | -9.02e-04 |
Pos logit contributions | |
til | +0.038 |
ucks | +0.038 |
pret | +0.036 |
name | +0.034 |
Tracy | +0.031 |
Neg logit contributions | |
no | -0.031 |
jected | -0.029 |
unatt | -0.029 |
fore | -0.028 |
vern | -0.027 |
Token | strange |
Token ID | 6283 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ucks | +0.013 |
til | +0.011 |
pret | +0.011 |
ours | +0.010 |
ora | +0.010 |
Neg logit contributions | |
no | -0.009 |
fore | -0.008 |
unatt | -0.008 |
course | -0.008 |
never | -0.008 |
Token | noise |
Token ID | 7838 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
ucks | +0.073 |
ours | +0.062 |
Tracy | +0.061 |
ora | +0.060 |
til | +0.059 |
Neg logit contributions | |
no | -0.051 |
fore | -0.050 |
gh | -0.047 |
course | -0.047 |
unatt | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
til | +0.063 |
ucks | +0.062 |
pret | +0.059 |
name | +0.056 |
Tracy | +0.055 |
Neg logit contributions | |
no | -0.035 |
unatt | -0.031 |
jected | -0.030 |
fore | -0.029 |
course | -0.028 |
Token | It |
Token ID | 632 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
no | +0.012 |
unatt | +0.011 |
fore | +0.010 |
Jerry | +0.010 |
jected | +0.010 |
Neg logit contributions | |
ucks | -0.017 |
til | -0.017 |
pret | -0.016 |
Tracy | -0.014 |
name | -0.014 |
Token | sounded |
Token ID | 14846 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ucks | +0.026 |
til | +0.023 |
ashes | +0.022 |
ours | +0.022 |
pret | +0.022 |
Neg logit contributions | |
no | -0.016 |
never | -0.014 |
fore | -0.013 |
gone | -0.013 |
jected | -0.013 |
Token | weird |
Token ID | 7650 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
til | +0.032 |
ucks | +0.032 |
pret | +0.029 |
name | +0.027 |
Tracy | +0.026 |
Neg logit contributions | |
no | -0.040 |
unatt | -0.037 |
jected | -0.036 |
fore | -0.036 |
course | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
til | +0.005 |
ucks | +0.005 |
pret | +0.005 |
name | +0.005 |
Tracy | +0.005 |
Neg logit contributions | |
no | -0.003 |
unatt | -0.003 |
jected | -0.003 |
fore | -0.003 |
course | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ucks | +0.009 |
til | +0.009 |
pret | +0.008 |
name | +0.008 |
Tracy | +0.008 |
Neg logit contributions | |
no | -0.008 |
unatt | -0.007 |
jected | -0.006 |
fore | -0.006 |
course | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | +6.06e-04 |
Pos logit contributions | |
til | +0.029 |
ucks | +0.029 |
pret | +0.027 |
name | +0.025 |
Tracy | +0.025 |
Neg logit contributions | |
no | -0.020 |
unatt | -0.017 |
fore | -0.016 |
jected | -0.016 |
course | -0.015 |
Token | feel |
Token ID | 1254 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
ucks | +0.001 |
til | +0.001 |
pret | +0.001 |
Tracy | +0.001 |
ora | +0.001 |
Neg logit contributions | |
no | -0.001 |
never | -0.001 |
unatt | -0.001 |
fore | -0.001 |
gone | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ucks | +0.094 |
til | +0.085 |
pret | +0.081 |
ora | +0.077 |
Tracy | +0.076 |
Neg logit contributions | |
no | -0.082 |
unatt | -0.070 |
fore | -0.067 |
never | -0.065 |
gone | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
ucks | +0.058 |
til | +0.057 |
pret | +0.054 |
name | +0.050 |
Tracy | +0.050 |
Neg logit contributions | |
no | -0.032 |
unatt | -0.027 |
fore | -0.026 |
jected | -0.025 |
course | -0.025 |
Token | want |
Token ID | 765 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
no | +0.007 |
fore | +0.006 |
unatt | +0.006 |
never | +0.006 |
Jerry | +0.006 |
Neg logit contributions | |
ucks | -0.008 |
til | -0.008 |
pret | -0.007 |
ours | -0.007 |
Tracy | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
til | +0.006 |
ucks | +0.006 |
pret | +0.005 |
name | +0.005 |
Tracy | +0.005 |
Neg logit contributions | |
no | -0.003 |
unatt | -0.003 |
jected | -0.003 |
fore | -0.003 |
course | -0.003 |
Token | see |
Token ID | 766 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
no | +0.028 |
unatt | +0.026 |
jected | +0.025 |
fore | +0.025 |
course | +0.024 |
Neg logit contributions | |
til | -0.022 |
ucks | -0.022 |
pret | -0.020 |
name | -0.019 |
Tracy | -0.018 |
Token | what |
Token ID | 644 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
no | +0.016 |
unatt | +0.014 |
fore | +0.013 |
course | +0.013 |
jected | +0.013 |
Neg logit contributions | |
ucks | -0.023 |
til | -0.023 |
pret | -0.021 |
name | -0.020 |
Tracy | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
til | +0.029 |
ucks | +0.028 |
pret | +0.027 |
name | +0.026 |
Tracy | +0.025 |
Neg logit contributions | |
unatt | -0.029 |
no | -0.029 |
jected | -0.028 |
fore | -0.026 |
iable | -0.026 |
Token | has |
Token ID | 468 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
no | +0.007 |
never | +0.007 |
unatt | +0.006 |
course | +0.006 |
fore | +0.006 |
Neg logit contributions | |
ucks | -0.010 |
til | -0.009 |
Tracy | -0.008 |
pret | -0.008 |
ours | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +4.41e-03 |
Pos logit contributions | |
no | +0.015 |
jected | +0.014 |
unatt | +0.014 |
Mic | +0.014 |
fore | +0.013 |
Neg logit contributions | |
ucks | -0.022 |
til | -0.022 |
pret | -0.021 |
name | -0.020 |
Tracy | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
til | +0.008 |
ucks | +0.008 |
pret | +0.008 |
name | +0.007 |
smell | +0.007 |
Neg logit contributions | |
no | -0.005 |
Jerry | -0.004 |
unatt | -0.004 |
course | -0.004 |
Once | -0.004 |
Token | ask |
Token ID | 1265 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
ucks | +0.027 |
til | +0.024 |
pret | +0.022 |
Tracy | +0.021 |
ours | +0.020 |
Neg logit contributions | |
no | -0.030 |
never | -0.026 |
course | -0.025 |
fore | -0.025 |
unatt | -0.025 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
til | +0.102 |
ucks | +0.101 |
pret | +0.096 |
name | +0.092 |
Tracy | +0.089 |
Neg logit contributions | |
no | -0.093 |
unatt | -0.093 |
jected | -0.092 |
fore | -0.085 |
vern | -0.082 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
no | +0.045 |
unatt | +0.042 |
fore | +0.039 |
Jerry | +0.038 |
course | +0.037 |
Neg logit contributions | |
til | -0.058 |
ucks | -0.057 |
name | -0.053 |
Tracy | -0.052 |
pret | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
til | +0.023 |
pret | +0.021 |
name | +0.020 |
ucks | +0.020 |
Tracy | +0.020 |
Neg logit contributions | |
unatt | -0.011 |
jected | -0.010 |
fore | -0.010 |
iable | -0.009 |
vern | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
no | +0.032 |
unatt | +0.028 |
jected | +0.026 |
fore | +0.025 |
course | +0.024 |
Neg logit contributions | |
ucks | -0.057 |
til | -0.057 |
pret | -0.054 |
name | -0.051 |
Tracy | -0.050 |
Token | sail |
Token ID | 14936 |
Feature activation | -9.12e-03 |
Pos logit contributions | |
no | +0.029 |
unatt | +0.026 |
jected | +0.025 |
fore | +0.025 |
course | +0.024 |
Neg logit contributions | |
til | -0.034 |
ucks | -0.034 |
pret | -0.032 |
name | -0.030 |
Tracy | -0.029 |
Token | got |
Token ID | 1392 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
no | +0.013 |
unatt | +0.013 |
vern | +0.013 |
iable | +0.012 |
Mic | +0.012 |
Neg logit contributions | |
til | -0.013 |
ucks | -0.012 |
pret | -0.012 |
name | -0.012 |
smell | -0.011 |
Token | torn |
Token ID | 12445 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
no | +0.027 |
unatt | +0.026 |
jected | +0.024 |
course | +0.024 |
fore | +0.024 |
Neg logit contributions | |
til | -0.031 |
ucks | -0.031 |
pret | -0.029 |
name | -0.027 |
Tracy | -0.026 |
Token | away |
Token ID | 1497 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
Mic | +0.104 |
no | +0.104 |
Fred | +0.103 |
vern | +0.102 |
course | +0.102 |
Neg logit contributions | |
til | -0.093 |
pret | -0.086 |
ucks | -0.083 |
name | -0.080 |
smell | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
Mic | +0.063 |
jected | +0.059 |
iable | +0.057 |
P | +0.057 |
unatt | +0.056 |
Neg logit contributions | |
til | -0.054 |
smell | -0.048 |
ucks | -0.048 |
pret | -0.047 |
name | -0.047 |
Token | The |
Token ID | 383 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
no | +0.016 |
unatt | +0.015 |
jected | +0.014 |
fore | +0.014 |
course | +0.014 |
Neg logit contributions | |
til | -0.020 |
ucks | -0.019 |
pret | -0.018 |
name | -0.018 |
Tracy | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
ucks | +0.002 |
til | +0.002 |
pret | +0.002 |
name | +0.002 |
Tracy | +0.002 |
Neg logit contributions | |
no | -0.002 |
unatt | -0.002 |
jected | -0.001 |
fore | -0.001 |
course | -0.001 |
Token | called |
Token ID | 1444 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
til | +0.071 |
ucks | +0.070 |
pret | +0.066 |
name | +0.062 |
Tracy | +0.059 |
Neg logit contributions | |
no | -0.064 |
unatt | -0.059 |
jected | -0.056 |
fore | -0.056 |
course | -0.054 |
Token | new |
Token ID | 649 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
no | +0.029 |
unatt | +0.027 |
jected | +0.025 |
fore | +0.025 |
course | +0.024 |
Neg logit contributions | |
til | -0.035 |
ucks | -0.035 |
pret | -0.033 |
name | -0.031 |
Tracy | -0.030 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
no | +0.006 |
fore | +0.005 |
unatt | +0.005 |
course | +0.005 |
Jerry | +0.005 |
Neg logit contributions | |
til | -0.010 |
ucks | -0.010 |
pret | -0.009 |
Tracy | -0.009 |
ours | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
no | +0.038 |
jected | +0.036 |
fore | +0.036 |
unatt | +0.035 |
vern | +0.034 |
Neg logit contributions | |
til | -0.044 |
ucks | -0.043 |
pret | -0.042 |
name | -0.040 |
Tracy | -0.038 |
Token | day |
Token ID | 1110 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
no | +0.029 |
unatt | +0.027 |
jected | +0.026 |
Mic | +0.026 |
vern | +0.026 |
Neg logit contributions | |
til | -0.026 |
ucks | -0.025 |
pret | -0.024 |
name | -0.023 |
Tracy | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
til | +0.027 |
name | +0.023 |
pret | +0.023 |
Tracy | +0.022 |
curiously | +0.022 |
Neg logit contributions | |
unatt | -0.028 |
fore | -0.028 |
course | -0.028 |
jected | -0.028 |
asure | -0.027 |
Token | From |
Token ID | 3574 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
no | +0.025 |
unatt | +0.024 |
jected | +0.022 |
fore | +0.022 |
iable | +0.021 |
Neg logit contributions | |
ucks | -0.029 |
til | -0.028 |
pret | -0.026 |
name | -0.026 |
Tracy | -0.024 |
Token | then |
Token ID | 788 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
no | +0.055 |
unatt | +0.048 |
jected | +0.045 |
fore | +0.044 |
course | +0.042 |
Neg logit contributions | |
ucks | -0.105 |
til | -0.104 |
pret | -0.099 |
name | -0.094 |
Tracy | -0.091 |
Token | on |
Token ID | 319 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
til | +0.065 |
pret | +0.059 |
name | +0.058 |
ucks | +0.057 |
Tracy | +0.051 |
Neg logit contributions | |
unatt | -0.084 |
vern | -0.079 |
no | -0.076 |
iable | -0.074 |
Mic | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
unatt | +0.047 |
vern | +0.043 |
jected | +0.041 |
asure | +0.041 |
iable | +0.040 |
Neg logit contributions | |
til | -0.070 |
Randy | -0.063 |
pret | -0.063 |
name | -0.061 |
Tracy | -0.060 |
Token | he |
Token ID | 339 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
unatt | +0.028 |
jected | +0.027 |
vern | +0.027 |
no | +0.026 |
fore | +0.026 |
Neg logit contributions | |
til | -0.039 |
ucks | -0.036 |
pret | -0.035 |
name | -0.035 |
Tracy | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.029 |
jected | +0.027 |
fore | +0.026 |
vern | +0.026 |
Neg logit contributions | |
til | -0.039 |
ucks | -0.038 |
pret | -0.036 |
name | -0.034 |
Tracy | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
no | +0.010 |
unatt | +0.009 |
jected | +0.009 |
fore | +0.009 |
course | +0.008 |
Neg logit contributions | |
til | -0.014 |
ucks | -0.013 |
pret | -0.013 |
name | -0.012 |
Tracy | -0.012 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
no | +0.009 |
unatt | +0.008 |
jected | +0.008 |
fore | +0.008 |
vern | +0.008 |
Neg logit contributions | |
til | -0.010 |
ucks | -0.010 |
pret | -0.009 |
name | -0.009 |
Tracy | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
unatt | +0.076 |
jected | +0.072 |
no | +0.070 |
Mic | +0.067 |
ross | +0.063 |
Neg logit contributions | |
til | -0.126 |
ucks | -0.121 |
name | -0.117 |
pret | -0.117 |
Tracy | -0.108 |
Token | helping |
Token ID | 5742 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
til | +0.048 |
ucks | +0.047 |
pret | +0.045 |
name | +0.042 |
Tracy | +0.040 |
Neg logit contributions | |
no | -0.041 |
unatt | -0.039 |
jected | -0.039 |
fore | -0.037 |
vern | -0.036 |
Token | each |
Token ID | 1123 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
ucks | +0.010 |
til | +0.010 |
name | +0.009 |
pret | +0.009 |
Tracy | +0.008 |
Neg logit contributions | |
no | -0.007 |
unatt | -0.007 |
jected | -0.007 |
vern | -0.006 |
fore | -0.006 |
Token | other |
Token ID | 584 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
unatt | +0.026 |
no | +0.026 |
jected | +0.026 |
gh | +0.024 |
iable | +0.024 |
Neg logit contributions | |
til | -0.035 |
name | -0.034 |
ucks | -0.034 |
pret | -0.033 |
smell | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
no | +0.075 |
unatt | +0.069 |
jected | +0.066 |
fore | +0.066 |
course | +0.063 |
Neg logit contributions | |
til | -0.078 |
ucks | -0.077 |
pret | -0.072 |
name | -0.068 |
Tracy | -0.065 |
Token | better |
Token ID | 1365 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
unatt | +0.012 |
jected | +0.012 |
no | +0.012 |
course | +0.011 |
Mic | +0.011 |
Neg logit contributions | |
til | -0.017 |
ucks | -0.016 |
name | -0.016 |
pret | -0.016 |
smell | -0.015 |
Token | than |
Token ID | 621 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ucks | +0.023 |
til | +0.023 |
pret | +0.022 |
name | +0.021 |
ora | +0.019 |
Neg logit contributions | |
unatt | -0.023 |
no | -0.023 |
jected | -0.023 |
Mic | -0.022 |
iable | -0.022 |
Token | trying |
Token ID | 2111 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
jected | +0.037 |
P | +0.034 |
unatt | +0.033 |
gh | +0.033 |
His | +0.033 |
Neg logit contributions | |
til | -0.039 |
pret | -0.037 |
smell | -0.035 |
name | -0.034 |
ucks | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
til | +0.031 |
name | +0.029 |
pret | +0.028 |
ucks | +0.027 |
lands | +0.026 |
Neg logit contributions | |
jected | -0.028 |
unatt | -0.027 |
Mic | -0.025 |
no | -0.025 |
course | -0.025 |
Token | You |
Token ID | 921 |
Feature activation | -9.58e-04 |
Pos logit contributions | |
no | +0.023 |
unatt | +0.022 |
fore | +0.020 |
jected | +0.020 |
iable | +0.019 |
Neg logit contributions | |
ucks | -0.030 |
til | -0.029 |
pret | -0.027 |
name | -0.027 |
Tracy | -0.025 |
Token | are |
Token ID | 389 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
unatt | +0.001 |
no | +0.001 |
ross | +0.001 |
gh | +0.001 |
His | +0.001 |
Neg logit contributions | |
til | -0.002 |
name | -0.002 |
pret | -0.002 |
smell | -0.001 |
ucks | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
unatt | +0.053 |
no | +0.052 |
jected | +0.049 |
fore | +0.047 |
iable | +0.046 |
Neg logit contributions | |
til | -0.083 |
name | -0.078 |
pret | -0.077 |
ucks | -0.077 |
Tracy | -0.073 |
Token | best |
Token ID | 1266 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
no | +0.019 |
unatt | +0.018 |
jected | +0.017 |
fore | +0.016 |
vern | +0.015 |
Neg logit contributions | |
til | -0.038 |
ucks | -0.037 |
pret | -0.036 |
name | -0.035 |
Tracy | -0.033 |
Token | ride |
Token ID | 6594 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
no | +0.045 |
unatt | +0.040 |
fore | +0.038 |
jected | +0.038 |
course | +0.037 |
Neg logit contributions | |
ucks | -0.057 |
til | -0.057 |
pret | -0.053 |
name | -0.049 |
Tracy | -0.049 |
Token | ever |
Token ID | 1683 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
unatt | +0.012 |
no | +0.011 |
fore | +0.011 |
Mic | +0.011 |
vern | +0.011 |
Neg logit contributions | |
ucks | -0.023 |
til | -0.023 |
pret | -0.022 |
name | -0.022 |
Tracy | -0.020 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.12e-03 |
Pos logit contributions | |
no | +0.084 |
unatt | +0.079 |
fore | +0.076 |
jected | +0.075 |
vern | +0.074 |
Neg logit contributions | |
til | -0.086 |
ucks | -0.084 |
pret | -0.080 |
name | -0.076 |
ora | -0.072 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
til | +0.010 |
ucks | +0.010 |
pret | +0.009 |
name | +0.009 |
Tracy | +0.009 |
Neg logit contributions | |
no | -0.008 |
unatt | -0.008 |
jected | -0.007 |
fore | -0.007 |
vern | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
til | +0.132 |
ucks | +0.130 |
pret | +0.124 |
name | +0.114 |
Tracy | +0.113 |
Neg logit contributions | |
no | -0.089 |
unatt | -0.078 |
fore | -0.075 |
jected | -0.075 |
course | -0.073 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
til | +0.020 |
ucks | +0.020 |
pret | +0.017 |
name | +0.016 |
Tracy | +0.015 |
Neg logit contributions | |
no | -0.049 |
unatt | -0.047 |
jected | -0.046 |
fore | -0.045 |
course | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +5.98e-03 |
Pos logit contributions | |
ucks | +0.059 |
til | +0.058 |
pret | +0.055 |
name | +0.052 |
Tracy | +0.051 |
Neg logit contributions | |
no | -0.029 |
unatt | -0.025 |
jected | -0.023 |
fore | -0.023 |
course | -0.022 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
no | +0.079 |
unatt | +0.076 |
jected | +0.074 |
fore | +0.070 |
vern | +0.069 |
Neg logit contributions | |
til | -0.090 |
ucks | -0.082 |
pret | -0.080 |
name | -0.075 |
Tracy | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ucks | +0.038 |
til | +0.038 |
pret | +0.036 |
name | +0.035 |
Tracy | +0.034 |
Neg logit contributions | |
no | -0.015 |
unatt | -0.013 |
jected | -0.012 |
fore | -0.012 |
course | -0.011 |
Token | Tim |
Token ID | 5045 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
no | +0.026 |
unatt | +0.025 |
jected | +0.024 |
fore | +0.023 |
vern | +0.022 |
Neg logit contributions | |
til | -0.047 |
ucks | -0.046 |
pret | -0.044 |
name | -0.042 |
Tracy | -0.041 |
Token | my |
Token ID | 1820 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
no | +0.064 |
unatt | +0.059 |
jected | +0.055 |
fore | +0.055 |
course | +0.053 |
Neg logit contributions | |
til | -0.090 |
ucks | -0.089 |
pret | -0.084 |
name | -0.080 |
Tracy | -0.077 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
no | +0.004 |
unatt | +0.004 |
jected | +0.003 |
fore | +0.003 |
course | +0.003 |
Neg logit contributions | |
til | -0.004 |
ucks | -0.004 |
pret | -0.004 |
name | -0.004 |
Tracy | -0.004 |
Token | broke |
Token ID | 6265 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
no | +0.031 |
unatt | +0.029 |
jected | +0.028 |
fore | +0.027 |
course | +0.027 |
Neg logit contributions | |
til | -0.032 |
ucks | -0.031 |
pret | -0.030 |
name | -0.028 |
Tracy | -0.026 |
Token | his |
Token ID | 465 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
jected | +0.088 |
unatt | +0.088 |
no | +0.084 |
vern | +0.084 |
iable | +0.078 |
Neg logit contributions | |
ucks | -0.113 |
til | -0.110 |
pret | -0.105 |
name | -0.097 |
Tracy | -0.097 |
Token | new |
Token ID | 649 |
Feature activation | -7.66e-03 |
Pos logit contributions | |
no | +0.035 |
unatt | +0.032 |
jected | +0.032 |
fore | +0.030 |
course | +0.030 |
Neg logit contributions | |
til | -0.041 |
ucks | -0.040 |
pret | -0.039 |
name | -0.037 |
Tracy | -0.034 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
no | +0.009 |
unatt | +0.008 |
fore | +0.008 |
jected | +0.008 |
course | +0.008 |
Neg logit contributions | |
ucks | -0.014 |
til | -0.014 |
pret | -0.013 |
name | -0.012 |
Tracy | -0.012 |
Token | soldier |
Token ID | 10686 |
Feature activation | +8.31e-03 |
Pos logit contributions | |
vern | +0.033 |
jected | +0.032 |
fore | +0.032 |
Fred | +0.031 |
unatt | +0.031 |
Neg logit contributions | |
pret | -0.033 |
til | -0.033 |
ucks | -0.032 |
name | -0.031 |
smell | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
til | +0.014 |
pret | +0.013 |
name | +0.012 |
ucks | +0.012 |
smell | +0.011 |
Neg logit contributions | |
no | -0.010 |
vern | -0.010 |
jected | -0.009 |
unatt | -0.009 |
fore | -0.009 |