Token |
|
Token ID | 198 |
Feature activation | +3.10e-03 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.007 |
ymes | +0.007 |
able | +0.007 |
iffs | +0.007 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.002 |
Jack | -0.002 |
int | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
ymes | +0.007 |
aking | +0.006 |
ang | +0.006 |
asc | +0.006 |
rying | +0.006 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
um | -0.004 |
finally | -0.004 |
Jack | -0.004 |
Token | cat |
Token ID | 3797 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
aking | +0.005 |
ang | +0.004 |
iffs | +0.004 |
ymes | +0.004 |
beh | +0.004 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
one | -0.003 |
King | -0.003 |
Token | grinned |
Token ID | 36268 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
aking | +0.073 |
ang | +0.069 |
ymes | +0.067 |
able | +0.062 |
iffs | +0.061 |
Neg logit contributions | |
Daddy | -0.037 |
mummy | -0.034 |
Peter | -0.033 |
Jack | -0.031 |
int | -0.031 |
Token | mis |
Token ID | 2984 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
Daddy | +0.038 |
oph | +0.036 |
mummy | +0.036 |
Peter | +0.035 |
Jenna | +0.034 |
Neg logit contributions | |
aking | -0.064 |
ang | -0.059 |
ymes | -0.056 |
able | -0.053 |
aring | -0.051 |
Token | chie |
Token ID | 3043 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
iffs | +0.088 |
ymes | +0.083 |
arl | +0.081 |
aking | +0.080 |
Deal | +0.077 |
Neg logit contributions | |
even | -0.136 |
der | -0.135 |
int | -0.133 |
written | -0.133 |
um | -0.133 |
Token | v |
Token ID | 85 |
Feature activation | -7.44e-03 |
Pos logit contributions | |
aking | +0.149 |
ang | +0.135 |
ymes | +0.129 |
iffs | +0.109 |
able | +0.105 |
Neg logit contributions | |
Daddy | -0.293 |
mummy | -0.285 |
Peter | -0.282 |
Jack | -0.276 |
int | -0.275 |
Token | ously |
Token ID | 3481 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.011 |
Peter | +0.011 |
int | +0.011 |
Jack | +0.011 |
Neg logit contributions | |
aking | -0.015 |
ang | -0.014 |
ymes | -0.013 |
able | -0.012 |
iffs | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
aking | +0.053 |
ang | +0.050 |
aring | +0.046 |
able | +0.045 |
cautious | +0.045 |
Neg logit contributions | |
Daddy | -0.030 |
mummy | -0.028 |
oph | -0.027 |
Peter | -0.027 |
Jason | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
aking | +0.017 |
ang | +0.016 |
ymes | +0.015 |
iffs | +0.015 |
itty | +0.014 |
Neg logit contributions | |
Daddy | -0.008 |
mummy | -0.008 |
oph | -0.007 |
Peter | -0.007 |
int | -0.007 |
Token | Never |
Token ID | 12295 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
aking | +0.070 |
ang | +0.065 |
ymes | +0.064 |
iffs | +0.057 |
aring | +0.057 |
Neg logit contributions | |
Daddy | -0.065 |
mummy | -0.062 |
Peter | -0.061 |
written | -0.061 |
finally | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
aking | +0.104 |
ang | +0.098 |
ymes | +0.093 |
able | +0.089 |
aring | +0.087 |
Neg logit contributions | |
Daddy | -0.049 |
int | -0.047 |
mummy | -0.045 |
der | -0.045 |
written | -0.043 |
Token | Rover |
Token ID | 36718 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
aking | +0.018 |
ymes | +0.017 |
ang | +0.017 |
able | +0.015 |
iffs | +0.015 |
Neg logit contributions | |
Daddy | -0.014 |
mummy | -0.013 |
Peter | -0.013 |
Jack | -0.013 |
der | -0.012 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
aking | +0.099 |
ang | +0.095 |
ymes | +0.093 |
iffs | +0.087 |
arl | +0.084 |
Neg logit contributions | |
Daddy | -0.039 |
Peter | -0.037 |
mummy | -0.037 |
Jack | -0.036 |
King | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Daddy | +0.021 |
mummy | +0.020 |
Peter | +0.019 |
int | +0.018 |
der | +0.018 |
Neg logit contributions | |
aking | -0.054 |
ang | -0.053 |
ymes | -0.050 |
able | -0.049 |
iffs | -0.047 |
Token | Wh |
Token ID | 854 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
aking | +0.044 |
ang | +0.043 |
ymes | +0.039 |
able | +0.037 |
iffs | +0.035 |
Neg logit contributions | |
Daddy | -0.048 |
mummy | -0.047 |
int | -0.046 |
der | -0.045 |
oph | -0.045 |
Token | isk |
Token ID | 1984 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
aking | +0.074 |
ang | +0.067 |
ymes | +0.066 |
able | +0.057 |
ites | +0.057 |
Neg logit contributions | |
der | -0.092 |
oph | -0.090 |
um | -0.088 |
Daddy | -0.086 |
Peter | -0.085 |
Token | ers |
Token ID | 364 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
ang | +0.271 |
aking | +0.264 |
etchup | +0.231 |
unnecessary | +0.228 |
ites | +0.228 |
Neg logit contributions | |
der | -0.132 |
Jack | -0.127 |
aloud | -0.125 |
King | -0.124 |
um | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
aking | +0.018 |
ang | +0.016 |
ymes | +0.014 |
aring | +0.014 |
ighed | +0.014 |
Neg logit contributions | |
Daddy | -0.012 |
mummy | -0.012 |
oph | -0.012 |
Father | -0.011 |
moons | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
aking | +0.037 |
ang | +0.036 |
iffs | +0.033 |
ymes | +0.032 |
itty | +0.031 |
Neg logit contributions | |
Daddy | -0.018 |
mummy | -0.018 |
Peter | -0.017 |
oph | -0.016 |
int | -0.016 |
Token | You |
Token ID | 1639 |
Feature activation | +9.07e-04 |
Pos logit contributions | |
aking | +0.064 |
ang | +0.060 |
ymes | +0.057 |
able | +0.050 |
iffs | +0.050 |
Neg logit contributions | |
Daddy | -0.079 |
Peter | -0.076 |
mummy | -0.076 |
Jack | -0.075 |
written | -0.075 |
Token | are |
Token ID | 389 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
aking | +0.002 |
ang | +0.002 |
ymes | +0.002 |
able | +0.002 |
trap | +0.002 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
int | -0.001 |
Peter | -0.001 |
der | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
Daddy | +0.003 |
oph | +0.003 |
mummy | +0.003 |
written | +0.003 |
int | +0.003 |
Neg logit contributions | |
aking | -0.010 |
ang | -0.009 |
ymes | -0.009 |
able | -0.009 |
iffs | -0.008 |
Token | El |
Token ID | 2574 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
aking | +0.018 |
ang | +0.017 |
ymes | +0.017 |
able | +0.015 |
iffs | +0.015 |
Neg logit contributions | |
Daddy | -0.010 |
mummy | -0.009 |
Peter | -0.009 |
Jack | -0.009 |
der | -0.009 |
Token | p |
Token ID | 79 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
aking | +0.056 |
iffs | +0.053 |
arl | +0.050 |
beh | +0.050 |
property | +0.048 |
Neg logit contributions | |
mummy | -0.048 |
Daddy | -0.048 |
oph | -0.047 |
int | -0.045 |
one | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | -3.81e-04 |
Pos logit contributions | |
aking | +0.031 |
ang | +0.029 |
ymes | +0.028 |
able | +0.027 |
iffs | +0.026 |
Neg logit contributions | |
Daddy | -0.015 |
mummy | -0.014 |
Peter | -0.013 |
int | -0.013 |
der | -0.013 |
Token | known |
Token ID | 1900 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.000 |
Peter | +0.000 |
Jack | +0.000 |
int | +0.000 |
Neg logit contributions | |
aking | -0.001 |
ang | -0.001 |
ymes | -0.001 |
iffs | -0.001 |
able | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
aking | +0.018 |
ang | +0.017 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.016 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.006 |
Peter | -0.006 |
Jack | -0.005 |
der | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
aking | +0.283 |
ang | +0.267 |
ymes | +0.260 |
able | +0.242 |
iffs | +0.239 |
Neg logit contributions | |
Daddy | -0.147 |
mummy | -0.139 |
Peter | -0.134 |
Jack | -0.128 |
der | -0.127 |
Token | most |
Token ID | 749 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
aking | +0.039 |
ang | +0.037 |
ymes | +0.035 |
iffs | +0.034 |
ites | +0.032 |
Neg logit contributions | |
Daddy | -0.035 |
mummy | -0.035 |
Peter | -0.032 |
King | -0.031 |
int | -0.031 |
Token | brave |
Token ID | 14802 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
aking | +0.019 |
iffs | +0.017 |
ymes | +0.017 |
ang | +0.017 |
ighed | +0.016 |
Neg logit contributions | |
Daddy | -0.022 |
mummy | -0.022 |
der | -0.020 |
even | -0.020 |
Peter | -0.020 |
Token | pony |
Token ID | 26902 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
aking | +0.025 |
ang | +0.023 |
ymes | +0.022 |
iffs | +0.020 |
able | +0.020 |
Neg logit contributions | |
Daddy | -0.021 |
mummy | -0.020 |
Peter | -0.020 |
Jack | -0.019 |
der | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
aking | +0.064 |
ang | +0.060 |
ymes | +0.059 |
able | +0.055 |
iffs | +0.054 |
Neg logit contributions | |
Daddy | -0.033 |
mummy | -0.031 |
Peter | -0.030 |
Jack | -0.028 |
der | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
mummy | +0.021 |
oph | +0.021 |
Daddy | +0.020 |
Father | +0.019 |
King | +0.019 |
Neg logit contributions | |
aking | -0.025 |
ang | -0.021 |
able | -0.021 |
ymes | -0.020 |
aring | -0.020 |
Token | unlock |
Token ID | 12116 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
aking | +0.014 |
ang | +0.013 |
ymes | +0.012 |
trap | +0.012 |
able | +0.012 |
Neg logit contributions | |
Daddy | -0.014 |
der | -0.014 |
mummy | -0.013 |
Peter | -0.013 |
int | -0.013 |
Token | ," |
Token ID | 553 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
Daddy | +0.016 |
mummy | +0.015 |
oph | +0.015 |
int | +0.015 |
Peter | +0.015 |
Neg logit contributions | |
aking | -0.028 |
ang | -0.027 |
ymes | -0.026 |
able | -0.024 |
iffs | -0.024 |
Token | said |
Token ID | 531 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Daddy | +0.031 |
mummy | +0.029 |
Peter | +0.027 |
der | +0.027 |
int | +0.027 |
Neg logit contributions | |
aking | -0.088 |
ang | -0.086 |
ymes | -0.083 |
able | -0.079 |
iffs | -0.077 |
Token | Wh |
Token ID | 854 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
aking | +0.035 |
ang | +0.034 |
ymes | +0.032 |
able | +0.030 |
iffs | +0.029 |
Neg logit contributions | |
Daddy | -0.031 |
mummy | -0.030 |
int | -0.029 |
der | -0.029 |
Peter | -0.029 |
Token | isk |
Token ID | 1984 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
aking | +0.071 |
ang | +0.065 |
ymes | +0.063 |
able | +0.055 |
ites | +0.054 |
Neg logit contributions | |
oph | -0.094 |
der | -0.093 |
Daddy | -0.092 |
um | -0.091 |
Peter | -0.089 |
Token | ers |
Token ID | 364 |
Feature activation | +5.76e-03 |
Pos logit contributions | |
ang | +0.260 |
aking | +0.252 |
etchup | +0.218 |
ites | +0.217 |
ymes | +0.215 |
Neg logit contributions | |
der | -0.143 |
aloud | -0.143 |
Jack | -0.139 |
written | -0.137 |
Peter | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
aking | +0.012 |
ang | +0.010 |
ymes | +0.010 |
aring | +0.010 |
cautious | +0.010 |
Neg logit contributions | |
Daddy | -0.008 |
oph | -0.008 |
moons | -0.008 |
mummy | -0.008 |
moon | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
aking | +0.015 |
ang | +0.014 |
ymes | +0.013 |
iffs | +0.013 |
able | +0.012 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.006 |
Peter | -0.006 |
int | -0.006 |
Jack | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.57e-03 |
Pos logit contributions | |
Daddy | +0.002 |
mummy | +0.002 |
Peter | +0.002 |
Jack | +0.002 |
um | +0.002 |
Neg logit contributions | |
aking | -0.007 |
ymes | -0.007 |
ang | -0.007 |
able | -0.006 |
beh | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
um | +0.005 |
replied | +0.005 |
finally | +0.005 |
one | +0.005 |
then | +0.005 |
Neg logit contributions | |
aking | -0.006 |
ymes | -0.006 |
asc | -0.006 |
rying | -0.005 |
ang | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
oph | +0.001 |
Daddy | +0.001 |
der | +0.001 |
int | +0.001 |
written | +0.001 |
Neg logit contributions | |
aking | -0.002 |
ang | -0.002 |
ymes | -0.002 |
able | -0.002 |
itty | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
aking | +0.011 |
ang | +0.011 |
ymes | +0.011 |
able | +0.010 |
iffs | +0.010 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
der | -0.003 |
int | -0.003 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
aking | +0.011 |
ang | +0.011 |
ymes | +0.010 |
iffs | +0.010 |
beh | +0.010 |
Neg logit contributions | |
mummy | -0.007 |
Daddy | -0.006 |
Peter | -0.006 |
King | -0.006 |
moon | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -3.69e-04 |
Pos logit contributions | |
aking | +0.070 |
ang | +0.066 |
ymes | +0.065 |
iffs | +0.060 |
able | +0.060 |
Neg logit contributions | |
Daddy | -0.033 |
mummy | -0.032 |
Peter | -0.030 |
Jack | -0.029 |
der | -0.029 |
Token | known |
Token ID | 1900 |
Feature activation | +8.17e-03 |
Pos logit contributions | |
Daddy | +0.000 |
mummy | +0.000 |
Peter | +0.000 |
Jack | +0.000 |
even | +0.000 |
Neg logit contributions | |
aking | -0.001 |
ymes | -0.001 |
ang | -0.001 |
iffs | -0.001 |
able | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
aking | +0.022 |
ang | +0.021 |
ymes | +0.020 |
able | +0.019 |
iffs | +0.019 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.007 |
Peter | -0.006 |
Jack | -0.006 |
der | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
aking | +0.274 |
ang | +0.257 |
ymes | +0.250 |
able | +0.234 |
iffs | +0.228 |
Neg logit contributions | |
Daddy | -0.151 |
mummy | -0.143 |
Peter | -0.137 |
der | -0.134 |
int | -0.133 |
Token | friendly |
Token ID | 8030 |
Feature activation | +3.91e-04 |
Pos logit contributions | |
aking | +0.043 |
ang | +0.042 |
ymes | +0.039 |
iffs | +0.039 |
ites | +0.036 |
Neg logit contributions | |
mummy | -0.041 |
Daddy | -0.040 |
King | -0.039 |
moon | -0.038 |
Peter | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +7.07e-03 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.001 |
ymes | +0.001 |
iffs | +0.001 |
able | +0.001 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
Peter | -0.001 |
Jack | -0.001 |
der | -0.001 |
Token | smiling |
Token ID | 16755 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
aking | +0.016 |
ang | +0.016 |
ymes | +0.015 |
iffs | +0.014 |
able | +0.014 |
Neg logit contributions | |
Daddy | -0.009 |
mummy | -0.009 |
Peter | -0.009 |
Jack | -0.008 |
int | -0.008 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Daddy | +0.033 |
mummy | +0.031 |
Peter | +0.030 |
Jack | +0.029 |
der | +0.029 |
Neg logit contributions | |
aking | -0.067 |
ang | -0.063 |
ymes | -0.061 |
able | -0.057 |
iffs | -0.057 |
Token | on |
Token ID | 319 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
aking | +0.066 |
ang | +0.061 |
ymes | +0.059 |
able | +0.054 |
iffs | +0.053 |
Neg logit contributions | |
Daddy | -0.055 |
mummy | -0.053 |
Peter | -0.051 |
Jack | -0.050 |
der | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +7.70e-03 |
Pos logit contributions | |
Daddy | +0.003 |
int | +0.003 |
der | +0.003 |
oph | +0.003 |
mummy | +0.003 |
Neg logit contributions | |
aking | -0.008 |
ang | -0.007 |
ymes | -0.007 |
able | -0.007 |
itty | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
aking | +0.019 |
ang | +0.018 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.016 |
Neg logit contributions | |
Daddy | -0.009 |
mummy | -0.008 |
Peter | -0.008 |
der | -0.008 |
int | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +6.62e-04 |
Pos logit contributions | |
aking | +0.067 |
ang | +0.063 |
ymes | +0.060 |
able | +0.057 |
iffs | +0.055 |
Neg logit contributions | |
Daddy | -0.038 |
mummy | -0.036 |
Peter | -0.035 |
int | -0.033 |
der | -0.033 |
Token | known |
Token ID | 1900 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
aking | +0.002 |
ymes | +0.002 |
ang | +0.002 |
iffs | +0.001 |
able | +0.001 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
Peter | -0.001 |
even | -0.001 |
Jack | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
aking | +0.016 |
ang | +0.015 |
ymes | +0.014 |
able | +0.014 |
iffs | +0.013 |
Neg logit contributions | |
Daddy | -0.006 |
mummy | -0.005 |
Peter | -0.005 |
der | -0.005 |
Jack | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
aking | +0.281 |
ang | +0.266 |
ymes | +0.257 |
able | +0.239 |
iffs | +0.238 |
Neg logit contributions | |
Daddy | -0.149 |
mummy | -0.140 |
Peter | -0.136 |
Jack | -0.130 |
der | -0.127 |
Token | powerful |
Token ID | 3665 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
aking | +0.046 |
ang | +0.044 |
ymes | +0.041 |
iffs | +0.040 |
ites | +0.038 |
Neg logit contributions | |
Daddy | -0.044 |
mummy | -0.044 |
King | -0.041 |
Peter | -0.040 |
father | -0.039 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Daddy | +0.017 |
mummy | +0.016 |
Peter | +0.016 |
Jack | +0.015 |
der | +0.015 |
Neg logit contributions | |
aking | -0.021 |
ang | -0.020 |
ymes | -0.019 |
iffs | -0.017 |
able | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
aking | +0.053 |
ang | +0.050 |
ymes | +0.049 |
iffs | +0.046 |
able | +0.045 |
Neg logit contributions | |
Daddy | -0.031 |
mummy | -0.029 |
Peter | -0.029 |
Jack | -0.028 |
der | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
aking | +0.047 |
ang | +0.045 |
ymes | +0.041 |
iffs | +0.040 |
able | +0.040 |
Neg logit contributions | |
Daddy | -0.026 |
int | -0.025 |
mummy | -0.025 |
der | -0.024 |
oph | -0.024 |
Token | Ch |
Token ID | 609 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.003 |
ymes | +0.003 |
iffs | +0.003 |
able | +0.003 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
oph | -0.003 |
int | -0.003 |
Peter | -0.003 |
Token | ir |
Token ID | 343 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
aking | +0.016 |
ymes | +0.015 |
ang | +0.013 |
respectful | +0.013 |
iffs | +0.013 |
Neg logit contributions | |
der | -0.018 |
um | -0.018 |
Daddy | -0.018 |
mummy | -0.017 |
Peter | -0.017 |
Token | py |
Token ID | 9078 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
aking | +0.020 |
ang | +0.018 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.015 |
Neg logit contributions | |
Daddy | -0.018 |
mummy | -0.017 |
Peter | -0.017 |
Jack | -0.016 |
int | -0.016 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
aking | +0.084 |
ang | +0.079 |
ymes | +0.079 |
iffs | +0.074 |
able | +0.073 |
Neg logit contributions | |
Daddy | -0.030 |
mummy | -0.029 |
Peter | -0.028 |
Jack | -0.026 |
der | -0.026 |
Token | Wh |
Token ID | 854 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
Daddy | +0.019 |
mummy | +0.018 |
Peter | +0.018 |
Jack | +0.017 |
der | +0.017 |
Neg logit contributions | |
aking | -0.031 |
ang | -0.029 |
ymes | -0.029 |
able | -0.026 |
iffs | -0.026 |
Token | isk |
Token ID | 1984 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
aking | +0.066 |
ang | +0.062 |
ymes | +0.062 |
iffs | +0.056 |
ites | +0.053 |
Neg logit contributions | |
Peter | -0.088 |
der | -0.088 |
oph | -0.086 |
um | -0.086 |
Daddy | -0.084 |
Token | ers |
Token ID | 364 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
aking | +0.254 |
ang | +0.249 |
ymes | +0.223 |
ighed | +0.218 |
etchup | +0.215 |
Neg logit contributions | |
Peter | -0.144 |
King | -0.140 |
Jack | -0.139 |
der | -0.136 |
ilda | -0.131 |
Token | for |
Token ID | 329 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
aking | +0.020 |
ang | +0.019 |
ymes | +0.018 |
able | +0.017 |
iffs | +0.017 |
Neg logit contributions | |
Daddy | -0.009 |
mummy | -0.009 |
Peter | -0.008 |
der | -0.008 |
Jack | -0.008 |
Token | helping |
Token ID | 5742 |
Feature activation | +4.30e-03 |
Pos logit contributions | |
aking | +0.048 |
ang | +0.047 |
ymes | +0.046 |
able | +0.043 |
iffs | +0.042 |
Neg logit contributions | |
Peter | -0.026 |
Daddy | -0.026 |
Jack | -0.025 |
mummy | -0.025 |
finally | -0.024 |
Token | him |
Token ID | 683 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
aking | +0.012 |
ang | +0.011 |
ymes | +0.011 |
able | +0.010 |
iffs | +0.010 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.003 |
Peter | -0.003 |
Jack | -0.003 |
int | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
aking | +0.059 |
ang | +0.057 |
ymes | +0.056 |
able | +0.052 |
iffs | +0.051 |
Neg logit contributions | |
Daddy | -0.026 |
mummy | -0.024 |
Peter | -0.023 |
Jack | -0.022 |
int | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e-04 |
Pos logit contributions | |
Daddy | +0.032 |
mummy | +0.029 |
Peter | +0.027 |
Jack | +0.025 |
der | +0.025 |
Neg logit contributions | |
aking | -0.106 |
ang | -0.101 |
ymes | -0.098 |
able | -0.093 |
iffs | -0.092 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
Daddy | +0.000 |
mummy | +0.000 |
Peter | +0.000 |
Jack | +0.000 |
Father | +0.000 |
Neg logit contributions | |
aking | -0.001 |
ang | -0.001 |
ymes | -0.001 |
able | -0.001 |
iffs | -0.001 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.004 |
ymes | +0.004 |
able | +0.003 |
iffs | +0.003 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
Jack | -0.002 |
der | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
der | +0.046 |
oph | +0.043 |
um | +0.041 |
int | +0.041 |
cuc | +0.040 |
Neg logit contributions | |
aking | -0.061 |
ang | -0.061 |
Spot | -0.057 |
itty | -0.056 |
ymes | -0.055 |
Token | Wh |
Token ID | 854 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
ang | +0.033 |
aking | +0.033 |
ymes | +0.032 |
itty | +0.030 |
able | +0.030 |
Neg logit contributions | |
der | -0.021 |
int | -0.019 |
horizon | -0.019 |
oph | -0.018 |
moons | -0.018 |
Token | isk |
Token ID | 1984 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
aking | +0.089 |
ang | +0.087 |
ymes | +0.079 |
ites | +0.075 |
iffs | +0.074 |
Neg logit contributions | |
Daddy | -0.074 |
der | -0.071 |
Peter | -0.071 |
mummy | -0.070 |
oph | -0.070 |
Token | ers |
Token ID | 364 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
ang | +0.271 |
aking | +0.256 |
etchup | +0.232 |
arate | +0.225 |
ites | +0.223 |
Neg logit contributions | |
aloud | -0.133 |
King | -0.131 |
Peter | -0.129 |
der | -0.129 |
Jack | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
aking | +0.014 |
ang | +0.013 |
ymes | +0.013 |
aring | +0.012 |
respectful | +0.012 |
Neg logit contributions | |
Daddy | -0.008 |
mummy | -0.008 |
oph | -0.007 |
Jenna | -0.007 |
um | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
oph | +0.025 |
um | +0.025 |
Daddy | +0.024 |
mummy | +0.024 |
Peter | +0.023 |
Neg logit contributions | |
aking | -0.045 |
ang | -0.043 |
ymes | -0.040 |
iffs | -0.038 |
trap | -0.037 |
Token | Do |
Token ID | 5211 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
aking | +0.056 |
ang | +0.052 |
ymes | +0.050 |
able | +0.044 |
iffs | +0.044 |
Neg logit contributions | |
Daddy | -0.062 |
mummy | -0.060 |
Peter | -0.059 |
Jack | -0.057 |
int | -0.057 |
Token | you |
Token ID | 345 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
Daddy | +0.051 |
mummy | +0.049 |
Peter | +0.048 |
Jack | +0.047 |
der | +0.045 |
Neg logit contributions | |
aking | -0.052 |
ang | -0.048 |
ymes | -0.045 |
able | -0.041 |
iffs | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
Daddy | +0.009 |
mummy | +0.008 |
Peter | +0.008 |
Jack | +0.008 |
int | +0.008 |
Neg logit contributions | |
aking | -0.012 |
ymes | -0.012 |
ang | -0.012 |
iffs | -0.010 |
able | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-04 |
Pos logit contributions | |
Daddy | +0.003 |
mummy | +0.002 |
der | +0.002 |
int | +0.002 |
Peter | +0.002 |
Neg logit contributions | |
aking | -0.008 |
ang | -0.008 |
ymes | -0.007 |
able | -0.007 |
iffs | -0.007 |
Token | Jane |
Token ID | 12091 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.000 |
ymes | +0.000 |
able | +0.000 |
iffs | +0.000 |
Neg logit contributions | |
Daddy | -0.000 |
der | -0.000 |
mummy | -0.000 |
Peter | -0.000 |
int | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
Daddy | +0.008 |
mummy | +0.007 |
Peter | +0.007 |
int | +0.007 |
der | +0.007 |
Neg logit contributions | |
aking | -0.013 |
ang | -0.012 |
ymes | -0.012 |
able | -0.011 |
itty | -0.011 |
Token | known |
Token ID | 1900 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
Daddy | +0.002 |
mummy | +0.002 |
Peter | +0.002 |
Jack | +0.002 |
even | +0.002 |
Neg logit contributions | |
aking | -0.004 |
ang | -0.004 |
ymes | -0.004 |
iffs | -0.004 |
able | -0.004 |
Token | as |
Token ID | 355 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
aking | +0.014 |
ang | +0.013 |
ymes | +0.013 |
able | +0.012 |
iffs | +0.012 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
Jack | -0.003 |
int | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
aking | +0.276 |
ang | +0.258 |
ymes | +0.253 |
able | +0.238 |
iffs | +0.229 |
Neg logit contributions | |
Daddy | -0.144 |
mummy | -0.136 |
Peter | -0.131 |
der | -0.129 |
int | -0.128 |
Token | unlocking |
Token ID | 39052 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
aking | +0.045 |
ang | +0.043 |
ymes | +0.041 |
iffs | +0.040 |
ites | +0.036 |
Neg logit contributions | |
Daddy | -0.036 |
mummy | -0.036 |
Peter | -0.034 |
King | -0.034 |
Jack | -0.032 |
Token | z |
Token ID | 1976 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Daddy | +0.016 |
mummy | +0.015 |
Peter | +0.015 |
Jack | +0.014 |
int | +0.014 |
Neg logit contributions | |
aking | -0.024 |
ang | -0.022 |
ymes | -0.021 |
iffs | -0.020 |
able | -0.019 |
Token | ebra |
Token ID | 37052 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
aking | +0.021 |
ang | +0.019 |
ymes | +0.019 |
Spot | +0.018 |
able | +0.018 |
Neg logit contributions | |
um | -0.024 |
mummy | -0.023 |
Daddy | -0.023 |
der | -0.023 |
King | -0.022 |
Token | ! |
Token ID | 0 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
aking | +0.069 |
ang | +0.065 |
ymes | +0.063 |
able | +0.059 |
iffs | +0.058 |
Neg logit contributions | |
Daddy | -0.031 |
mummy | -0.029 |
Peter | -0.028 |
Jack | -0.026 |
der | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -9.87e-05 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.001 |
Peter | +0.001 |
Jack | +0.001 |
der | +0.001 |
Neg logit contributions | |
aking | -0.003 |
ang | -0.003 |
ymes | -0.003 |
able | -0.003 |
iffs | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
Daddy | +0.000 |
mummy | +0.000 |
der | +0.000 |
int | +0.000 |
Peter | +0.000 |
Neg logit contributions | |
aking | -0.000 |
ang | -0.000 |
ymes | -0.000 |
iffs | -0.000 |
able | -0.000 |
Token | vet |
Token ID | 20202 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.011 |
Peter | +0.011 |
der | +0.010 |
Jack | +0.010 |
Neg logit contributions | |
aking | -0.016 |
ang | -0.015 |
ymes | -0.015 |
iffs | -0.014 |
able | -0.013 |
Token | showed |
Token ID | 3751 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
aking | +0.061 |
ang | +0.057 |
ymes | +0.056 |
able | +0.052 |
iffs | +0.051 |
Neg logit contributions | |
Daddy | -0.028 |
mummy | -0.027 |
Peter | -0.026 |
der | -0.024 |
int | -0.024 |
Token | Wh |
Token ID | 854 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.011 |
Peter | +0.011 |
der | +0.010 |
int | +0.010 |
Neg logit contributions | |
aking | -0.023 |
ang | -0.022 |
ymes | -0.021 |
able | -0.020 |
iffs | -0.019 |
Token | isk |
Token ID | 1984 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ang | +0.063 |
aking | +0.063 |
ymes | +0.059 |
iffs | +0.058 |
ites | +0.054 |
Neg logit contributions | |
der | -0.085 |
ilda | -0.081 |
omm | -0.079 |
um | -0.079 |
Daddy | -0.079 |
Token | ers |
Token ID | 364 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
ang | +0.243 |
aking | +0.241 |
ymes | +0.208 |
ighed | +0.206 |
arl | +0.202 |
Neg logit contributions | |
Peter | -0.151 |
Jack | -0.149 |
der | -0.148 |
written | -0.148 |
Daddy | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | -3.87e-03 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.006 |
ymes | +0.006 |
able | +0.005 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.002 |
Peter | -0.002 |
Jack | -0.002 |
int | -0.002 |
Token | x |
Token ID | 2124 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Daddy | +0.006 |
mummy | +0.006 |
Peter | +0.006 |
Jack | +0.006 |
der | +0.006 |
Neg logit contributions | |
aking | -0.008 |
ang | -0.007 |
ymes | -0.007 |
able | -0.006 |
iffs | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
Daddy | +0.033 |
mummy | +0.032 |
Peter | +0.031 |
Jack | +0.030 |
der | +0.030 |
Neg logit contributions | |
aking | -0.023 |
ang | -0.021 |
ymes | -0.020 |
able | -0.018 |
iffs | -0.018 |
Token | ray |
Token ID | 2433 |
Feature activation | -7.13e-03 |
Pos logit contributions | |
aking | +0.094 |
ang | +0.087 |
ymes | +0.083 |
able | +0.074 |
iffs | +0.074 |
Neg logit contributions | |
Daddy | -0.100 |
mummy | -0.095 |
Peter | -0.093 |
der | -0.092 |
int | -0.091 |
Token | on |
Token ID | 319 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
Daddy | +0.005 |
mummy | +0.005 |
Peter | +0.005 |
Jack | +0.005 |
int | +0.005 |
Neg logit contributions | |
aking | -0.007 |
ang | -0.007 |
ymes | -0.007 |
able | -0.006 |
iffs | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
Daddy | +0.002 |
mummy | +0.002 |
Peter | +0.002 |
der | +0.002 |
int | +0.002 |
Neg logit contributions | |
aking | -0.006 |
ang | -0.006 |
ymes | -0.006 |
able | -0.006 |
iffs | -0.006 |
Token | Belle |
Token ID | 31974 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
aking | +0.007 |
ang | +0.006 |
ymes | +0.006 |
able | +0.006 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
der | -0.004 |
Jack | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
aking | +0.090 |
ang | +0.085 |
ymes | +0.083 |
iffs | +0.077 |
able | +0.077 |
Neg logit contributions | |
Daddy | -0.040 |
mummy | -0.037 |
Peter | -0.036 |
Jack | -0.034 |
der | -0.034 |
Token | known |
Token ID | 1900 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
Daddy | +0.004 |
mummy | +0.004 |
Peter | +0.004 |
Jack | +0.004 |
even | +0.003 |
Neg logit contributions | |
aking | -0.007 |
ymes | -0.007 |
ang | -0.007 |
iffs | -0.006 |
able | -0.006 |
Token | as |
Token ID | 355 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
aking | +0.012 |
ang | +0.011 |
ymes | +0.011 |
able | +0.010 |
iffs | +0.010 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
Jack | -0.003 |
int | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
aking | +0.286 |
ang | +0.270 |
ymes | +0.263 |
able | +0.247 |
iffs | +0.241 |
Neg logit contributions | |
Daddy | -0.135 |
mummy | -0.127 |
Peter | -0.122 |
der | -0.117 |
int | -0.116 |
Token | Bel |
Token ID | 12193 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
aking | +0.077 |
ang | +0.071 |
ymes | +0.069 |
iffs | +0.062 |
able | +0.061 |
Neg logit contributions | |
Daddy | -0.089 |
mummy | -0.086 |
Peter | -0.084 |
Jack | -0.082 |
oph | -0.081 |
Token | le |
Token ID | 293 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
aking | +0.055 |
ang | +0.053 |
iffs | +0.051 |
ymes | +0.048 |
itty | +0.045 |
Neg logit contributions | |
int | -0.048 |
der | -0.045 |
written | -0.045 |
mummy | -0.045 |
Daddy | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
Daddy | +0.006 |
mummy | +0.005 |
Peter | +0.005 |
Jack | +0.005 |
der | +0.005 |
Neg logit contributions | |
aking | -0.010 |
ang | -0.009 |
ymes | -0.009 |
iffs | -0.009 |
able | -0.009 |
Token | knot |
Token ID | 29654 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
aking | +0.021 |
ang | +0.020 |
iffs | +0.018 |
ymes | +0.018 |
asc | +0.018 |
Neg logit contributions | |
mummy | -0.015 |
Daddy | -0.015 |
one | -0.014 |
Peter | -0.013 |
even | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
Daddy | +0.013 |
mummy | +0.012 |
Peter | +0.012 |
Jack | +0.011 |
int | +0.011 |
Neg logit contributions | |
aking | -0.020 |
ymes | -0.019 |
ang | -0.019 |
able | -0.017 |
iffs | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -6.14e-04 |
Pos logit contributions | |
Daddy | +0.003 |
oph | +0.003 |
mummy | +0.003 |
int | +0.003 |
der | +0.003 |
Neg logit contributions | |
aking | -0.009 |
ang | -0.009 |
ymes | -0.008 |
able | -0.008 |
itty | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.001 |
Peter | +0.001 |
der | +0.000 |
Jack | +0.000 |
Neg logit contributions | |
aking | -0.002 |
ang | -0.002 |
ymes | -0.001 |
able | -0.001 |
iffs | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
aking | +0.058 |
ang | +0.055 |
ymes | +0.054 |
able | +0.050 |
iffs | +0.049 |
Neg logit contributions | |
Daddy | -0.029 |
mummy | -0.027 |
Peter | -0.026 |
Jack | -0.025 |
der | -0.025 |
Token | known |
Token ID | 1900 |
Feature activation | +4.83e-03 |
Pos logit contributions | |
Daddy | +0.005 |
mummy | +0.005 |
Peter | +0.005 |
even | +0.005 |
finally | +0.005 |
Neg logit contributions | |
ymes | -0.010 |
aking | -0.010 |
ang | -0.010 |
iffs | -0.010 |
able | -0.009 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.013 |
ang | +0.013 |
ymes | +0.012 |
able | +0.012 |
iffs | +0.011 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
Jack | -0.003 |
int | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
aking | +0.280 |
ang | +0.265 |
ymes | +0.257 |
able | +0.239 |
iffs | +0.237 |
Neg logit contributions | |
Daddy | -0.143 |
mummy | -0.134 |
Peter | -0.130 |
Jack | -0.124 |
der | -0.122 |
Token | mighty |
Token ID | 18680 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
aking | +0.035 |
ymes | +0.033 |
ang | +0.033 |
iffs | +0.031 |
ites | +0.029 |
Neg logit contributions | |
mummy | -0.033 |
Daddy | -0.033 |
Peter | -0.031 |
King | -0.031 |
one | -0.031 |
Token | hunter |
Token ID | 19177 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
Daddy | +0.014 |
mummy | +0.014 |
Peter | +0.014 |
der | +0.013 |
Jack | +0.013 |
Neg logit contributions | |
aking | -0.016 |
ymes | -0.015 |
ang | -0.014 |
iffs | -0.014 |
asc | -0.013 |
Token | who |
Token ID | 508 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
aking | +0.095 |
ang | +0.090 |
ymes | +0.089 |
iffs | +0.083 |
able | +0.081 |
Neg logit contributions | |
Daddy | -0.046 |
Peter | -0.044 |
mummy | -0.044 |
Jack | -0.042 |
der | -0.041 |
Token | always |
Token ID | 1464 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
aking | +0.057 |
ang | +0.053 |
ymes | +0.053 |
iffs | +0.049 |
able | +0.048 |
Neg logit contributions | |
Daddy | -0.025 |
Peter | -0.024 |
mummy | -0.024 |
Jack | -0.022 |
der | -0.021 |
Token | on |
Token ID | 319 |
Feature activation | -4.87e-03 |
Pos logit contributions | |
aking | +0.061 |
ang | +0.057 |
ymes | +0.054 |
able | +0.050 |
iffs | +0.048 |
Neg logit contributions | |
Daddy | -0.053 |
mummy | -0.051 |
der | -0.050 |
oph | -0.050 |
int | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
Daddy | +0.004 |
int | +0.004 |
der | +0.004 |
mummy | +0.004 |
oph | +0.004 |
Neg logit contributions | |
aking | -0.012 |
ang | -0.012 |
ymes | -0.011 |
able | -0.011 |
iffs | -0.010 |
Token | James |
Token ID | 3700 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
aking | +0.003 |
ymes | +0.003 |
ang | +0.003 |
able | +0.003 |
arate | +0.003 |
Neg logit contributions | |
oph | -0.001 |
der | -0.001 |
um | -0.001 |
mummy | -0.001 |
Jenna | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -7.70e-04 |
Pos logit contributions | |
Daddy | +0.008 |
mummy | +0.008 |
Peter | +0.007 |
int | +0.007 |
der | +0.007 |
Neg logit contributions | |
aking | -0.015 |
ang | -0.014 |
ymes | -0.013 |
able | -0.012 |
ites | -0.012 |
Token | known |
Token ID | 1900 |
Feature activation | +7.19e-03 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.001 |
Peter | +0.001 |
Jack | +0.001 |
int | +0.001 |
Neg logit contributions | |
aking | -0.002 |
ang | -0.002 |
ymes | -0.002 |
able | -0.001 |
iffs | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.019 |
ang | +0.018 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.016 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.007 |
Peter | -0.006 |
oph | -0.006 |
der | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
aking | +0.267 |
ang | +0.249 |
ymes | +0.244 |
able | +0.230 |
iffs | +0.220 |
Neg logit contributions | |
Daddy | -0.145 |
mummy | -0.139 |
der | -0.134 |
int | -0.132 |
Peter | -0.131 |
Token | creator |
Token ID | 13172 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
aking | +0.041 |
ang | +0.039 |
ymes | +0.037 |
able | +0.034 |
iffs | +0.034 |
Neg logit contributions | |
Daddy | -0.035 |
mummy | -0.034 |
Peter | -0.033 |
Jack | -0.032 |
int | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
aking | +0.005 |
ang | +0.005 |
ymes | +0.005 |
able | +0.005 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
Jack | -0.003 |
der | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
aking | +0.099 |
ang | +0.093 |
ymes | +0.091 |
iffs | +0.085 |
able | +0.084 |
Neg logit contributions | |
Daddy | -0.047 |
mummy | -0.044 |
Peter | -0.043 |
Jack | -0.041 |
der | -0.039 |
Token | original |
Token ID | 2656 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
aking | +0.021 |
ang | +0.020 |
ymes | +0.019 |
able | +0.017 |
iffs | +0.017 |
Neg logit contributions | |
Daddy | -0.014 |
mummy | -0.013 |
Peter | -0.013 |
Jack | -0.012 |
int | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
aking | +0.059 |
ang | +0.055 |
ymes | +0.054 |
able | +0.049 |
iffs | +0.048 |
Neg logit contributions | |
Daddy | -0.047 |
mummy | -0.045 |
Peter | -0.044 |
Jack | -0.042 |
der | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e-04 |
Pos logit contributions | |
Daddy | +0.006 |
mummy | +0.006 |
int | +0.006 |
oph | +0.006 |
der | +0.006 |
Neg logit contributions | |
aking | -0.017 |
ang | -0.017 |
ymes | -0.016 |
able | -0.015 |
iffs | -0.015 |
Token | Bob |
Token ID | 5811 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Daddy | +0.000 |
mummy | +0.000 |
Peter | +0.000 |
der | +0.000 |
int | +0.000 |
Neg logit contributions | |
aking | -0.001 |
ang | -0.000 |
ymes | -0.000 |
able | -0.000 |
iffs | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
aking | +0.044 |
ang | +0.041 |
ymes | +0.040 |
able | +0.037 |
iffs | +0.037 |
Neg logit contributions | |
Daddy | -0.022 |
mummy | -0.021 |
Peter | -0.020 |
Jack | -0.019 |
der | -0.019 |
Token | known |
Token ID | 1900 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
Daddy | +0.003 |
mummy | +0.003 |
Peter | +0.003 |
Jack | +0.003 |
int | +0.003 |
Neg logit contributions | |
aking | -0.006 |
ang | -0.006 |
ymes | -0.006 |
iffs | -0.006 |
able | -0.006 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.017 |
ang | +0.016 |
ymes | +0.016 |
able | +0.015 |
iffs | +0.015 |
Neg logit contributions | |
Daddy | -0.006 |
mummy | -0.005 |
Peter | -0.005 |
Jack | -0.005 |
der | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
aking | +0.274 |
ang | +0.257 |
ymes | +0.250 |
able | +0.236 |
iffs | +0.228 |
Neg logit contributions | |
Daddy | -0.139 |
mummy | -0.132 |
der | -0.126 |
Peter | -0.126 |
int | -0.125 |
Token | famous |
Token ID | 5863 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
aking | +0.040 |
ang | +0.038 |
ymes | +0.037 |
iffs | +0.035 |
able | +0.033 |
Neg logit contributions | |
Daddy | -0.035 |
mummy | -0.035 |
Peter | -0.033 |
Jack | -0.032 |
King | -0.031 |
Token | n |
Token ID | 299 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
aking | +0.003 |
ang | +0.002 |
ymes | +0.002 |
able | +0.002 |
itty | +0.002 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
int | -0.002 |
der | -0.002 |
Token | apping |
Token ID | 5912 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
aking | +0.033 |
ymes | +0.031 |
ang | +0.029 |
able | +0.027 |
iffs | +0.027 |
Neg logit contributions | |
Daddy | -0.047 |
mummy | -0.046 |
der | -0.045 |
um | -0.045 |
Peter | -0.044 |
Token | post |
Token ID | 1281 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
aking | +0.014 |
ang | +0.013 |
ymes | +0.013 |
able | +0.012 |
trap | +0.012 |
Neg logit contributions | |
Daddy | -0.008 |
mummy | -0.008 |
Peter | -0.007 |
int | -0.007 |
der | -0.007 |
Token | need |
Token ID | 761 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Daddy | +0.038 |
mummy | +0.035 |
Peter | +0.034 |
Jack | +0.033 |
der | +0.032 |
Neg logit contributions | |
aking | -0.070 |
ang | -0.066 |
ymes | -0.064 |
able | -0.059 |
iffs | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
aking | +0.041 |
ang | +0.038 |
ymes | +0.037 |
able | +0.036 |
iffs | +0.034 |
Neg logit contributions | |
Daddy | -0.018 |
mummy | -0.017 |
Peter | -0.017 |
int | -0.016 |
oph | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.007 |
iffs | +0.007 |
itty | +0.007 |
able | +0.007 |
Neg logit contributions | |
mummy | -0.006 |
int | -0.006 |
written | -0.006 |
lit | -0.006 |
aloud | -0.006 |
Token | became |
Token ID | 2627 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
aking | +0.028 |
ang | +0.026 |
ymes | +0.024 |
able | +0.024 |
cautious | +0.023 |
Neg logit contributions | |
Daddy | -0.018 |
Peter | -0.017 |
mummy | -0.017 |
int | -0.017 |
der | -0.016 |
Token | known |
Token ID | 1900 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
aking | +0.075 |
ang | +0.071 |
ymes | +0.070 |
iffs | +0.067 |
trap | +0.064 |
Neg logit contributions | |
Daddy | -0.039 |
mummy | -0.039 |
Peter | -0.035 |
Jack | -0.035 |
even | -0.034 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.006 |
ymes | +0.006 |
able | +0.005 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
oph | -0.002 |
der | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
aking | +0.273 |
ang | +0.254 |
ymes | +0.250 |
able | +0.237 |
iffs | +0.226 |
Neg logit contributions | |
Daddy | -0.139 |
mummy | -0.132 |
Peter | -0.127 |
int | -0.126 |
der | -0.126 |
Token | kind |
Token ID | 1611 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
aking | +0.039 |
ang | +0.037 |
ymes | +0.036 |
iffs | +0.034 |
ites | +0.032 |
Neg logit contributions | |
Daddy | -0.032 |
mummy | -0.031 |
King | -0.029 |
Peter | -0.029 |
Father | -0.029 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
aking | +0.039 |
ang | +0.035 |
able | +0.035 |
ymes | +0.033 |
aring | +0.031 |
Neg logit contributions | |
Daddy | -0.032 |
mummy | -0.032 |
Peter | -0.031 |
int | -0.031 |
oph | -0.029 |
Token | who |
Token ID | 508 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
aking | +0.044 |
ang | +0.041 |
ymes | +0.040 |
iffs | +0.038 |
able | +0.037 |
Neg logit contributions | |
Daddy | -0.022 |
mummy | -0.020 |
Peter | -0.020 |
Jack | -0.019 |
der | -0.018 |
Token | helped |
Token ID | 4193 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
aking | +0.059 |
ang | +0.056 |
ymes | +0.054 |
able | +0.050 |
iffs | +0.050 |
Neg logit contributions | |
Daddy | -0.030 |
mummy | -0.028 |
Peter | -0.027 |
Jack | -0.026 |
der | -0.026 |
Token | made |
Token ID | 925 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
aking | +0.043 |
ang | +0.042 |
ymes | +0.040 |
iffs | +0.039 |
arl | +0.038 |
Neg logit contributions | |
Daddy | -0.015 |
couldn | -0.014 |
Peter | -0.014 |
Jack | -0.014 |
mummy | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
aking | +0.013 |
ang | +0.012 |
ymes | +0.012 |
able | +0.011 |
iffs | +0.011 |
Neg logit contributions | |
Daddy | -0.006 |
mummy | -0.005 |
Peter | -0.005 |
der | -0.005 |
int | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.006 |
ymes | +0.005 |
iffs | +0.005 |
able | +0.005 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
int | -0.004 |
written | -0.004 |
Token | became |
Token ID | 2627 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
aking | +0.025 |
ang | +0.024 |
ymes | +0.022 |
able | +0.021 |
cautious | +0.020 |
Neg logit contributions | |
Daddy | -0.016 |
mummy | -0.014 |
Peter | -0.014 |
int | -0.014 |
um | -0.014 |
Token | known |
Token ID | 1900 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
aking | +0.079 |
ang | +0.075 |
ymes | +0.073 |
iffs | +0.071 |
arl | +0.068 |
Neg logit contributions | |
Daddy | -0.037 |
mummy | -0.037 |
Peter | -0.033 |
even | -0.033 |
Jack | -0.033 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.009 |
ang | +0.009 |
ymes | +0.008 |
able | +0.008 |
iffs | +0.008 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.002 |
Jack | -0.002 |
der | -0.002 |
Token | Brave |
Token ID | 22813 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
aking | +0.287 |
ang | +0.272 |
ymes | +0.263 |
able | +0.245 |
iffs | +0.244 |
Neg logit contributions | |
Daddy | -0.137 |
mummy | -0.128 |
Peter | -0.124 |
Jack | -0.118 |
der | -0.115 |
Token | Mia |
Token ID | 32189 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
aking | +0.002 |
ang | +0.002 |
ymes | +0.002 |
iffs | +0.002 |
ites | +0.002 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
Peter | -0.001 |
Jack | -0.001 |
der | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
aking | +0.005 |
ang | +0.005 |
ymes | +0.005 |
iffs | +0.004 |
able | +0.004 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
Jack | -0.002 |
der | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
aking | +0.060 |
ang | +0.057 |
ymes | +0.056 |
able | +0.053 |
iffs | +0.051 |
Neg logit contributions | |
Daddy | -0.029 |
mummy | -0.027 |
Peter | -0.026 |
der | -0.025 |
int | -0.025 |
Token | special |
Token ID | 2041 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
aking | +0.051 |
ang | +0.048 |
ymes | +0.047 |
able | +0.044 |
trap | +0.042 |
Neg logit contributions | |
Daddy | -0.035 |
mummy | -0.033 |
Peter | -0.032 |
oph | -0.031 |
int | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
Daddy | +0.014 |
mummy | +0.014 |
Peter | +0.013 |
Jack | +0.013 |
int | +0.013 |
Neg logit contributions | |
aking | -0.019 |
ang | -0.017 |
ymes | -0.017 |
able | -0.015 |
iffs | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.88e-03 |
Pos logit contributions | |
Daddy | +0.004 |
mummy | +0.004 |
oph | +0.004 |
der | +0.004 |
int | +0.003 |
Neg logit contributions | |
aking | -0.011 |
ang | -0.010 |
ymes | -0.010 |
able | -0.010 |
itty | -0.009 |
Token | Mark |
Token ID | 2940 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Daddy | +0.002 |
oph | +0.002 |
der | +0.002 |
mummy | +0.002 |
um | +0.002 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.004 |
ymes | -0.004 |
able | -0.004 |
ites | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
aking | +0.024 |
ang | +0.023 |
ymes | +0.022 |
able | +0.021 |
iffs | +0.020 |
Neg logit contributions | |
Daddy | -0.012 |
mummy | -0.012 |
Peter | -0.011 |
int | -0.011 |
der | -0.011 |
Token | known |
Token ID | 1900 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
Daddy | +0.004 |
mummy | +0.004 |
Peter | +0.004 |
Jack | +0.004 |
int | +0.004 |
Neg logit contributions | |
aking | -0.008 |
ang | -0.007 |
ymes | -0.007 |
iffs | -0.007 |
able | -0.006 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.015 |
ang | +0.014 |
ymes | +0.014 |
able | +0.013 |
iffs | +0.013 |
Neg logit contributions | |
Daddy | -0.005 |
mummy | -0.004 |
Peter | -0.004 |
Jack | -0.004 |
der | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
aking | +0.271 |
ang | +0.254 |
ymes | +0.247 |
able | +0.234 |
iffs | +0.224 |
Neg logit contributions | |
Daddy | -0.141 |
mummy | -0.134 |
der | -0.128 |
Peter | -0.126 |
int | -0.126 |
Token | fat |
Token ID | 3735 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
aking | +0.036 |
ang | +0.034 |
ymes | +0.032 |
iffs | +0.030 |
able | +0.029 |
Neg logit contributions | |
Daddy | -0.033 |
mummy | -0.032 |
Peter | -0.031 |
Jack | -0.030 |
int | -0.030 |
Token | cat |
Token ID | 3797 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
Daddy | +0.011 |
mummy | +0.010 |
Peter | +0.010 |
int | +0.010 |
oph | +0.010 |
Neg logit contributions | |
aking | -0.014 |
ang | -0.013 |
ymes | -0.013 |
able | -0.012 |
trap | -0.012 |
Token | king |
Token ID | 5822 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
aking | +0.050 |
ang | +0.047 |
ymes | +0.046 |
iffs | +0.043 |
able | +0.043 |
Neg logit contributions | |
Daddy | -0.027 |
mummy | -0.026 |
Peter | -0.025 |
Jack | -0.024 |
der | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
aking | +0.042 |
ang | +0.039 |
ymes | +0.038 |
iffs | +0.036 |
able | +0.035 |
Neg logit contributions | |
Daddy | -0.025 |
mummy | -0.024 |
Peter | -0.024 |
Jack | -0.023 |
der | -0.022 |
Token | on |
Token ID | 319 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
Daddy | +0.016 |
mummy | +0.015 |
Peter | +0.015 |
Jack | +0.014 |
int | +0.014 |
Neg logit contributions | |
aking | -0.020 |
ang | -0.019 |
ymes | -0.019 |
able | -0.017 |
iffs | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
Daddy | +0.005 |
der | +0.005 |
oph | +0.005 |
int | +0.005 |
mummy | +0.005 |
Neg logit contributions | |
aking | -0.013 |
ang | -0.012 |
able | -0.012 |
ymes | -0.011 |
cautious | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
der | +0.002 |
omm | +0.002 |
mummy | +0.002 |
Daddy | +0.002 |
oph | +0.002 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.004 |
able | -0.004 |
ymes | -0.004 |
cautious | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
aking | +0.055 |
ang | +0.052 |
ymes | +0.050 |
able | +0.047 |
iffs | +0.046 |
Neg logit contributions | |
Daddy | -0.031 |
mummy | -0.029 |
Peter | -0.028 |
int | -0.027 |
der | -0.027 |
Token | known |
Token ID | 1900 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
Daddy | +0.009 |
mummy | +0.009 |
Peter | +0.008 |
Jack | +0.008 |
even | +0.008 |
Neg logit contributions | |
aking | -0.014 |
ymes | -0.014 |
ang | -0.013 |
iffs | -0.012 |
able | -0.012 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.004 |
ymes | +0.004 |
able | +0.004 |
iffs | +0.004 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
der | -0.002 |
oph | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
aking | +0.266 |
ang | +0.249 |
ymes | +0.242 |
able | +0.228 |
iffs | +0.220 |
Neg logit contributions | |
Daddy | -0.148 |
mummy | -0.141 |
der | -0.134 |
Peter | -0.133 |
int | -0.132 |
Token | brav |
Token ID | 49025 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
aking | +0.034 |
ang | +0.032 |
ymes | +0.031 |
able | +0.028 |
iffs | +0.028 |
Neg logit contributions | |
Daddy | -0.033 |
mummy | -0.032 |
Peter | -0.031 |
Jack | -0.030 |
int | -0.030 |
Token | est |
Token ID | 395 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Daddy | +0.003 |
mummy | +0.002 |
Peter | +0.002 |
Jack | +0.002 |
int | +0.002 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.005 |
ymes | -0.005 |
able | -0.004 |
iffs | -0.004 |
Token | knight |
Token ID | 22062 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
Daddy | +0.017 |
oph | +0.015 |
mummy | +0.015 |
Jenna | +0.015 |
int | +0.015 |
Neg logit contributions | |
aking | -0.020 |
ang | -0.019 |
ymes | -0.019 |
able | -0.018 |
trap | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
aking | +0.015 |
ang | +0.014 |
ymes | +0.014 |
able | +0.013 |
iffs | +0.012 |
Neg logit contributions | |
Daddy | -0.010 |
mummy | -0.009 |
Peter | -0.009 |
der | -0.008 |
int | -0.008 |
Token | them |
Token ID | 606 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.006 |
ymes | +0.006 |
able | +0.005 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.002 |
der | -0.002 |
int | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-03 |
Pos logit contributions | |
aking | +0.010 |
ang | +0.010 |
ymes | +0.010 |
iffs | +0.009 |
able | +0.009 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
Jack | -0.003 |
der | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +6.90e-03 |
Pos logit contributions | |
Daddy | +0.003 |
mummy | +0.002 |
der | +0.002 |
int | +0.002 |
Peter | +0.002 |
Neg logit contributions | |
aking | -0.004 |
ang | -0.004 |
ymes | -0.004 |
iffs | -0.004 |
able | -0.004 |
Token | became |
Token ID | 2627 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
aking | +0.016 |
ang | +0.014 |
ymes | +0.014 |
able | +0.013 |
iffs | +0.013 |
Neg logit contributions | |
Daddy | -0.009 |
mummy | -0.009 |
Peter | -0.009 |
int | -0.008 |
der | -0.008 |
Token | known |
Token ID | 1900 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
aking | +0.080 |
ang | +0.076 |
ymes | +0.074 |
iffs | +0.072 |
arl | +0.070 |
Neg logit contributions | |
mummy | -0.037 |
Daddy | -0.036 |
even | -0.034 |
Peter | -0.032 |
Jack | -0.032 |
Token | as |
Token ID | 355 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aking | +0.007 |
ang | +0.006 |
ymes | +0.006 |
able | +0.006 |
iffs | +0.006 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
Jack | -0.001 |
int | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
aking | +0.290 |
ang | +0.276 |
ymes | +0.266 |
iffs | +0.249 |
able | +0.247 |
Neg logit contributions | |
Daddy | -0.134 |
mummy | -0.125 |
Peter | -0.121 |
Jack | -0.116 |
der | -0.111 |
Token | resc |
Token ID | 6811 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
aking | +0.041 |
iffs | +0.038 |
ang | +0.038 |
ymes | +0.036 |
ighed | +0.034 |
Neg logit contributions | |
mummy | -0.033 |
Daddy | -0.030 |
one | -0.030 |
father | -0.029 |
mother | -0.028 |
Token | uer |
Token ID | 15573 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
aking | +0.060 |
ymes | +0.056 |
iffs | +0.050 |
ang | +0.049 |
able | +0.048 |
Neg logit contributions | |
der | -0.064 |
um | -0.062 |
int | -0.061 |
mummy | -0.057 |
oph | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
aking | +0.058 |
ang | +0.055 |
ymes | +0.053 |
iffs | +0.051 |
able | +0.048 |
Neg logit contributions | |
Daddy | -0.023 |
Peter | -0.022 |
mummy | -0.021 |
Jack | -0.021 |
der | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Daddy | +0.014 |
mummy | +0.013 |
Peter | +0.013 |
Jack | +0.013 |
der | +0.012 |
Neg logit contributions | |
aking | -0.032 |
ang | -0.031 |
ymes | -0.030 |
iffs | -0.028 |
able | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
oph | +0.094 |
Daddy | +0.093 |
der | +0.091 |
mummy | +0.090 |
um | +0.085 |
Neg logit contributions | |
aking | -0.141 |
ang | -0.132 |
ymes | -0.120 |
iffs | -0.118 |
render | -0.111 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
aking | +0.044 |
ang | +0.041 |
ymes | +0.039 |
able | +0.037 |
iffs | +0.036 |
Neg logit contributions | |
Daddy | -0.026 |
mummy | -0.024 |
Peter | -0.023 |
Jack | -0.023 |
int | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Daddy | +0.034 |
mummy | +0.031 |
int | +0.030 |
Peter | +0.030 |
der | +0.030 |
Neg logit contributions | |
aking | -0.058 |
ang | -0.054 |
ymes | -0.051 |
able | -0.050 |
trap | -0.048 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
Daddy | +0.015 |
int | +0.015 |
mummy | +0.014 |
um | +0.014 |
oph | +0.014 |
Neg logit contributions | |
aking | -0.024 |
ang | -0.023 |
ymes | -0.021 |
iffs | -0.021 |
able | -0.020 |
Token | Wh |
Token ID | 854 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
Daddy | +0.024 |
mummy | +0.023 |
Peter | +0.023 |
Jack | +0.022 |
der | +0.021 |
Neg logit contributions | |
aking | -0.026 |
ang | -0.024 |
ymes | -0.023 |
able | -0.021 |
iffs | -0.021 |
Token | isk |
Token ID | 1984 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ang | +0.068 |
aking | +0.068 |
ymes | +0.065 |
ites | +0.060 |
iffs | +0.058 |
Neg logit contributions | |
der | -0.082 |
um | -0.080 |
Peter | -0.080 |
Jack | -0.079 |
oph | -0.077 |
Token | ers |
Token ID | 364 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
ang | +0.250 |
aking | +0.247 |
ymes | +0.216 |
ighed | +0.214 |
cautious | +0.208 |
Neg logit contributions | |
Jack | -0.144 |
Peter | -0.142 |
King | -0.136 |
Andrew | -0.133 |
um | -0.133 |
Token | for |
Token ID | 329 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
aking | +0.018 |
ang | +0.017 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.016 |
Neg logit contributions | |
Daddy | -0.010 |
mummy | -0.009 |
Peter | -0.009 |
der | -0.008 |
Jack | -0.008 |
Token | helping |
Token ID | 5742 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
aking | +0.040 |
ang | +0.038 |
ymes | +0.037 |
able | +0.035 |
iffs | +0.034 |
Neg logit contributions | |
Daddy | -0.022 |
Peter | -0.021 |
Jack | -0.021 |
mummy | -0.021 |
finally | -0.018 |
Token | him |
Token ID | 683 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
aking | +0.005 |
ang | +0.004 |
ymes | +0.004 |
able | +0.004 |
iffs | +0.004 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
Peter | -0.001 |
der | -0.001 |
int | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
aking | +0.054 |
ang | +0.051 |
ymes | +0.049 |
able | +0.046 |
iffs | +0.046 |
Neg logit contributions | |
Daddy | -0.027 |
mummy | -0.025 |
Peter | -0.024 |
oph | -0.023 |
der | -0.023 |
Token | down |
Token ID | 866 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
Daddy | +0.045 |
mummy | +0.043 |
Peter | +0.042 |
der | +0.041 |
Jack | +0.040 |
Neg logit contributions | |
aking | -0.049 |
ang | -0.046 |
ymes | -0.044 |
able | -0.040 |
iffs | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
aking | +0.043 |
ang | +0.041 |
ymes | +0.039 |
able | +0.037 |
iffs | +0.036 |
Neg logit contributions | |
Daddy | -0.024 |
mummy | -0.022 |
Peter | -0.022 |
der | -0.021 |
Jack | -0.021 |
Token | used |
Token ID | 973 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
Daddy | +0.026 |
mummy | +0.025 |
Peter | +0.024 |
der | +0.024 |
um | +0.024 |
Neg logit contributions | |
aking | -0.041 |
ang | -0.038 |
ymes | -0.036 |
able | -0.034 |
iffs | -0.034 |
Token | his |
Token ID | 465 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
der | +0.008 |
oph | +0.008 |
Daddy | +0.007 |
mummy | +0.007 |
Peter | +0.007 |
Neg logit contributions | |
aking | -0.012 |
ang | -0.011 |
ymes | -0.011 |
able | -0.011 |
iffs | -0.010 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
aking | +0.002 |
ang | +0.002 |
ymes | +0.002 |
able | +0.002 |
iffs | +0.002 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
der | -0.002 |
oph | -0.002 |
Token | ker |
Token ID | 6122 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Daddy | +0.029 |
mummy | +0.028 |
Peter | +0.027 |
oph | +0.026 |
der | +0.026 |
Neg logit contributions | |
aking | -0.047 |
ang | -0.044 |
ymes | -0.042 |
able | -0.040 |
iffs | -0.039 |
Token | chief |
Token ID | 17351 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
der | +0.126 |
oph | +0.123 |
Daddy | +0.122 |
int | +0.121 |
written | +0.119 |
Neg logit contributions | |
aking | -0.222 |
ang | -0.209 |
iffs | -0.196 |
ymes | -0.191 |
itty | -0.185 |
Token | to |
Token ID | 284 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
Daddy | +0.008 |
mummy | +0.008 |
oph | +0.007 |
Peter | +0.007 |
Andrew | +0.007 |
Neg logit contributions | |
aking | -0.011 |
ang | -0.010 |
ymes | -0.010 |
able | -0.009 |
iffs | -0.009 |
Token | pick |
Token ID | 2298 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
aking | +0.012 |
ang | +0.012 |
ymes | +0.011 |
able | +0.010 |
iffs | +0.010 |
Neg logit contributions | |
Daddy | -0.010 |
mummy | -0.010 |
Peter | -0.010 |
der | -0.009 |
Jack | -0.009 |
Token | up |
Token ID | 510 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.012 |
der | +0.012 |
Peter | +0.011 |
Father | +0.011 |
Neg logit contributions | |
aking | -0.023 |
ang | -0.022 |
ymes | -0.021 |
able | -0.020 |
iffs | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e-03 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.004 |
ymes | +0.003 |
able | +0.003 |
iffs | +0.003 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
der | -0.002 |
oph | -0.002 |
Token | then |
Token ID | 788 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
aking | +0.026 |
ang | +0.025 |
ymes | +0.024 |
able | +0.022 |
iffs | +0.022 |
Neg logit contributions | |
Daddy | -0.016 |
mummy | -0.015 |
Peter | -0.014 |
der | -0.014 |
int | -0.014 |
Token | took |
Token ID | 1718 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Daddy | +0.033 |
mummy | +0.031 |
Peter | +0.030 |
Jack | +0.028 |
der | +0.028 |
Neg logit contributions | |
aking | -0.064 |
ang | -0.061 |
ymes | -0.059 |
able | -0.055 |
iffs | -0.055 |
Token | out |
Token ID | 503 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
aking | +0.038 |
ang | +0.035 |
ymes | +0.034 |
able | +0.033 |
iffs | +0.032 |
Neg logit contributions | |
der | -0.025 |
Daddy | -0.024 |
int | -0.023 |
mummy | -0.023 |
Peter | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
aking | +0.034 |
ang | +0.032 |
ymes | +0.031 |
able | +0.029 |
iffs | +0.029 |
Neg logit contributions | |
Daddy | -0.014 |
mummy | -0.013 |
Peter | -0.013 |
Jack | -0.012 |
int | -0.012 |
Token | hand |
Token ID | 1021 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
aking | +0.041 |
ang | +0.038 |
ymes | +0.037 |
able | +0.034 |
iffs | +0.034 |
Neg logit contributions | |
Daddy | -0.028 |
mummy | -0.027 |
Peter | -0.025 |
Jack | -0.025 |
int | -0.024 |
Token | ker |
Token ID | 6122 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
Daddy | +0.011 |
oph | +0.010 |
mummy | +0.010 |
Peter | +0.010 |
der | +0.010 |
Neg logit contributions | |
aking | -0.018 |
ang | -0.016 |
ymes | -0.015 |
able | -0.015 |
itty | -0.014 |
Token | chief |
Token ID | 17351 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
der | +0.111 |
Daddy | +0.108 |
int | +0.106 |
oph | +0.105 |
written | +0.105 |
Neg logit contributions | |
aking | -0.215 |
ang | -0.204 |
iffs | -0.189 |
ymes | -0.187 |
itty | -0.181 |
Token | and |
Token ID | 290 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
aking | +0.009 |
ang | +0.008 |
able | +0.008 |
ymes | +0.008 |
iffs | +0.007 |
Neg logit contributions | |
Daddy | -0.006 |
mummy | -0.006 |
oph | -0.006 |
Andrew | -0.006 |
Father | -0.006 |
Token | carefully |
Token ID | 7773 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
Daddy | +0.028 |
mummy | +0.027 |
der | +0.026 |
int | +0.026 |
Peter | +0.026 |
Neg logit contributions | |
aking | -0.046 |
ang | -0.043 |
ymes | -0.041 |
able | -0.039 |
iffs | -0.038 |
Token | picked |
Token ID | 6497 |
Feature activation | -7.31e-03 |
Pos logit contributions | |
Daddy | +0.084 |
mummy | +0.081 |
Peter | +0.080 |
der | +0.078 |
int | +0.076 |
Neg logit contributions | |
aking | -0.105 |
ang | -0.097 |
ymes | -0.090 |
able | -0.086 |
iffs | -0.084 |
Token | up |
Token ID | 510 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
Daddy | +0.009 |
der | +0.009 |
mummy | +0.008 |
Peter | +0.008 |
oph | +0.008 |
Neg logit contributions | |
aking | -0.016 |
ang | -0.015 |
ymes | -0.014 |
able | -0.014 |
iffs | -0.014 |
Token | look |
Token ID | 804 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
Daddy | +0.028 |
mummy | +0.026 |
Peter | +0.026 |
Jack | +0.025 |
der | +0.024 |
Neg logit contributions | |
aking | -0.039 |
ang | -0.037 |
ymes | -0.036 |
able | -0.033 |
iffs | -0.032 |
Token | at |
Token ID | 379 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
Daddy | +0.046 |
mummy | +0.044 |
Peter | +0.042 |
der | +0.040 |
Jack | +0.040 |
Neg logit contributions | |
aking | -0.082 |
ang | -0.077 |
ymes | -0.075 |
able | -0.069 |
iffs | -0.068 |
Token | my |
Token ID | 616 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
aking | +0.053 |
ang | +0.051 |
ymes | +0.047 |
iffs | +0.041 |
able | +0.040 |
Neg logit contributions | |
int | -0.077 |
oph | -0.076 |
mummy | -0.076 |
Daddy | -0.076 |
aloud | -0.075 |
Token | net |
Token ID | 2010 |
Feature activation | -7.04e-03 |
Pos logit contributions | |
Daddy | +0.028 |
mummy | +0.026 |
Peter | +0.026 |
Jack | +0.025 |
der | +0.025 |
Neg logit contributions | |
aking | -0.037 |
ang | -0.035 |
ymes | -0.034 |
able | -0.031 |
iffs | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
Daddy | +0.008 |
mummy | +0.008 |
Peter | +0.007 |
int | +0.007 |
der | +0.007 |
Neg logit contributions | |
aking | -0.017 |
ang | -0.016 |
ymes | -0.016 |
able | -0.015 |
iffs | -0.014 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
aking | +0.029 |
ang | +0.028 |
iffs | +0.026 |
ymes | +0.026 |
able | +0.025 |
Neg logit contributions | |
oph | -0.019 |
int | -0.019 |
mummy | -0.018 |
Daddy | -0.018 |
der | -0.018 |
Token | 't |
Token ID | 470 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
Daddy | +0.129 |
mummy | +0.123 |
der | +0.119 |
Father | +0.117 |
Peter | +0.117 |
Neg logit contributions | |
aking | -0.199 |
ang | -0.188 |
ymes | -0.178 |
iffs | -0.168 |
able | -0.163 |
Token | it |
Token ID | 340 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
um | +0.003 |
mummy | +0.003 |
int | +0.002 |
oph | +0.002 |
Father | +0.002 |
Neg logit contributions | |
aking | -0.003 |
ymes | -0.003 |
ang | -0.003 |
able | -0.003 |
trap | -0.003 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
Daddy | +0.021 |
oph | +0.021 |
der | +0.021 |
mummy | +0.020 |
Peter | +0.020 |
Neg logit contributions | |
aking | -0.017 |
ymes | -0.014 |
ang | -0.014 |
able | -0.013 |
iffs | -0.012 |
Token | ? |
Token ID | 30 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
oph | +0.057 |
Daddy | +0.056 |
Father | +0.056 |
Andrew | +0.055 |
Peter | +0.055 |
Neg logit contributions | |
aking | -0.053 |
ymes | -0.047 |
ang | -0.045 |
iffs | -0.041 |
able | -0.041 |
Token | Can |
Token ID | 1680 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
aking | +0.005 |
ang | +0.005 |
ymes | +0.004 |
iffs | +0.004 |
itty | +0.004 |
Neg logit contributions | |
oph | -0.003 |
mummy | -0.003 |
Daddy | -0.003 |
int | -0.003 |
Peter | -0.003 |
Token | us |
Token ID | 514 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
Daddy | +0.015 |
der | +0.014 |
mummy | +0.014 |
int | +0.014 |
Peter | +0.014 |
Neg logit contributions | |
aking | -0.015 |
ang | -0.014 |
ymes | -0.014 |
able | -0.012 |
iffs | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +4.14e-03 |
Pos logit contributions | |
aking | +0.064 |
ang | +0.061 |
ymes | +0.059 |
able | +0.055 |
iffs | +0.054 |
Neg logit contributions | |
Daddy | -0.037 |
mummy | -0.035 |
Peter | -0.034 |
Jack | -0.032 |
der | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.007 |
ymes | +0.007 |
iffs | +0.007 |
trap | +0.007 |
Neg logit contributions | |
Daddy | -0.006 |
der | -0.006 |
mummy | -0.006 |
int | -0.006 |
Peter | -0.006 |
Token | park |
Token ID | 3952 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
Daddy | +0.016 |
mummy | +0.015 |
Peter | +0.015 |
der | +0.015 |
Jack | +0.015 |
Neg logit contributions | |
aking | -0.020 |
ang | -0.019 |
ymes | -0.018 |
able | -0.017 |
trap | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
aking | +0.036 |
ang | +0.035 |
ymes | +0.034 |
able | +0.031 |
iffs | +0.031 |
Neg logit contributions | |
Daddy | -0.019 |
mummy | -0.018 |
Peter | -0.017 |
Jack | -0.016 |
der | -0.016 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
Daddy | +0.005 |
mummy | +0.005 |
der | +0.005 |
Peter | +0.005 |
int | +0.005 |
Neg logit contributions | |
aking | -0.008 |
ang | -0.007 |
ymes | -0.007 |
iffs | -0.006 |
able | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | -5.14e-03 |
Pos logit contributions | |
Daddy | +0.119 |
mummy | +0.114 |
der | +0.108 |
Peter | +0.107 |
Father | +0.104 |
Neg logit contributions | |
aking | -0.208 |
ang | -0.195 |
ymes | -0.186 |
iffs | -0.174 |
able | -0.171 |
Token | that |
Token ID | 326 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
mummy | +0.006 |
Daddy | +0.006 |
um | +0.006 |
int | +0.006 |
omm | +0.006 |
Neg logit contributions | |
aking | -0.011 |
ang | -0.011 |
ymes | -0.010 |
able | -0.010 |
trap | -0.009 |
Token | great |
Token ID | 1049 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
aking | +0.071 |
ang | +0.065 |
ymes | +0.064 |
able | +0.060 |
trap | +0.057 |
Neg logit contributions | |
Daddy | -0.060 |
mummy | -0.058 |
der | -0.056 |
Peter | -0.056 |
oph | -0.055 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
Daddy | +0.033 |
mummy | +0.031 |
Peter | +0.031 |
int | +0.030 |
der | +0.030 |
Neg logit contributions | |
aking | -0.042 |
ang | -0.038 |
ymes | -0.038 |
able | -0.035 |
iffs | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +1.83e-03 |
Pos logit contributions | |
der | +0.046 |
moons | +0.043 |
written | +0.041 |
ceiling | +0.040 |
markers | +0.040 |
Neg logit contributions | |
aking | -0.056 |
ang | -0.054 |
iffs | -0.047 |
itty | -0.047 |
ymes | -0.046 |
Token | You |
Token ID | 921 |
Feature activation | -4.89e-03 |
Pos logit contributions | |
aking | +0.048 |
ang | +0.045 |
ymes | +0.042 |
iffs | +0.041 |
itty | +0.039 |
Neg logit contributions | |
Daddy | -0.043 |
mummy | -0.042 |
Peter | -0.041 |
int | -0.040 |
oph | -0.040 |
Token | can |
Token ID | 460 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
Daddy | +0.009 |
mummy | +0.008 |
Peter | +0.008 |
int | +0.008 |
der | +0.008 |
Neg logit contributions | |
aking | -0.009 |
ang | -0.008 |
ymes | -0.008 |
able | -0.007 |
iffs | -0.007 |
Token | play |
Token ID | 711 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Daddy | +0.103 |
Peter | +0.098 |
der | +0.098 |
oph | +0.097 |
int | +0.096 |
Neg logit contributions | |
aking | -0.091 |
ang | -0.085 |
ymes | -0.077 |
iffs | -0.076 |
trap | -0.072 |
Token | together |
Token ID | 1978 |
Feature activation | +6.67e-04 |
Pos logit contributions | |
aking | +0.055 |
ang | +0.052 |
ymes | +0.048 |
able | +0.046 |
beh | +0.045 |
Neg logit contributions | |
Daddy | -0.036 |
mummy | -0.035 |
Jack | -0.034 |
Peter | -0.033 |
der | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.001 |
ymes | +0.001 |
able | +0.001 |
iffs | +0.001 |
Neg logit contributions | |
Daddy | -0.001 |
Peter | -0.001 |
mummy | -0.001 |
Jenna | -0.001 |
Father | -0.001 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
aking | +0.047 |
ang | +0.044 |
ymes | +0.040 |
iffs | +0.039 |
itty | +0.037 |
Neg logit contributions | |
Daddy | -0.044 |
mummy | -0.044 |
int | -0.042 |
Peter | -0.042 |
oph | -0.042 |
Token | 't |
Token ID | 470 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
Daddy | +0.129 |
mummy | +0.123 |
der | +0.117 |
Father | +0.117 |
Peter | +0.116 |
Neg logit contributions | |
aking | -0.196 |
ang | -0.183 |
ymes | -0.179 |
iffs | -0.165 |
able | -0.161 |
Token | that |
Token ID | 326 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
um | +0.002 |
oph | +0.002 |
horizon | +0.002 |
omm | +0.002 |
mummy | +0.002 |
Neg logit contributions | |
aking | -0.003 |
ymes | -0.003 |
able | -0.003 |
ang | -0.003 |
respectful | -0.003 |
Token | better |
Token ID | 1365 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
aking | +0.053 |
ymes | +0.052 |
able | +0.046 |
ang | +0.046 |
trap | +0.044 |
Neg logit contributions | |
Daddy | -0.070 |
Peter | -0.068 |
mummy | -0.067 |
oph | -0.067 |
Father | -0.067 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Daddy | +0.031 |
Peter | +0.031 |
oph | +0.030 |
mummy | +0.029 |
int | +0.029 |
Neg logit contributions | |
aking | -0.038 |
ang | -0.035 |
ymes | -0.034 |
able | -0.032 |
iffs | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
der | +0.015 |
oph | +0.014 |
Daddy | +0.014 |
int | +0.014 |
mummy | +0.014 |
Neg logit contributions | |
aking | -0.023 |
ang | -0.022 |
ymes | -0.021 |
able | -0.021 |
iffs | -0.020 |
Token | Look |
Token ID | 8567 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
aking | +0.052 |
ang | +0.048 |
ymes | +0.046 |
able | +0.041 |
iffs | +0.040 |
Neg logit contributions | |
Daddy | -0.063 |
mummy | -0.061 |
Peter | -0.060 |
Jack | -0.058 |
der | -0.058 |
Token | at |
Token ID | 379 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
der | +0.072 |
Daddy | +0.071 |
mummy | +0.066 |
Peter | +0.066 |
int | +0.066 |
Neg logit contributions | |
aking | -0.170 |
ang | -0.163 |
ymes | -0.157 |
iffs | -0.145 |
able | -0.143 |
Token | my |
Token ID | 616 |
Feature activation | -8.67e-03 |
Pos logit contributions | |
aking | +0.077 |
ang | +0.072 |
ymes | +0.070 |
able | +0.065 |
iffs | +0.064 |
Neg logit contributions | |
Daddy | -0.048 |
mummy | -0.046 |
Peter | -0.044 |
Jack | -0.043 |
der | -0.042 |
Token | veil |
Token ID | 30615 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
Daddy | +0.011 |
Peter | +0.011 |
mummy | +0.011 |
int | +0.010 |
der | +0.010 |
Neg logit contributions | |
aking | -0.019 |
ang | -0.018 |
ymes | -0.018 |
able | -0.016 |
trap | -0.016 |
Token | ! |
Token ID | 0 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
Daddy | +0.022 |
mummy | +0.020 |
Peter | +0.019 |
int | +0.019 |
der | +0.018 |
Neg logit contributions | |
aking | -0.052 |
ang | -0.049 |
ymes | -0.048 |
able | -0.045 |
iffs | -0.044 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
Daddy | +0.011 |
mummy | +0.011 |
Peter | +0.010 |
int | +0.010 |
der | +0.010 |
Neg logit contributions | |
aking | -0.018 |
ang | -0.018 |
ymes | -0.017 |
iffs | -0.016 |
able | -0.015 |
Token | 't |
Token ID | 470 |
Feature activation | -3.72e-05 |
Pos logit contributions | |
Daddy | +0.127 |
mummy | +0.120 |
der | +0.116 |
Father | +0.115 |
Peter | +0.114 |
Neg logit contributions | |
aking | -0.199 |
ang | -0.188 |
ymes | -0.180 |
iffs | -0.169 |
trap | -0.164 |
Token | it |
Token ID | 340 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
um | +0.000 |
mummy | +0.000 |
int | +0.000 |
Father | +0.000 |
Daddy | +0.000 |
Neg logit contributions | |
aking | -0.000 |
ymes | -0.000 |
ang | -0.000 |
able | -0.000 |
trap | -0.000 |
Token | lovely |
Token ID | 14081 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Daddy | +0.025 |
der | +0.024 |
mummy | +0.024 |
Peter | +0.024 |
int | +0.024 |
Neg logit contributions | |
aking | -0.019 |
ymes | -0.016 |
ang | -0.016 |
able | -0.014 |
iffs | -0.014 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
Daddy | +0.037 |
Father | +0.035 |
Peter | +0.035 |
mummy | +0.035 |
int | +0.035 |
Neg logit contributions | |
aking | -0.043 |
ymes | -0.038 |
ang | -0.038 |
able | -0.034 |
iffs | -0.034 |
Token | Anna |
Token ID | 11735 |
Feature activation | +2.56e-03 |
Pos logit contributions | |
Daddy | +0.036 |
mummy | +0.036 |
Peter | +0.035 |
int | +0.034 |
der | +0.034 |
Neg logit contributions | |
aking | -0.055 |
ang | -0.053 |
ymes | -0.051 |
iffs | -0.050 |
able | -0.048 |
Token | " |
Token ID | 366 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
mummy | +0.021 |
Daddy | +0.021 |
der | +0.021 |
Andrew | +0.020 |
Peter | +0.020 |
Neg logit contributions | |
aking | -0.029 |
ang | -0.028 |
iffs | -0.026 |
ymes | -0.025 |
itty | -0.025 |
Token | Look |
Token ID | 8567 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
aking | +0.040 |
ang | +0.037 |
ymes | +0.036 |
able | +0.032 |
iffs | +0.032 |
Neg logit contributions | |
Daddy | -0.041 |
mummy | -0.040 |
Peter | -0.039 |
Jack | -0.037 |
int | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
der | +0.090 |
horizon | +0.084 |
moons | +0.081 |
Andrew | +0.075 |
Father | +0.074 |
Neg logit contributions | |
aking | -0.147 |
ang | -0.144 |
ymes | -0.134 |
iffs | -0.124 |
itty | -0.124 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
int | +0.016 |
Daddy | +0.016 |
der | +0.016 |
Peter | +0.016 |
mummy | +0.016 |
Neg logit contributions | |
aking | -0.025 |
ang | -0.023 |
ymes | -0.023 |
able | -0.021 |
iffs | -0.021 |
Token | ! |
Token ID | 0 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
Daddy | +0.015 |
int | +0.015 |
mummy | +0.015 |
der | +0.014 |
Peter | +0.013 |
Neg logit contributions | |
aking | -0.038 |
ang | -0.035 |
ymes | -0.034 |
able | -0.032 |
itty | -0.031 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
Daddy | +0.015 |
mummy | +0.014 |
Peter | +0.014 |
Jack | +0.013 |
der | +0.013 |
Neg logit contributions | |
aking | -0.024 |
ang | -0.023 |
ymes | -0.022 |
able | -0.021 |
iffs | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | -4.61e-03 |
Pos logit contributions | |
Daddy | +0.131 |
mummy | +0.123 |
der | +0.122 |
Father | +0.120 |
Peter | +0.118 |
Neg logit contributions | |
aking | -0.193 |
ang | -0.181 |
ymes | -0.170 |
iffs | -0.160 |
itty | -0.156 |
Token | it |
Token ID | 340 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
um | +0.006 |
mummy | +0.006 |
Daddy | +0.006 |
Father | +0.006 |
int | +0.006 |
Neg logit contributions | |
aking | -0.009 |
ymes | -0.008 |
ang | -0.008 |
able | -0.008 |
trap | -0.008 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
Daddy | +0.025 |
der | +0.025 |
Father | +0.024 |
oph | +0.024 |
Peter | +0.024 |
Neg logit contributions | |
aking | -0.018 |
ymes | -0.015 |
ang | -0.014 |
able | -0.014 |
respectful | -0.013 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
Daddy | +0.060 |
Father | +0.060 |
Andrew | +0.059 |
Jason | +0.059 |
Peter | +0.057 |
Neg logit contributions | |
aking | -0.054 |
ymes | -0.049 |
ang | -0.045 |
able | -0.043 |
iffs | -0.040 |
Token | she |
Token ID | 673 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
der | +0.050 |
horizon | +0.048 |
moons | +0.045 |
oph | +0.044 |
asts | +0.043 |
Neg logit contributions | |
ang | -0.059 |
aking | -0.058 |
able | -0.055 |
itty | -0.055 |
iffs | -0.052 |
Token | Look |
Token ID | 8567 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
aking | +0.046 |
ang | +0.041 |
ymes | +0.040 |
able | +0.035 |
iffs | +0.034 |
Neg logit contributions | |
Daddy | -0.065 |
mummy | -0.063 |
Peter | -0.061 |
der | -0.060 |
Jack | -0.060 |
Token | what |
Token ID | 644 |
Feature activation | -1.02e-03 |
Pos logit contributions | |
Daddy | +0.069 |
der | +0.066 |
mummy | +0.065 |
Peter | +0.064 |
int | +0.062 |
Neg logit contributions | |
aking | -0.150 |
ang | -0.142 |
ymes | -0.137 |
iffs | -0.126 |
able | -0.125 |
Token | I |
Token ID | 314 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
Daddy | +0.002 |
mummy | +0.002 |
int | +0.002 |
Peter | +0.002 |
der | +0.002 |
Neg logit contributions | |
aking | -0.002 |
ang | -0.002 |
ymes | -0.002 |
able | -0.002 |
iffs | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Daddy | +0.047 |
mummy | +0.045 |
Peter | +0.045 |
der | +0.044 |
int | +0.043 |
Neg logit contributions | |
aking | -0.056 |
ang | -0.050 |
ymes | -0.048 |
able | -0.045 |
iffs | -0.044 |
Token | ! |
Token ID | 0 |
Feature activation | -7.07e-03 |
Pos logit contributions | |
der | +0.016 |
Daddy | +0.016 |
oph | +0.016 |
mummy | +0.015 |
int | +0.015 |
Neg logit contributions | |
aking | -0.020 |
ang | -0.018 |
ymes | -0.017 |
able | -0.016 |
iffs | -0.016 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
Daddy | +0.011 |
mummy | +0.011 |
int | +0.011 |
oph | +0.011 |
der | +0.011 |
Neg logit contributions | |
aking | -0.013 |
ang | -0.012 |
ymes | -0.011 |
iffs | -0.011 |
itty | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
Daddy | +0.129 |
mummy | +0.124 |
der | +0.123 |
Father | +0.120 |
Peter | +0.118 |
Neg logit contributions | |
aking | -0.191 |
ang | -0.176 |
ymes | -0.168 |
iffs | -0.157 |
ites | -0.154 |
Token | it |
Token ID | 340 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
mummy | +0.003 |
um | +0.003 |
Daddy | +0.003 |
int | +0.003 |
Father | +0.003 |
Neg logit contributions | |
aking | -0.006 |
ymes | -0.005 |
ang | -0.005 |
able | -0.005 |
respectful | -0.005 |
Token | great |
Token ID | 1049 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Daddy | +0.021 |
der | +0.021 |
oph | +0.021 |
mummy | +0.021 |
int | +0.021 |
Neg logit contributions | |
aking | -0.019 |
ymes | -0.016 |
ang | -0.015 |
able | -0.014 |
respectful | -0.014 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
Daddy | +0.025 |
Father | +0.024 |
oph | +0.024 |
Andrew | +0.024 |
int | +0.024 |
Neg logit contributions | |
aking | -0.032 |
ymes | -0.028 |
ang | -0.027 |
able | -0.027 |
iffs | -0.025 |
Token | |
Token ID | 220 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
der | +0.034 |
Daddy | +0.034 |
oph | +0.034 |
mummy | +0.034 |
int | +0.033 |
Neg logit contributions | |
aking | -0.057 |
ang | -0.055 |
ymes | -0.052 |
itty | -0.050 |
iffs | -0.049 |
Token | is |
Token ID | 318 |
Feature activation | -7.93e-03 |
Pos logit contributions | |
aking | +0.001 |
ymes | +0.001 |
ang | +0.001 |
able | +0.001 |
trap | +0.001 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
oph | -0.002 |
int | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +8.56e-03 |
Pos logit contributions | |
Daddy | +0.012 |
oph | +0.012 |
mummy | +0.012 |
der | +0.012 |
int | +0.012 |
Neg logit contributions | |
aking | -0.015 |
ang | -0.014 |
ymes | -0.013 |
able | -0.012 |
trap | -0.012 |
Token | fairy |
Token ID | 25607 |
Feature activation | +9.13e-03 |
Pos logit contributions | |
aking | +0.016 |
ymes | +0.015 |
ang | +0.014 |
able | +0.013 |
trap | +0.013 |
Neg logit contributions | |
Daddy | -0.014 |
Peter | -0.014 |
oph | -0.013 |
int | -0.013 |
der | -0.013 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
aking | +0.021 |
ang | +0.020 |
ymes | +0.019 |
iffs | +0.018 |
able | +0.018 |
Neg logit contributions | |
Daddy | -0.011 |
mummy | -0.011 |
Peter | -0.011 |
Jack | -0.010 |
written | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.004 |
ymes | +0.003 |
iffs | +0.003 |
able | +0.003 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.001 |
Peter | -0.001 |
Jack | -0.001 |
der | -0.001 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
aking | +0.059 |
ang | +0.056 |
ymes | +0.052 |
iffs | +0.050 |
able | +0.049 |
Neg logit contributions | |
Daddy | -0.046 |
mummy | -0.045 |
Peter | -0.043 |
int | -0.043 |
oph | -0.043 |
Token | 't |
Token ID | 470 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
Daddy | +0.128 |
mummy | +0.121 |
der | +0.117 |
Father | +0.116 |
Peter | +0.114 |
Neg logit contributions | |
aking | -0.192 |
ang | -0.180 |
ymes | -0.174 |
iffs | -0.161 |
trap | -0.158 |
Token | it |
Token ID | 340 |
Feature activation | -8.60e-03 |
Pos logit contributions | |
aking | +0.002 |
ymes | +0.002 |
able | +0.002 |
ang | +0.002 |
trap | +0.002 |
Neg logit contributions | |
um | -0.002 |
omm | -0.002 |
mummy | -0.001 |
oph | -0.001 |
Daddy | -0.001 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
der | +0.017 |
Daddy | +0.017 |
oph | +0.017 |
um | +0.016 |
Peter | +0.016 |
Neg logit contributions | |
aking | -0.013 |
ymes | -0.011 |
ang | -0.010 |
able | -0.010 |
respectful | -0.009 |
Token | ?" |
Token ID | 1701 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
oph | +0.033 |
Daddy | +0.032 |
Father | +0.031 |
Andrew | +0.031 |
Peter | +0.031 |
Neg logit contributions | |
aking | -0.030 |
ymes | -0.028 |
ang | -0.025 |
able | -0.025 |
iffs | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
der | +0.011 |
mummy | +0.011 |
oph | +0.011 |
um | +0.011 |
Peter | +0.011 |
Neg logit contributions | |
ang | -0.016 |
aking | -0.016 |
able | -0.015 |
ymes | -0.014 |
iffs | -0.014 |
Token | drew |
Token ID | 9859 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
Daddy | +0.043 |
mummy | +0.041 |
Peter | +0.040 |
Jack | +0.038 |
der | +0.038 |
Neg logit contributions | |
aking | -0.062 |
ang | -0.058 |
ymes | -0.056 |
able | -0.052 |
iffs | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
Daddy | +0.061 |
oph | +0.060 |
mummy | +0.059 |
Peter | +0.058 |
Father | +0.057 |
Neg logit contributions | |
aking | -0.084 |
ymes | -0.081 |
ang | -0.079 |
ites | -0.070 |
iffs | -0.070 |
Token | pink |
Token ID | 11398 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.006 |
ymes | +0.006 |
trap | +0.005 |
able | +0.005 |
Neg logit contributions | |
Daddy | -0.005 |
der | -0.005 |
Peter | -0.005 |
oph | -0.005 |
Jack | -0.005 |
Token | flower |
Token ID | 15061 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Daddy | +0.082 |
Andrew | +0.080 |
Peter | +0.079 |
Kevin | +0.079 |
int | +0.079 |
Neg logit contributions | |
ang | -0.072 |
aking | -0.072 |
ymes | -0.071 |
trap | -0.065 |
itty | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Daddy | +0.022 |
Peter | +0.021 |
mummy | +0.021 |
oph | +0.020 |
Father | +0.020 |
Neg logit contributions | |
aking | -0.031 |
ang | -0.029 |
ymes | -0.028 |
able | -0.026 |
trap | -0.025 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
aking | +0.046 |
ang | +0.044 |
iffs | +0.041 |
ymes | +0.041 |
able | +0.038 |
Neg logit contributions | |
Daddy | -0.033 |
mummy | -0.033 |
oph | -0.033 |
Peter | -0.032 |
int | -0.032 |
Token | 't |
Token ID | 470 |
Feature activation | -6.30e-04 |
Pos logit contributions | |
Daddy | +0.135 |
mummy | +0.129 |
Father | +0.128 |
der | +0.125 |
Peter | +0.125 |
Neg logit contributions | |
aking | -0.179 |
ang | -0.169 |
ymes | -0.163 |
iffs | -0.153 |
trap | -0.146 |
Token | it |
Token ID | 340 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
um | +0.001 |
Peter | +0.001 |
Father | +0.001 |
mummy | +0.001 |
omm | +0.001 |
Neg logit contributions | |
aking | -0.001 |
ymes | -0.001 |
ang | -0.001 |
able | -0.001 |
respectful | -0.001 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
der | +0.023 |
Daddy | +0.023 |
Peter | +0.023 |
oph | +0.022 |
Father | +0.022 |
Neg logit contributions | |
aking | -0.015 |
ymes | -0.013 |
ang | -0.012 |
respectful | -0.011 |
able | -0.011 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
Daddy | +0.058 |
Father | +0.058 |
Peter | +0.058 |
Andrew | +0.057 |
oph | +0.056 |
Neg logit contributions | |
aking | -0.050 |
ymes | -0.046 |
ang | -0.043 |
able | -0.040 |
iffs | -0.038 |
Token | she |
Token ID | 673 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
oph | +0.016 |
der | +0.016 |
um | +0.015 |
Peter | +0.014 |
ongs | +0.014 |
Neg logit contributions | |
ang | -0.021 |
aking | -0.020 |
ymes | -0.020 |
able | -0.019 |
iffs | -0.019 |
Token | shows |
Token ID | 2523 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
aking | +0.041 |
ang | +0.037 |
ymes | +0.036 |
able | +0.034 |
trap | +0.032 |
Neg logit contributions | |
Daddy | -0.036 |
oph | -0.035 |
der | -0.035 |
mummy | -0.035 |
int | -0.034 |
Token | all |
Token ID | 477 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
Daddy | +0.025 |
mummy | +0.024 |
oph | +0.024 |
Peter | +0.023 |
int | +0.023 |
Neg logit contributions | |
aking | -0.041 |
ymes | -0.038 |
ang | -0.037 |
able | -0.034 |
iffs | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
aking | +0.010 |
ang | +0.009 |
ymes | +0.009 |
able | +0.008 |
iffs | +0.008 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.006 |
Peter | -0.006 |
der | -0.006 |
int | -0.006 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
Daddy | +0.028 |
mummy | +0.026 |
Peter | +0.026 |
der | +0.026 |
oph | +0.025 |
Neg logit contributions | |
aking | -0.039 |
ymes | -0.036 |
ang | -0.036 |
able | -0.033 |
ites | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
Daddy | +0.077 |
mummy | +0.074 |
Peter | +0.073 |
oph | +0.072 |
int | +0.070 |
Neg logit contributions | |
aking | -0.127 |
ang | -0.117 |
ymes | -0.114 |
able | -0.107 |
iffs | -0.105 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
aking | +0.038 |
ang | +0.035 |
iffs | +0.032 |
ymes | +0.032 |
itty | +0.030 |
Neg logit contributions | |
oph | -0.035 |
Daddy | -0.034 |
int | -0.034 |
mummy | -0.034 |
der | -0.033 |
Token | 't |
Token ID | 470 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
Daddy | +0.127 |
mummy | +0.121 |
der | +0.118 |
Peter | +0.115 |
Father | +0.115 |
Neg logit contributions | |
aking | -0.190 |
ang | -0.176 |
ymes | -0.170 |
iffs | -0.157 |
ites | -0.155 |
Token | that |
Token ID | 326 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
aking | +0.004 |
able | +0.004 |
ang | +0.004 |
ymes | +0.004 |
respectful | +0.003 |
Neg logit contributions | |
oph | -0.004 |
omm | -0.003 |
um | -0.003 |
mummy | -0.003 |
ian | -0.003 |
Token | amazing |
Token ID | 4998 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
aking | +0.060 |
ymes | +0.055 |
ang | +0.050 |
able | +0.050 |
respectful | +0.050 |
Neg logit contributions | |
oph | -0.070 |
Daddy | -0.067 |
omm | -0.066 |
um | -0.066 |
der | -0.065 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
oph | +0.041 |
Daddy | +0.041 |
Peter | +0.040 |
int | +0.040 |
Jason | +0.039 |
Neg logit contributions | |
aking | -0.049 |
ymes | -0.045 |
ang | -0.044 |
able | -0.040 |
ites | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Daddy | +0.021 |
der | +0.020 |
oph | +0.020 |
mummy | +0.020 |
int | +0.020 |
Neg logit contributions | |
aking | -0.028 |
ang | -0.026 |
iffs | -0.024 |
itty | -0.023 |
able | -0.023 |
Token | made |
Token ID | 925 |
Feature activation | +4.56e-04 |
Pos logit contributions | |
Daddy | +0.037 |
mummy | +0.035 |
Jack | +0.034 |
couldn | +0.033 |
written | +0.033 |
Neg logit contributions | |
aking | -0.048 |
ang | -0.047 |
ymes | -0.047 |
iffs | -0.040 |
ites | -0.040 |
Token | Ruby |
Token ID | 10888 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
aking | +0.001 |
ymes | +0.001 |
ang | +0.001 |
iffs | +0.001 |
trap | +0.001 |
Neg logit contributions | |
der | -0.001 |
oph | -0.001 |
Father | -0.001 |
horizon | -0.001 |
Daddy | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
aking | +0.022 |
ang | +0.022 |
ymes | +0.020 |
iffs | +0.019 |
able | +0.019 |
Neg logit contributions | |
Daddy | -0.013 |
mummy | -0.013 |
Peter | -0.011 |
Jack | -0.011 |
even | -0.011 |
Token | princess |
Token ID | 21752 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
aking | +0.026 |
ang | +0.024 |
ymes | +0.023 |
able | +0.021 |
iffs | +0.021 |
Neg logit contributions | |
Daddy | -0.020 |
mummy | -0.019 |
Peter | -0.018 |
der | -0.018 |
Jack | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
aking | +0.003 |
ang | +0.003 |
ymes | +0.003 |
able | +0.003 |
iffs | +0.003 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.001 |
Peter | -0.001 |
Jack | -0.001 |
der | -0.001 |
Token | Isn |
Token ID | 25110 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
aking | +0.049 |
ang | +0.046 |
ymes | +0.044 |
iffs | +0.044 |
able | +0.042 |
Neg logit contributions | |
Daddy | -0.035 |
int | -0.035 |
mummy | -0.034 |
oph | -0.034 |
um | -0.033 |
Token | 't |
Token ID | 470 |
Feature activation | -4.56e-04 |
Pos logit contributions | |
Daddy | +0.128 |
mummy | +0.122 |
Father | +0.120 |
der | +0.118 |
Peter | +0.116 |
Neg logit contributions | |
aking | -0.187 |
ang | -0.174 |
ymes | -0.171 |
iffs | -0.159 |
able | -0.154 |
Token | she |
Token ID | 673 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
um | +0.001 |
mummy | +0.001 |
Father | +0.001 |
int | +0.001 |
Daddy | +0.001 |
Neg logit contributions | |
aking | -0.001 |
ymes | -0.001 |
able | -0.001 |
ang | -0.001 |
trap | -0.001 |
Token | much |
Token ID | 881 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
aking | +0.024 |
ang | +0.022 |
ymes | +0.022 |
able | +0.019 |
iffs | +0.019 |
Neg logit contributions | |
Daddy | -0.028 |
mummy | -0.027 |
Peter | -0.027 |
der | -0.026 |
int | -0.026 |
Token | better |
Token ID | 1365 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
aking | +0.055 |
ymes | +0.048 |
able | +0.046 |
ang | +0.043 |
respectful | +0.043 |
Neg logit contributions | |
Peter | -0.069 |
Daddy | -0.069 |
Andrew | -0.068 |
Father | -0.067 |
Kevin | -0.066 |
Token | now |
Token ID | 783 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
Daddy | +0.021 |
Peter | +0.021 |
int | +0.020 |
oph | +0.020 |
der | +0.020 |
Neg logit contributions | |
aking | -0.027 |
ang | -0.025 |
ymes | -0.024 |
able | -0.023 |
iffs | -0.022 |
Token | let |
Token ID | 1309 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
Daddy | +0.030 |
mummy | +0.029 |
Peter | +0.028 |
int | +0.027 |
der | +0.027 |
Neg logit contributions | |
aking | -0.039 |
ang | -0.037 |
ymes | -0.035 |
able | -0.033 |
iffs | -0.032 |
Token | go |
Token ID | 467 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
der | +0.008 |
Daddy | +0.007 |
int | +0.007 |
moons | +0.007 |
oph | +0.007 |
Neg logit contributions | |
aking | -0.013 |
ang | -0.012 |
ymes | -0.011 |
trap | -0.011 |
able | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
aking | +0.075 |
ymes | +0.073 |
ang | +0.071 |
able | +0.066 |
trap | +0.064 |
Neg logit contributions | |
Daddy | -0.034 |
mummy | -0.032 |
Peter | -0.030 |
Jack | -0.029 |
int | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +4.60e-04 |
Pos logit contributions | |
aking | +0.069 |
ang | +0.066 |
ymes | +0.063 |
able | +0.059 |
iffs | +0.058 |
Neg logit contributions | |
Daddy | -0.037 |
mummy | -0.035 |
Peter | -0.034 |
der | -0.034 |
int | -0.033 |
Token | hand |
Token ID | 1021 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.001 |
ymes | +0.001 |
iffs | +0.001 |
able | +0.001 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
sunset | -0.001 |
top | -0.001 |
Peter | -0.001 |
Token | ker |
Token ID | 6122 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.008 |
ymes | +0.007 |
able | +0.007 |
iffs | +0.007 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
der | -0.004 |
Jack | -0.003 |
Token | chief |
Token ID | 17351 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
Daddy | +0.105 |
written | +0.098 |
oph | +0.098 |
mummy | +0.097 |
Peter | +0.097 |
Neg logit contributions | |
aking | -0.206 |
ang | -0.196 |
ymes | -0.181 |
iffs | -0.179 |
ites | -0.169 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
aking | +0.014 |
ang | +0.013 |
ymes | +0.012 |
able | +0.011 |
iffs | +0.011 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.007 |
Peter | -0.006 |
Father | -0.006 |
oph | -0.006 |
Token | started |
Token ID | 2067 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
Daddy | +0.032 |
der | +0.032 |
mummy | +0.031 |
int | +0.031 |
oph | +0.030 |
Neg logit contributions | |
aking | -0.045 |
ang | -0.042 |
ymes | -0.039 |
able | -0.037 |
iffs | -0.037 |
Token | climbing |
Token ID | 14281 |
Feature activation | -1.66e-04 |
Pos logit contributions | |
aking | +0.018 |
ang | +0.017 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.015 |
Neg logit contributions | |
Daddy | -0.012 |
mummy | -0.011 |
Peter | -0.011 |
Jack | -0.010 |
int | -0.010 |
Token | back |
Token ID | 736 |
Feature activation | +7.35e-03 |
Pos logit contributions | |
Daddy | +0.000 |
mummy | +0.000 |
oph | +0.000 |
Peter | +0.000 |
Father | +0.000 |
Neg logit contributions | |
aking | -0.000 |
ang | -0.000 |
ymes | -0.000 |
able | -0.000 |
iffs | -0.000 |
Token | I |
Token ID | 314 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.001 |
ymes | +0.001 |
itty | +0.001 |
iffs | +0.001 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
der | -0.001 |
int | -0.001 |
oph | -0.001 |
Token | made |
Token ID | 925 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
Daddy | +0.025 |
mummy | +0.024 |
Peter | +0.023 |
Jack | +0.023 |
int | +0.022 |
Neg logit contributions | |
aking | -0.029 |
ang | -0.027 |
ymes | -0.026 |
iffs | -0.024 |
able | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
oph | +0.004 |
der | +0.004 |
horizon | +0.004 |
Daddy | +0.004 |
lit | +0.004 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.005 |
ymes | -0.005 |
iffs | -0.004 |
render | -0.004 |
Token | dress |
Token ID | 6576 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
aking | +0.023 |
ang | +0.022 |
ymes | +0.021 |
able | +0.019 |
iffs | +0.019 |
Neg logit contributions | |
Daddy | -0.021 |
mummy | -0.020 |
Peter | -0.019 |
der | -0.019 |
Jack | -0.019 |
Token | ! |
Token ID | 0 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
Daddy | +0.020 |
Peter | +0.019 |
mummy | +0.019 |
Father | +0.019 |
Andrew | +0.018 |
Neg logit contributions | |
aking | -0.030 |
ang | -0.028 |
ymes | -0.026 |
able | -0.025 |
iffs | -0.025 |
Token | Isn |
Token ID | 25110 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
Daddy | +0.010 |
mummy | +0.009 |
der | +0.009 |
int | +0.009 |
Peter | +0.009 |
Neg logit contributions | |
aking | -0.013 |
ang | -0.012 |
ymes | -0.011 |
iffs | -0.011 |
itty | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
Daddy | +0.132 |
Father | +0.128 |
der | +0.127 |
mummy | +0.127 |
Peter | +0.124 |
Neg logit contributions | |
aking | -0.179 |
ang | -0.169 |
ymes | -0.160 |
iffs | -0.149 |
ites | -0.146 |
Token | it |
Token ID | 340 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
int | +0.006 |
Father | +0.006 |
um | +0.006 |
horizon | +0.006 |
omm | +0.006 |
Neg logit contributions | |
aking | -0.009 |
ang | -0.008 |
ymes | -0.008 |
able | -0.008 |
respectful | -0.007 |
Token | pretty |
Token ID | 2495 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
Daddy | +0.027 |
der | +0.027 |
Peter | +0.026 |
mummy | +0.026 |
int | +0.026 |
Neg logit contributions | |
aking | -0.023 |
ang | -0.019 |
ymes | -0.019 |
able | -0.018 |
iffs | -0.016 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
Father | +0.057 |
Daddy | +0.056 |
Andrew | +0.055 |
Peter | +0.054 |
Jason | +0.053 |
Neg logit contributions | |
aking | -0.054 |
ymes | -0.049 |
ang | -0.046 |
able | -0.044 |
iffs | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
der | +0.037 |
oph | +0.035 |
written | +0.034 |
moons | +0.034 |
int | +0.033 |
Neg logit contributions | |
ang | -0.061 |
aking | -0.060 |
ymes | -0.053 |
able | -0.053 |
itty | -0.053 |
Token | " |
Token ID | 366 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
oph | +0.004 |
Daddy | +0.004 |
mummy | +0.004 |
Peter | +0.004 |
um | +0.004 |
Neg logit contributions | |
aking | -0.007 |
ang | -0.007 |
ymes | -0.006 |
iffs | -0.006 |
aring | -0.006 |
Token | Look |
Token ID | 8567 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
aking | +0.070 |
ymes | +0.065 |
ang | +0.065 |
render | +0.056 |
able | +0.056 |
Neg logit contributions | |
Daddy | -0.055 |
mummy | -0.052 |
Peter | -0.051 |
Jack | -0.050 |
oph | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
der | +0.059 |
Daddy | +0.059 |
mummy | +0.055 |
Peter | +0.055 |
int | +0.054 |
Neg logit contributions | |
aking | -0.168 |
ang | -0.161 |
ymes | -0.154 |
iffs | -0.145 |
able | -0.144 |
Token | Tom |
Token ID | 4186 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
Daddy | +0.003 |
mummy | +0.002 |
Peter | +0.002 |
Jack | +0.002 |
der | +0.002 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.005 |
ymes | -0.005 |
able | -0.004 |
iffs | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | +3.59e-04 |
Pos logit contributions | |
Daddy | +0.003 |
Jack | +0.002 |
mummy | +0.002 |
Peter | +0.002 |
Andrew | +0.002 |
Neg logit contributions | |
aking | -0.012 |
ang | -0.012 |
ymes | -0.012 |
iffs | -0.011 |
able | -0.011 |
Token | Isn |
Token ID | 25110 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.001 |
ymes | +0.001 |
able | +0.001 |
beh | +0.001 |
Neg logit contributions | |
Daddy | -0.000 |
mummy | -0.000 |
Peter | -0.000 |
Jack | -0.000 |
Jenna | -0.000 |
Token | 't |
Token ID | 470 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
Daddy | +0.117 |
mummy | +0.111 |
der | +0.107 |
Peter | +0.106 |
Father | +0.104 |
Neg logit contributions | |
aking | -0.202 |
ang | -0.190 |
ymes | -0.180 |
iffs | -0.171 |
able | -0.167 |
Token | it |
Token ID | 340 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
mummy | +0.002 |
Daddy | +0.002 |
int | +0.002 |
um | +0.002 |
Peter | +0.002 |
Neg logit contributions | |
aking | -0.004 |
ang | -0.004 |
ymes | -0.003 |
able | -0.003 |
trap | -0.003 |
Token | cool |
Token ID | 3608 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
Daddy | +0.019 |
mummy | +0.018 |
Peter | +0.018 |
der | +0.018 |
int | +0.018 |
Neg logit contributions | |
aking | -0.018 |
ang | -0.016 |
ymes | -0.016 |
able | -0.014 |
iffs | -0.014 |
Token | ? |
Token ID | 30 |
Feature activation | +2.71e-04 |
Pos logit contributions | |
Daddy | +0.025 |
Father | +0.024 |
mummy | +0.024 |
Peter | +0.024 |
Andrew | +0.023 |
Neg logit contributions | |
aking | -0.030 |
ang | -0.026 |
ymes | -0.025 |
able | -0.024 |
iffs | -0.024 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.001 |
ymes | +0.001 |
able | +0.001 |
iffs | +0.001 |
Neg logit contributions | |
Daddy | -0.000 |
mummy | -0.000 |
Peter | -0.000 |
int | -0.000 |
der | -0.000 |
Token | I |
Token ID | 314 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
Daddy | +0.017 |
int | +0.017 |
der | +0.017 |
mummy | +0.016 |
Peter | +0.016 |
Neg logit contributions | |
aking | -0.025 |
ang | -0.024 |
ymes | -0.023 |
able | -0.021 |
iffs | -0.021 |
Token | painted |
Token ID | 13055 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Daddy | +0.033 |
mummy | +0.031 |
Peter | +0.030 |
Jack | +0.029 |
der | +0.028 |
Neg logit contributions | |
aking | -0.056 |
ang | -0.053 |
ymes | -0.051 |
able | -0.047 |
iffs | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Daddy | +0.061 |
oph | +0.060 |
der | +0.059 |
mummy | +0.058 |
int | +0.057 |
Neg logit contributions | |
aking | -0.095 |
ang | -0.091 |
ymes | -0.089 |
iffs | -0.079 |
able | -0.078 |
Token | wall |
Token ID | 3355 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Daddy | +0.013 |
mummy | +0.012 |
Peter | +0.012 |
der | +0.012 |
oph | +0.011 |
Neg logit contributions | |
aking | -0.024 |
ang | -0.022 |
ymes | -0.022 |
able | -0.020 |
iffs | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.43e-03 |
Pos logit contributions | |
Daddy | +0.020 |
mummy | +0.019 |
Peter | +0.018 |
Jack | +0.017 |
der | +0.017 |
Neg logit contributions | |
aking | -0.032 |
ang | -0.030 |
ymes | -0.030 |
able | -0.027 |
iffs | -0.027 |
Token | Isn |
Token ID | 25110 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
aking | +0.005 |
ang | +0.004 |
ymes | +0.004 |
iffs | +0.004 |
itty | +0.004 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
int | -0.003 |
oph | -0.003 |
der | -0.003 |
Token | 't |
Token ID | 470 |
Feature activation | +8.14e-04 |
Pos logit contributions | |
Daddy | +0.126 |
mummy | +0.121 |
Father | +0.118 |
der | +0.118 |
Peter | +0.114 |
Neg logit contributions | |
aking | -0.188 |
ang | -0.175 |
ymes | -0.168 |
iffs | -0.156 |
trap | -0.151 |
Token | it |
Token ID | 340 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
aking | +0.002 |
ang | +0.002 |
able | +0.002 |
ymes | +0.002 |
trap | +0.001 |
Neg logit contributions | |
um | -0.001 |
mummy | -0.001 |
int | -0.001 |
oph | -0.001 |
omm | -0.001 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
der | +0.019 |
Daddy | +0.019 |
oph | +0.018 |
Father | +0.018 |
Peter | +0.018 |
Neg logit contributions | |
aking | -0.014 |
ymes | -0.012 |
ang | -0.011 |
able | -0.010 |
respectful | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
Daddy | +0.020 |
Father | +0.020 |
Peter | +0.020 |
Andrew | +0.020 |
mummy | +0.019 |
Neg logit contributions | |
aking | -0.025 |
ymes | -0.021 |
ang | -0.021 |
iffs | -0.020 |
able | -0.019 |
Token | spicy |
Token ID | 26880 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
aking | +0.013 |
ang | +0.012 |
ymes | +0.011 |
able | +0.010 |
iffs | +0.010 |
Neg logit contributions | |
Daddy | -0.013 |
mummy | -0.013 |
Peter | -0.013 |
Jack | -0.012 |
der | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -6.76e-04 |
Pos logit contributions | |
Daddy | +0.049 |
mummy | +0.048 |
oph | +0.048 |
Peter | +0.047 |
int | +0.046 |
Neg logit contributions | |
aking | -0.074 |
ang | -0.069 |
ymes | -0.069 |
able | -0.063 |
iffs | -0.062 |
Token | dishes |
Token ID | 16759 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
oph | +0.001 |
Peter | +0.001 |
Daddy | +0.001 |
Jenna | +0.001 |
Jack | +0.001 |
Neg logit contributions | |
aking | -0.001 |
ymes | -0.001 |
ang | -0.001 |
able | -0.001 |
iffs | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | +6.42e-04 |
Pos logit contributions | |
Daddy | +0.022 |
Peter | +0.022 |
mummy | +0.021 |
oph | +0.021 |
Jenna | +0.020 |
Neg logit contributions | |
aking | -0.048 |
ang | -0.045 |
ymes | -0.044 |
able | -0.042 |
iffs | -0.041 |
Token | us |
Token ID | 514 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
aking | +0.001 |
ymes | +0.001 |
ang | +0.001 |
iffs | +0.001 |
render | +0.001 |
Neg logit contributions | |
int | -0.001 |
oph | -0.001 |
der | -0.001 |
Peter | -0.001 |
Daddy | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
aking | +0.071 |
ang | +0.068 |
ymes | +0.066 |
able | +0.062 |
iffs | +0.061 |
Neg logit contributions | |
Daddy | -0.029 |
mummy | -0.026 |
Peter | -0.025 |
Jack | -0.024 |
der | -0.023 |
Token | Isn |
Token ID | 25110 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
aking | +0.050 |
ang | +0.046 |
ymes | +0.043 |
iffs | +0.042 |
able | +0.040 |
Neg logit contributions | |
Daddy | -0.037 |
mummy | -0.037 |
oph | -0.036 |
Peter | -0.036 |
int | -0.036 |
Token | 't |
Token ID | 470 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
Daddy | +0.111 |
mummy | +0.105 |
Peter | +0.101 |
der | +0.099 |
Father | +0.095 |
Neg logit contributions | |
aking | -0.208 |
ang | -0.195 |
ymes | -0.189 |
iffs | -0.175 |
able | -0.175 |
Token | that |
Token ID | 326 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
aking | +0.009 |
ang | +0.008 |
ymes | +0.008 |
able | +0.008 |
respectful | +0.007 |
Neg logit contributions | |
oph | -0.006 |
int | -0.006 |
um | -0.006 |
mummy | -0.006 |
omm | -0.005 |
Token | amazing |
Token ID | 4998 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
aking | +0.055 |
ymes | +0.051 |
respectful | +0.046 |
able | +0.046 |
ang | +0.044 |
Neg logit contributions | |
oph | -0.083 |
Peter | -0.079 |
Daddy | -0.079 |
der | -0.078 |
horizon | -0.078 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.02e-03 |
Pos logit contributions | |
oph | +0.040 |
int | +0.038 |
Daddy | +0.037 |
Peter | +0.037 |
Jenna | +0.037 |
Neg logit contributions | |
aking | -0.038 |
ymes | -0.034 |
ang | -0.032 |
able | -0.032 |
respectful | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
der | +0.008 |
oph | +0.007 |
ongs | +0.007 |
horizon | +0.007 |
int | +0.006 |
Neg logit contributions | |
ang | -0.016 |
aking | -0.016 |
able | -0.015 |
ymes | -0.014 |
iffs | -0.014 |
Token | flavors |
Token ID | 17361 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
Peter | +0.061 |
mummy | +0.058 |
Jenna | +0.058 |
Daddy | +0.056 |
int | +0.055 |
Neg logit contributions | |
aking | -0.085 |
ang | -0.077 |
able | -0.072 |
iffs | -0.070 |
ymes | -0.068 |
Token | they |
Token ID | 484 |
Feature activation | -8.30e-03 |
Pos logit contributions | |
Peter | +0.065 |
mummy | +0.063 |
Daddy | +0.062 |
Jenna | +0.062 |
Father | +0.061 |
Neg logit contributions | |
aking | -0.090 |
ang | -0.082 |
able | -0.077 |
iffs | -0.073 |
ymes | -0.072 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
Daddy | +0.011 |
Peter | +0.011 |
mummy | +0.011 |
der | +0.011 |
oph | +0.011 |
Neg logit contributions | |
aking | -0.017 |
ang | -0.016 |
able | -0.015 |
ymes | -0.015 |
trap | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Daddy | +0.015 |
mummy | +0.015 |
Peter | +0.015 |
oph | +0.014 |
der | +0.014 |
Neg logit contributions | |
aking | -0.031 |
ang | -0.030 |
ymes | -0.029 |
able | -0.028 |
iffs | -0.026 |
Token | what |
Token ID | 644 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
Daddy | +0.021 |
mummy | +0.020 |
Peter | +0.020 |
oph | +0.020 |
um | +0.020 |
Neg logit contributions | |
aking | -0.037 |
ang | -0.034 |
ymes | -0.033 |
able | -0.032 |
respectful | -0.030 |
Token | topp |
Token ID | 23126 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
der | +0.023 |
int | +0.023 |
Daddy | +0.022 |
horizon | +0.022 |
oph | +0.022 |
Neg logit contributions | |
aking | -0.042 |
ymes | -0.041 |
ang | -0.040 |
able | -0.040 |
respectful | -0.037 |
Token | ings |
Token ID | 654 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
Daddy | +0.180 |
mummy | +0.174 |
Peter | +0.174 |
Jenna | +0.167 |
Father | +0.164 |
Neg logit contributions | |
aking | -0.139 |
ang | -0.125 |
ymes | -0.125 |
able | -0.116 |
iffs | -0.109 |
Token | would |
Token ID | 561 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
Daddy | +0.034 |
mummy | +0.033 |
Peter | +0.032 |
oph | +0.031 |
int | +0.031 |
Neg logit contributions | |
aking | -0.067 |
ang | -0.062 |
ymes | -0.061 |
able | -0.061 |
iffs | -0.056 |
Token | go |
Token ID | 467 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
Daddy | +0.095 |
Peter | +0.092 |
mummy | +0.092 |
oph | +0.089 |
der | +0.089 |
Neg logit contributions | |
aking | -0.097 |
ang | -0.087 |
able | -0.082 |
ymes | -0.081 |
trap | -0.079 |
Token | best |
Token ID | 1266 |
Feature activation | +8.47e-03 |
Pos logit contributions | |
aking | +0.066 |
ang | +0.062 |
ymes | +0.061 |
able | +0.056 |
iffs | +0.056 |
Neg logit contributions | |
Daddy | -0.035 |
mummy | -0.033 |
Peter | -0.032 |
Jack | -0.031 |
der | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
aking | +0.019 |
ang | +0.018 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.015 |
Neg logit contributions | |
Daddy | -0.011 |
Peter | -0.011 |
mummy | -0.011 |
oph | -0.010 |
int | -0.010 |
Token | forms |
Token ID | 5107 |
Feature activation | -3.93e-04 |
Pos logit contributions | |
Daddy | +0.014 |
mummy | +0.014 |
Peter | +0.013 |
oph | +0.013 |
Jack | +0.013 |
Neg logit contributions | |
aking | -0.015 |
ang | -0.013 |
ymes | -0.013 |
able | -0.012 |
iffs | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.000 |
Peter | +0.000 |
int | +0.000 |
der | +0.000 |
Neg logit contributions | |
aking | -0.001 |
ang | -0.001 |
ymes | -0.001 |
able | -0.001 |
iffs | -0.001 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
aking | +0.005 |
ang | +0.005 |
ymes | +0.005 |
able | +0.004 |
trap | +0.004 |
Neg logit contributions | |
Daddy | -0.005 |
der | -0.005 |
Peter | -0.005 |
mummy | -0.005 |
oph | -0.005 |
Token | picture |
Token ID | 4286 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
Daddy | +0.047 |
der | +0.044 |
mummy | +0.044 |
Peter | +0.044 |
Andrew | +0.043 |
Neg logit contributions | |
aking | -0.058 |
ymes | -0.054 |
ang | -0.051 |
able | -0.051 |
trap | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
Daddy | +0.036 |
mummy | +0.035 |
oph | +0.033 |
int | +0.033 |
Father | +0.033 |
Neg logit contributions | |
aking | -0.049 |
ang | -0.045 |
ymes | -0.043 |
able | -0.042 |
trap | -0.040 |
Token | Isn |
Token ID | 25110 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
aking | +0.009 |
ang | +0.009 |
ymes | +0.008 |
iffs | +0.008 |
able | +0.008 |
Neg logit contributions | |
Daddy | -0.005 |
mummy | -0.005 |
Peter | -0.005 |
int | -0.005 |
der | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
Daddy | +0.119 |
mummy | +0.113 |
der | +0.108 |
Peter | +0.107 |
Father | +0.106 |
Neg logit contributions | |
aking | -0.194 |
ang | -0.182 |
ymes | -0.175 |
iffs | -0.161 |
able | -0.159 |
Token | that |
Token ID | 326 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
um | +0.001 |
mummy | +0.001 |
int | +0.001 |
omm | +0.001 |
oph | +0.001 |
Neg logit contributions | |
aking | -0.002 |
ang | -0.002 |
able | -0.002 |
ymes | -0.002 |
respectful | -0.002 |
Token | cool |
Token ID | 3608 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
aking | +0.065 |
ymes | +0.060 |
ang | +0.058 |
able | +0.057 |
trap | +0.054 |
Neg logit contributions | |
Daddy | -0.070 |
oph | -0.069 |
um | -0.068 |
der | -0.068 |
mummy | -0.067 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
Daddy | +0.031 |
mummy | +0.030 |
Peter | +0.030 |
der | +0.029 |
oph | +0.029 |
Neg logit contributions | |
aking | -0.049 |
ymes | -0.044 |
ang | -0.044 |
able | -0.042 |
iffs | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
der | +0.023 |
written | +0.021 |
moons | +0.021 |
oph | +0.021 |
Daddy | +0.021 |
Neg logit contributions | |
ang | -0.043 |
aking | -0.041 |
ymes | -0.037 |
itty | -0.037 |
able | -0.037 |
Token | found |
Token ID | 1043 |
Feature activation | +8.56e-03 |
Pos logit contributions | |
aking | +0.032 |
ang | +0.030 |
ymes | +0.028 |
able | +0.027 |
trap | +0.026 |
Neg logit contributions | |
Daddy | -0.021 |
mummy | -0.019 |
Peter | -0.019 |
der | -0.019 |
int | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
aking | +0.019 |
ang | +0.017 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.016 |
Neg logit contributions | |
Daddy | -0.011 |
oph | -0.011 |
Peter | -0.011 |
der | -0.010 |
mummy | -0.010 |
Token | big |
Token ID | 1263 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
aking | +0.017 |
ang | +0.017 |
ymes | +0.016 |
beh | +0.015 |
able | +0.015 |
Neg logit contributions | |
Daddy | -0.014 |
mummy | -0.014 |
Peter | -0.013 |
Jack | -0.012 |
Father | -0.012 |
Token | black |
Token ID | 2042 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.007 |
ymes | +0.007 |
beh | +0.007 |
able | +0.007 |
Neg logit contributions | |
Daddy | -0.006 |
mummy | -0.005 |
Peter | -0.005 |
Jack | -0.005 |
der | -0.005 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
Daddy | +0.045 |
mummy | +0.043 |
Peter | +0.043 |
int | +0.041 |
Jack | +0.041 |
Neg logit contributions | |
aking | -0.046 |
ang | -0.042 |
ymes | -0.041 |
able | -0.037 |
iffs | -0.036 |
Token | ker |
Token ID | 6122 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
Daddy | +0.004 |
mummy | +0.003 |
Peter | +0.003 |
oph | +0.003 |
int | +0.003 |
Neg logit contributions | |
aking | -0.006 |
ang | -0.006 |
ymes | -0.006 |
able | -0.005 |
itty | -0.005 |
Token | chief |
Token ID | 17351 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
Daddy | +0.103 |
Peter | +0.096 |
mummy | +0.095 |
oph | +0.094 |
der | +0.093 |
Neg logit contributions | |
aking | -0.202 |
ang | -0.192 |
ymes | -0.181 |
iffs | -0.176 |
ighed | -0.169 |
Token | in |
Token ID | 287 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
Daddy | +0.002 |
mummy | +0.002 |
Peter | +0.002 |
Father | +0.002 |
oph | +0.002 |
Neg logit contributions | |
aking | -0.003 |
ang | -0.003 |
ymes | -0.002 |
able | -0.002 |
trap | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
Daddy | +0.027 |
mummy | +0.025 |
Peter | +0.024 |
der | +0.023 |
int | +0.023 |
Neg logit contributions | |
aking | -0.053 |
ang | -0.050 |
ymes | -0.048 |
able | -0.045 |
iffs | -0.045 |
Token | pocket |
Token ID | 10000 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
aking | +0.031 |
ang | +0.028 |
ymes | +0.027 |
able | +0.025 |
iffs | +0.024 |
Neg logit contributions | |
Daddy | -0.028 |
Peter | -0.027 |
mummy | -0.027 |
int | -0.026 |
der | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
aking | +0.007 |
ang | +0.006 |
ymes | +0.006 |
able | +0.006 |
aring | +0.006 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
oph | -0.004 |
Andrew | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
Peter | +0.035 |
Daddy | +0.034 |
mummy | +0.034 |
Andrew | +0.033 |
oph | +0.033 |
Neg logit contributions | |
aking | -0.046 |
ang | -0.040 |
ymes | -0.039 |
able | -0.039 |
aring | -0.036 |
Token | said |
Token ID | 531 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
aking | +0.080 |
ang | +0.076 |
ymes | +0.072 |
able | +0.068 |
iffs | +0.068 |
Neg logit contributions | |
Daddy | -0.042 |
mummy | -0.040 |
Peter | -0.039 |
int | -0.037 |
der | -0.036 |
Token | : |
Token ID | 25 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
aking | +0.064 |
ang | +0.061 |
ymes | +0.060 |
able | +0.057 |
iffs | +0.056 |
Neg logit contributions | |
Daddy | -0.017 |
Peter | -0.016 |
mummy | -0.016 |
oph | -0.014 |
Andrew | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +7.09e-03 |
Pos logit contributions | |
aking | +0.027 |
ang | +0.026 |
ymes | +0.025 |
iffs | +0.025 |
arl | +0.023 |
Neg logit contributions | |
Daddy | -0.015 |
mummy | -0.014 |
Peter | -0.014 |
oph | -0.014 |
der | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
aking | +0.019 |
ang | +0.018 |
ymes | +0.017 |
able | +0.016 |
iffs | +0.016 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.006 |
Peter | -0.006 |
Jack | -0.006 |
int | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
aking | +0.015 |
ymes | +0.014 |
ang | +0.014 |
asc | +0.013 |
trap | +0.013 |
Neg logit contributions | |
Daddy | -0.011 |
mummy | -0.010 |
um | -0.010 |
Peter | -0.010 |
Jenna | -0.009 |
Token | Good |
Token ID | 10248 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
aking | +0.139 |
ang | +0.124 |
ymes | +0.119 |
unnecessary | +0.112 |
asc | +0.111 |
Neg logit contributions | |
Daddy | -0.131 |
der | -0.123 |
mummy | -0.121 |
Jack | -0.117 |
Peter | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
aking | +0.024 |
ang | +0.023 |
ymes | +0.022 |
able | +0.021 |
iffs | +0.020 |
Neg logit contributions | |
Daddy | -0.015 |
mummy | -0.014 |
Peter | -0.014 |
int | -0.013 |
Jack | -0.013 |
Token | Now |
Token ID | 2735 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
aking | +0.088 |
ymes | +0.083 |
ang | +0.081 |
able | +0.075 |
trap | +0.072 |
Neg logit contributions | |
Daddy | -0.059 |
Peter | -0.054 |
mummy | -0.054 |
Jack | -0.052 |
Jenna | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
Daddy | +0.043 |
der | +0.042 |
int | +0.041 |
Peter | +0.041 |
mummy | +0.041 |
Neg logit contributions | |
aking | -0.086 |
ang | -0.080 |
ymes | -0.078 |
iffs | -0.073 |
able | -0.073 |
Token | let |
Token ID | 1309 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.008 |
ymes | +0.008 |
able | +0.007 |
iffs | +0.007 |
Neg logit contributions | |
Daddy | -0.005 |
mummy | -0.005 |
Peter | -0.005 |
Jack | -0.005 |
der | -0.004 |
Token | Wow |
Token ID | 22017 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
aking | +0.130 |
ang | +0.122 |
ymes | +0.114 |
aring | +0.106 |
beh | +0.104 |
Neg logit contributions | |
Daddy | -0.121 |
mummy | -0.116 |
der | -0.113 |
oph | -0.111 |
Jack | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Daddy | +0.017 |
mummy | +0.015 |
Peter | +0.015 |
Jack | +0.013 |
der | +0.013 |
Neg logit contributions | |
aking | -0.063 |
ang | -0.060 |
ymes | -0.058 |
able | -0.055 |
iffs | -0.055 |
Token | they |
Token ID | 484 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
aking | +0.023 |
ang | +0.022 |
ymes | +0.021 |
able | +0.020 |
iffs | +0.019 |
Neg logit contributions | |
Daddy | -0.015 |
mummy | -0.014 |
Peter | -0.014 |
Jack | -0.013 |
der | -0.013 |
Token | splash |
Token ID | 22870 |
Feature activation | -4.88e-04 |
Pos logit contributions | |
ang | +0.021 |
aking | +0.021 |
ymes | +0.020 |
iffs | +0.018 |
itty | +0.018 |
Neg logit contributions | |
Daddy | -0.015 |
mummy | -0.014 |
Jack | -0.014 |
Peter | -0.013 |
written | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.000 |
Jack | +0.000 |
Peter | +0.000 |
um | +0.000 |
Neg logit contributions | |
aking | -0.001 |
ang | -0.001 |
ymes | -0.001 |
itty | -0.001 |
beh | -0.001 |
Token | lot |
Token ID | 1256 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
aking | +0.036 |
ang | +0.033 |
ymes | +0.032 |
beh | +0.030 |
iffs | +0.030 |
Neg logit contributions | |
Daddy | -0.025 |
mummy | -0.024 |
Peter | -0.022 |
der | -0.022 |
int | -0.022 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
aking | +0.174 |
ang | +0.163 |
ymes | +0.156 |
able | +0.149 |
iffs | +0.146 |
Neg logit contributions | |
Daddy | -0.108 |
mummy | -0.102 |
Peter | -0.101 |
Jack | -0.093 |
int | -0.093 |
Token | Lily |
Token ID | 20037 |
Feature activation | +6.70e-03 |
Pos logit contributions | |
int | +0.027 |
der | +0.027 |
aloud | +0.026 |
written | +0.026 |
oph | +0.026 |
Neg logit contributions | |
ang | -0.027 |
aking | -0.027 |
able | -0.026 |
iffs | -0.025 |
etchup | -0.025 |
Token | says |
Token ID | 1139 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
aking | +0.013 |
ang | +0.011 |
ymes | +0.011 |
iffs | +0.010 |
ites | +0.010 |
Neg logit contributions | |
mummy | -0.011 |
Daddy | -0.011 |
Peter | -0.010 |
oph | -0.010 |
um | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
aking | +0.099 |
ang | +0.093 |
ymes | +0.091 |
able | +0.085 |
iffs | +0.085 |
Neg logit contributions | |
Daddy | -0.044 |
oph | -0.044 |
mummy | -0.043 |
Peter | -0.042 |
der | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
aking | +0.056 |
ang | +0.054 |
iffs | +0.053 |
ymes | +0.048 |
Spot | +0.048 |
Neg logit contributions | |
oph | -0.042 |
int | -0.040 |
Peter | -0.040 |
mummy | -0.040 |
King | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
written | +0.002 |
lit | +0.002 |
Daddy | +0.002 |
mummy | +0.002 |
int | +0.002 |
Neg logit contributions | |
aking | -0.004 |
ang | -0.004 |
iffs | -0.004 |
ymes | -0.004 |
itty | -0.004 |
Token | wanted |
Token ID | 2227 |
Feature activation | +9.39e-03 |
Pos logit contributions | |
aking | +0.014 |
ang | +0.013 |
ymes | +0.012 |
able | +0.012 |
har | +0.011 |
Neg logit contributions | |
Daddy | -0.009 |
mummy | -0.008 |
der | -0.008 |
int | -0.008 |
Peter | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +2.79e-03 |
Pos logit contributions | |
aking | +0.016 |
ymes | +0.015 |
able | +0.014 |
ang | +0.014 |
iffs | +0.014 |
Neg logit contributions | |
der | -0.014 |
um | -0.014 |
int | -0.014 |
Daddy | -0.014 |
mummy | -0.014 |
Token | take |
Token ID | 1011 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.004 |
ymes | +0.004 |
trap | +0.004 |
iffs | +0.004 |
Neg logit contributions | |
der | -0.005 |
Daddy | -0.005 |
int | -0.005 |
oph | -0.005 |
Peter | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
aking | +0.050 |
ang | +0.047 |
ymes | +0.047 |
able | +0.044 |
iffs | +0.043 |
Neg logit contributions | |
Daddy | -0.029 |
der | -0.028 |
mummy | -0.027 |
Peter | -0.027 |
int | -0.026 |
Token | lot |
Token ID | 1256 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
aking | +0.016 |
ang | +0.015 |
ymes | +0.015 |
able | +0.013 |
iffs | +0.013 |
Neg logit contributions | |
Daddy | -0.012 |
mummy | -0.012 |
Peter | -0.012 |
Jack | -0.011 |
int | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
aking | +0.161 |
ang | +0.151 |
ymes | +0.145 |
able | +0.137 |
iffs | +0.134 |
Neg logit contributions | |
Daddy | -0.105 |
mummy | -0.100 |
Peter | -0.097 |
Jack | -0.092 |
der | -0.092 |
Token | pictures |
Token ID | 5986 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
aking | +0.085 |
ang | +0.079 |
ymes | +0.076 |
able | +0.071 |
iffs | +0.069 |
Neg logit contributions | |
Daddy | -0.073 |
mummy | -0.070 |
Peter | -0.068 |
der | -0.066 |
int | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
Daddy | +0.063 |
mummy | +0.061 |
Father | +0.061 |
Peter | +0.058 |
Andrew | +0.058 |
Neg logit contributions | |
aking | -0.082 |
ang | -0.074 |
ymes | -0.070 |
able | -0.069 |
itty | -0.065 |
Token | show |
Token ID | 905 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
der | +0.009 |
Daddy | +0.009 |
int | +0.008 |
Peter | +0.008 |
mummy | +0.008 |
Neg logit contributions | |
aking | -0.011 |
ang | -0.011 |
ymes | -0.011 |
able | -0.010 |
render | -0.009 |
Token | Grand |
Token ID | 5675 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Daddy | +0.016 |
der | +0.015 |
oph | +0.015 |
mummy | +0.015 |
int | +0.015 |
Neg logit contributions | |
aking | -0.031 |
ymes | -0.031 |
ang | -0.029 |
able | -0.028 |
respectful | -0.027 |
Token | ashing |
Token ID | 2140 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ymes | +0.007 |
render | +0.006 |
aking | +0.005 |
able | +0.005 |
ang | +0.005 |
Neg logit contributions | |
um | -0.010 |
der | -0.010 |
int | -0.010 |
Daddy | -0.010 |
Jack | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
aking | +0.026 |
ang | +0.025 |
ymes | +0.024 |
iffs | +0.023 |
itty | +0.022 |
Neg logit contributions | |
Daddy | -0.013 |
mummy | -0.012 |
Peter | -0.012 |
Jack | -0.012 |
der | -0.012 |
Token | p |
Token ID | 279 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
mummy | +0.010 |
Daddy | +0.010 |
sunset | +0.009 |
moon | +0.009 |
even | +0.009 |
Neg logit contributions | |
aking | -0.016 |
ang | -0.015 |
ymes | -0.015 |
render | -0.014 |
iffs | -0.014 |
Token | udd |
Token ID | 4185 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ymes | +0.014 |
aking | +0.013 |
render | +0.012 |
able | +0.012 |
trap | +0.011 |
Neg logit contributions | |
um | -0.020 |
der | -0.020 |
Daddy | -0.019 |
mummy | -0.019 |
int | -0.019 |
Token | les |
Token ID | 829 |
Feature activation | -1.01e-03 |
Pos logit contributions | |
Daddy | +0.013 |
mummy | +0.012 |
Peter | +0.011 |
der | +0.011 |
int | +0.011 |
Neg logit contributions | |
aking | -0.030 |
ang | -0.028 |
ymes | -0.028 |
iffs | -0.026 |
able | -0.025 |
Token | as |
Token ID | 355 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.001 |
Peter | +0.001 |
Jack | +0.001 |
der | +0.001 |
Neg logit contributions | |
aking | -0.002 |
ang | -0.002 |
ymes | -0.002 |
able | -0.002 |
iffs | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
aking | +0.159 |
ang | +0.148 |
ymes | +0.144 |
iffs | +0.134 |
able | +0.133 |
Neg logit contributions | |
Daddy | -0.092 |
mummy | -0.087 |
Peter | -0.083 |
Jack | -0.082 |
der | -0.078 |
Token | went |
Token ID | 1816 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.011 |
Peter | +0.011 |
Jack | +0.011 |
der | +0.010 |
Neg logit contributions | |
aking | -0.022 |
ang | -0.020 |
ymes | -0.020 |
able | -0.019 |
iffs | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
aking | +0.070 |
ymes | +0.067 |
ang | +0.066 |
able | +0.061 |
iffs | +0.059 |
Neg logit contributions | |
Daddy | -0.035 |
mummy | -0.034 |
Peter | -0.032 |
Jack | -0.031 |
int | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
oph | +0.002 |
der | +0.002 |
Daddy | +0.002 |
written | +0.002 |
mummy | +0.002 |
Neg logit contributions | |
aking | -0.004 |
ang | -0.004 |
iffs | -0.004 |
ymes | -0.004 |
Follow | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
Daddy | +0.007 |
der | +0.006 |
mummy | +0.006 |
oph | +0.006 |
Peter | +0.006 |
Neg logit contributions | |
aking | -0.012 |
ang | -0.011 |
ymes | -0.011 |
iffs | -0.010 |
able | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
aking | +0.003 |
ang | +0.003 |
ymes | +0.003 |
able | +0.002 |
iffs | +0.002 |
Neg logit contributions | |
Daddy | -0.001 |
Peter | -0.001 |
mummy | -0.001 |
oph | -0.001 |
Andrew | -0.001 |
Token | � |
Token ID | 6184 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
oph | +0.008 |
Daddy | +0.007 |
mummy | +0.007 |
um | +0.007 |
moons | +0.007 |
Neg logit contributions | |
aking | -0.011 |
ang | -0.011 |
aring | -0.010 |
cautious | -0.010 |
ymes | -0.010 |
Token | � |
Token ID | 95 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
aking | +0.009 |
ymes | +0.008 |
ang | +0.008 |
able | +0.008 |
ites | +0.007 |
Neg logit contributions | |
Daddy | -0.006 |
mummy | -0.006 |
der | -0.006 |
um | -0.006 |
int | -0.006 |
Token | € |
Token ID | 26391 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
ang | +0.036 |
aking | +0.035 |
ymes | +0.035 |
able | +0.031 |
ites | +0.030 |
Neg logit contributions | |
Daddy | -0.028 |
oph | -0.027 |
Jack | -0.027 |
written | -0.026 |
um | -0.026 |
Token | � |
Token ID | 129 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
Daddy | +0.037 |
mummy | +0.035 |
Peter | +0.034 |
Jack | +0.034 |
Jenna | +0.033 |
Neg logit contributions | |
aking | -0.036 |
ang | -0.034 |
ymes | -0.033 |
able | -0.031 |
iffs | -0.029 |
Token | � |
Token ID | 241 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
Daddy | +0.007 |
int | +0.006 |
mummy | +0.006 |
Peter | +0.006 |
Jack | +0.006 |
Neg logit contributions | |
aking | -0.008 |
ang | -0.007 |
ymes | -0.007 |
able | -0.007 |
iffs | -0.007 |
Token | I |
Token ID | 40 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
aking | +0.123 |
ang | +0.113 |
ymes | +0.108 |
able | +0.097 |
iffs | +0.095 |
Neg logit contributions | |
Daddy | -0.148 |
mummy | -0.142 |
Peter | -0.139 |
Jack | -0.135 |
der | -0.135 |
Token | want |
Token ID | 765 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Daddy | +0.007 |
mummy | +0.006 |
Peter | +0.006 |
Jack | +0.006 |
int | +0.006 |
Neg logit contributions | |
aking | -0.006 |
ang | -0.005 |
ymes | -0.005 |
able | -0.005 |
iffs | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
aking | +0.050 |
ymes | +0.047 |
ang | +0.045 |
able | +0.044 |
iffs | +0.042 |
Neg logit contributions | |
int | -0.037 |
Daddy | -0.037 |
der | -0.036 |
mummy | -0.036 |
Peter | -0.036 |
Token | dessert |
Token ID | 23084 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
aking | +0.081 |
ang | +0.075 |
ymes | +0.074 |
able | +0.070 |
iffs | +0.068 |
Neg logit contributions | |
Daddy | -0.041 |
Peter | -0.039 |
mummy | -0.039 |
der | -0.038 |
int | -0.037 |
Token | ! |
Token ID | 0 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
Daddy | +0.067 |
mummy | +0.063 |
Peter | +0.062 |
int | +0.060 |
der | +0.059 |
Neg logit contributions | |
aking | -0.123 |
ang | -0.115 |
ymes | -0.112 |
able | -0.105 |
iffs | -0.103 |
Token | full |
Token ID | 1336 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
aking | +0.029 |
ang | +0.027 |
ymes | +0.026 |
able | +0.024 |
iffs | +0.023 |
Neg logit contributions | |
Daddy | -0.023 |
mummy | -0.022 |
Peter | -0.022 |
Jack | -0.021 |
der | -0.021 |
Token | stomach |
Token ID | 11384 |
Feature activation | -8.00e-03 |
Pos logit contributions | |
aking | +0.007 |
ang | +0.006 |
ymes | +0.006 |
able | +0.006 |
trap | +0.006 |
Neg logit contributions | |
Daddy | -0.003 |
Peter | -0.003 |
der | -0.003 |
int | -0.003 |
Jenna | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
Daddy | +0.009 |
mummy | +0.009 |
Peter | +0.009 |
int | +0.008 |
oph | +0.008 |
Neg logit contributions | |
aking | -0.019 |
ang | -0.018 |
ymes | -0.017 |
able | -0.017 |
itty | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | +9.76e-03 |
Pos logit contributions | |
oph | +0.010 |
moons | +0.009 |
Jenna | +0.009 |
int | +0.009 |
mummy | +0.009 |
Neg logit contributions | |
aking | -0.011 |
Follow | -0.010 |
iffs | -0.010 |
aring | -0.009 |
ang | -0.009 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
aking | +0.021 |
ang | +0.019 |
ymes | +0.018 |
able | +0.018 |
cautious | +0.017 |
Neg logit contributions | |
Daddy | -0.013 |
Peter | -0.012 |
mummy | -0.012 |
int | -0.012 |
Jenna | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
oph | +0.056 |
Andrew | +0.053 |
Jenna | +0.053 |
Daddy | +0.053 |
Peter | +0.052 |
Neg logit contributions | |
aking | -0.078 |
ang | -0.069 |
able | -0.064 |
ymes | -0.064 |
cautious | -0.064 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
aking | +0.029 |
ang | +0.027 |
cautious | +0.024 |
able | +0.024 |
respectful | +0.024 |
Neg logit contributions | |
int | -0.020 |
der | -0.019 |
omm | -0.019 |
um | -0.019 |
Daddy | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
der | +0.026 |
oph | +0.024 |
moons | +0.023 |
tern | +0.023 |
imet | +0.023 |
Neg logit contributions | |
aking | -0.019 |
har | -0.018 |
obey | -0.018 |
respectful | -0.017 |
ang | -0.017 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
aking | +0.071 |
ang | +0.069 |
ymes | +0.066 |
respectful | +0.063 |
able | +0.063 |
Neg logit contributions | |
oph | -0.024 |
Peter | -0.024 |
Jenna | -0.023 |
der | -0.023 |
Jack | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
Daddy | +0.017 |
oph | +0.017 |
der | +0.016 |
mummy | +0.016 |
Peter | +0.016 |
Neg logit contributions | |
aking | -0.026 |
ang | -0.024 |
able | -0.022 |
ymes | -0.022 |
aring | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
oph | +0.003 |
moons | +0.003 |
written | +0.003 |
lit | +0.003 |
int | +0.003 |
Neg logit contributions | |
aking | -0.004 |
ang | -0.004 |
iffs | -0.004 |
Follow | -0.004 |
aring | -0.003 |
Token | nothing |
Token ID | 2147 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
oph | +0.030 |
Daddy | +0.027 |
um | +0.027 |
der | +0.027 |
mummy | +0.026 |
Neg logit contributions | |
aking | -0.062 |
ang | -0.059 |
ymes | -0.054 |
able | -0.054 |
cautious | -0.053 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
aking | +0.009 |
ang | +0.009 |
ymes | +0.009 |
iffs | +0.008 |
able | +0.008 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
Jack | -0.004 |
der | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-03 |
Pos logit contributions | |
aking | +0.039 |
ymes | +0.036 |
ang | +0.036 |
able | +0.034 |
trap | +0.033 |
Neg logit contributions | |
Daddy | -0.012 |
mummy | -0.011 |
der | -0.011 |
oph | -0.010 |
int | -0.010 |
Token | The |
Token ID | 383 |
Feature activation | -2.34e-03 |
Pos logit contributions | |
aking | +0.012 |
ang | +0.011 |
iffs | +0.010 |
ymes | +0.010 |
itty | +0.010 |
Neg logit contributions | |
oph | -0.007 |
der | -0.007 |
written | -0.007 |
lit | -0.007 |
mummy | -0.007 |
Token | little |
Token ID | 1310 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
Daddy | +0.004 |
mummy | +0.003 |
Peter | +0.003 |
Jack | +0.003 |
der | +0.003 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.005 |
ymes | -0.004 |
able | -0.004 |
iffs | -0.004 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.012 |
Peter | +0.011 |
Jack | +0.011 |
der | +0.011 |
Neg logit contributions | |
aking | -0.012 |
ang | -0.011 |
ymes | -0.011 |
iffs | -0.010 |
able | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
aking | +0.043 |
ang | +0.040 |
ymes | +0.039 |
able | +0.037 |
itty | +0.035 |
Neg logit contributions | |
Daddy | -0.021 |
mummy | -0.020 |
Peter | -0.019 |
der | -0.018 |
Jack | -0.018 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.003 |
ymes | +0.003 |
iffs | +0.003 |
able | +0.003 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.002 |
Peter | -0.002 |
Jack | -0.002 |
int | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
aking | +0.030 |
ang | +0.028 |
able | +0.026 |
ymes | +0.026 |
aring | +0.025 |
Neg logit contributions | |
oph | -0.017 |
Daddy | -0.016 |
mummy | -0.016 |
Andrew | -0.016 |
Jenna | -0.015 |
Token | deaf |
Token ID | 21815 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
aking | +0.078 |
ang | +0.073 |
ymes | +0.070 |
able | +0.068 |
trap | +0.065 |
Neg logit contributions | |
Daddy | -0.037 |
mummy | -0.035 |
oph | -0.035 |
der | -0.034 |
Peter | -0.034 |
Token | forever |
Token ID | 8097 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
Daddy | +0.002 |
mummy | +0.002 |
oph | +0.002 |
int | +0.002 |
um | +0.002 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.005 |
ymes | -0.005 |
able | -0.004 |
trap | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
aking | +0.007 |
ang | +0.007 |
ymes | +0.006 |
able | +0.006 |
trap | +0.006 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
oph | -0.003 |
der | -0.003 |
Token | His |
Token ID | 2399 |
Feature activation | -7.77e-03 |
Pos logit contributions | |
moons | +0.011 |
der | +0.009 |
oph | +0.009 |
mummy | +0.009 |
written | +0.009 |
Neg logit contributions | |
aking | -0.018 |
ang | -0.016 |
iffs | -0.016 |
aring | -0.016 |
Follow | -0.015 |
Token | dad |
Token ID | 9955 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
der | +0.008 |
Peter | +0.008 |
oph | +0.008 |
Jenna | +0.007 |
moons | +0.007 |
Neg logit contributions | |
aking | -0.018 |
ang | -0.017 |
ymes | -0.016 |
respectful | -0.016 |
able | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
Daddy | +0.024 |
der | +0.022 |
mummy | +0.022 |
int | +0.021 |
Peter | +0.021 |
Neg logit contributions | |
aking | -0.049 |
ang | -0.046 |
ymes | -0.044 |
able | -0.043 |
render | -0.041 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.58e-03 |
Pos logit contributions | |
Daddy | +0.006 |
mummy | +0.006 |
Peter | +0.006 |
Jack | +0.006 |
int | +0.006 |
Neg logit contributions | |
aking | -0.009 |
ang | -0.008 |
ymes | -0.008 |
able | -0.008 |
iffs | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.012 |
oph | +0.012 |
um | +0.012 |
int | +0.011 |
Neg logit contributions | |
aking | -0.020 |
ang | -0.018 |
ymes | -0.018 |
able | -0.017 |
aring | -0.016 |
Token | explain |
Token ID | 4727 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
aking | +0.038 |
ang | +0.033 |
able | +0.030 |
imp | +0.029 |
ymes | +0.029 |
Neg logit contributions | |
der | -0.053 |
Daddy | -0.052 |
oph | -0.051 |
int | -0.050 |
mummy | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
Daddy | +0.034 |
mummy | +0.033 |
oph | +0.032 |
Peter | +0.031 |
der | +0.030 |
Neg logit contributions | |
aking | -0.060 |
ang | -0.057 |
ymes | -0.056 |
able | -0.052 |
aring | -0.050 |
Token | " |
Token ID | 366 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
Daddy | +0.010 |
mummy | +0.009 |
Peter | +0.009 |
oph | +0.009 |
um | +0.009 |
Neg logit contributions | |
aking | -0.018 |
ang | -0.017 |
ymes | -0.016 |
able | -0.015 |
iffs | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
aking | +0.049 |
ang | +0.045 |
ymes | +0.043 |
able | +0.038 |
iffs | +0.038 |
Neg logit contributions | |
Daddy | -0.065 |
mummy | -0.063 |
Peter | -0.062 |
Jack | -0.060 |
int | -0.060 |
Token | helicopter |
Token ID | 15392 |
Feature activation | -8.38e-05 |
Pos logit contributions | |
Daddy | +0.029 |
mummy | +0.028 |
Peter | +0.027 |
Jack | +0.026 |
der | +0.026 |
Neg logit contributions | |
aking | -0.035 |
ang | -0.033 |
ymes | -0.032 |
able | -0.029 |
iffs | -0.029 |
Token | we |
Token ID | 356 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
aking | +0.071 |
ang | +0.066 |
ymes | +0.064 |
able | +0.059 |
iffs | +0.058 |
Neg logit contributions | |
Daddy | -0.056 |
mummy | -0.054 |
Peter | -0.052 |
Jack | -0.050 |
der | -0.050 |
Token | walk |
Token ID | 2513 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
Daddy | +0.070 |
mummy | +0.067 |
Peter | +0.065 |
Jack | +0.063 |
der | +0.062 |
Neg logit contributions | |
aking | -0.078 |
ang | -0.073 |
ymes | -0.071 |
able | -0.065 |
iffs | -0.063 |
Token | ," |
Token ID | 553 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
aking | +0.106 |
ang | +0.100 |
ymes | +0.097 |
able | +0.089 |
iffs | +0.089 |
Neg logit contributions | |
Daddy | -0.061 |
mummy | -0.057 |
Peter | -0.056 |
Jack | -0.054 |
der | -0.052 |
Token | he |
Token ID | 339 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
Daddy | +0.028 |
der | +0.027 |
mummy | +0.026 |
oph | +0.026 |
int | +0.026 |
Neg logit contributions | |
aking | -0.085 |
ang | -0.083 |
ymes | -0.079 |
able | -0.076 |
iffs | -0.074 |
Token | said |
Token ID | 531 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
aking | +0.024 |
ang | +0.023 |
ymes | +0.022 |
able | +0.021 |
trap | +0.021 |
Neg logit contributions | |
Daddy | -0.010 |
mummy | -0.009 |
Peter | -0.009 |
der | -0.009 |
horizon | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
aking | +0.049 |
ang | +0.046 |
ymes | +0.045 |
able | +0.042 |
iffs | +0.041 |
Neg logit contributions | |
Daddy | -0.019 |
mummy | -0.018 |
oph | -0.018 |
Peter | -0.017 |
der | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
aking | +0.031 |
ang | +0.030 |
ymes | +0.028 |
iffs | +0.027 |
itty | +0.026 |
Neg logit contributions | |
Daddy | -0.015 |
mummy | -0.015 |
int | -0.015 |
der | -0.015 |
oph | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
Daddy | +0.002 |
mummy | +0.002 |
Peter | +0.002 |
Jack | +0.002 |
int | +0.002 |
Neg logit contributions | |
aking | -0.006 |
ang | -0.005 |
ymes | -0.005 |
able | -0.005 |
iffs | -0.005 |
Token | So |
Token ID | 2396 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
Daddy | +0.006 |
mummy | +0.006 |
Peter | +0.006 |
um | +0.006 |
Jack | +0.006 |
Neg logit contributions | |
aking | -0.009 |
ang | -0.009 |
ymes | -0.009 |
asc | -0.009 |
iffs | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.004 |
ymes | +0.003 |
able | +0.003 |
iffs | +0.003 |
Neg logit contributions | |
der | -0.002 |
int | -0.002 |
Daddy | -0.002 |
oph | -0.002 |
written | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
Daddy | +0.006 |
mummy | +0.006 |
der | +0.005 |
int | +0.005 |
Peter | +0.005 |
Neg logit contributions | |
aking | -0.012 |
ang | -0.012 |
ymes | -0.011 |
able | -0.010 |
iffs | -0.010 |
Token | tired |
Token ID | 10032 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
aking | +0.044 |
ymes | +0.039 |
ang | +0.039 |
able | +0.037 |
iffs | +0.035 |
Neg logit contributions | |
Daddy | -0.035 |
mummy | -0.034 |
Peter | -0.033 |
der | -0.033 |
oph | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
aking | +0.063 |
able | +0.056 |
ymes | +0.055 |
ang | +0.055 |
trap | +0.051 |
Neg logit contributions | |
mummy | -0.035 |
oph | -0.034 |
Daddy | -0.034 |
Andrew | -0.033 |
int | -0.033 |
Token | The |
Token ID | 383 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
aking | +0.024 |
ang | +0.022 |
ymes | +0.021 |
iffs | +0.020 |
able | +0.020 |
Neg logit contributions | |
Daddy | -0.011 |
mummy | -0.010 |
der | -0.010 |
int | -0.010 |
oph | -0.010 |
Token | end |
Token ID | 886 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.003 |
ymes | +0.003 |
iffs | +0.003 |
able | +0.003 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
Peter | -0.001 |
Jack | -0.001 |
der | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
aking | +0.080 |
ang | +0.076 |
ymes | +0.075 |
able | +0.070 |
iffs | +0.070 |
Neg logit contributions | |
Daddy | -0.021 |
mummy | -0.020 |
Peter | -0.018 |
Jack | -0.017 |
der | -0.016 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
aking | +0.043 |
ang | +0.041 |
ymes | +0.039 |
iffs | +0.037 |
able | +0.037 |
Neg logit contributions | |
Daddy | -0.019 |
mummy | -0.018 |
der | -0.017 |
Peter | -0.017 |
int | -0.017 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
aking | +0.137 |
ang | +0.128 |
ymes | +0.125 |
iffs | +0.117 |
able | +0.117 |
Neg logit contributions | |
Daddy | -0.068 |
mummy | -0.065 |
der | -0.062 |
int | -0.062 |
Peter | -0.061 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
aking | +0.004 |
ang | +0.003 |
ymes | +0.003 |
able | +0.003 |
iffs | +0.003 |
Neg logit contributions | |
der | -0.004 |
Daddy | -0.004 |
written | -0.004 |
oph | -0.004 |
int | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
aking | +0.039 |
ang | +0.036 |
ymes | +0.036 |
able | +0.033 |
iffs | +0.033 |
Neg logit contributions | |
Daddy | -0.018 |
mummy | -0.017 |
Peter | -0.016 |
der | -0.015 |
int | -0.015 |
Token | time |
Token ID | 640 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
aking | +0.011 |
ang | +0.010 |
ymes | +0.010 |
beh | +0.009 |
iffs | +0.009 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
Jack | -0.003 |
oph | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
aking | +0.026 |
ang | +0.025 |
ymes | +0.024 |
able | +0.023 |
iffs | +0.023 |
Neg logit contributions | |
Daddy | -0.009 |
mummy | -0.008 |
der | -0.008 |
Peter | -0.007 |
int | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
aking | +0.032 |
ang | +0.031 |
ymes | +0.029 |
iffs | +0.028 |
able | +0.027 |
Neg logit contributions | |
Daddy | -0.017 |
der | -0.017 |
mummy | -0.017 |
Peter | -0.016 |
int | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
aking | +0.024 |
ymes | +0.023 |
ang | +0.022 |
beh | +0.021 |
trap | +0.021 |
Neg logit contributions | |
Daddy | -0.020 |
mummy | -0.018 |
Jack | -0.018 |
Andrew | -0.017 |
um | -0.017 |
Token | Yes |
Token ID | 5297 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
aking | +0.117 |
ang | +0.100 |
ymes | +0.096 |
iffs | +0.085 |
able | +0.084 |
Neg logit contributions | |
Daddy | -0.152 |
mummy | -0.144 |
der | -0.139 |
Jack | -0.136 |
Peter | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
written | +0.008 |
int | +0.008 |
Peter | +0.008 |
moons | +0.008 |
der | +0.008 |
Neg logit contributions | |
aking | -0.017 |
ang | -0.016 |
ymes | -0.015 |
able | -0.015 |
aring | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
aking | +0.031 |
ang | +0.030 |
ymes | +0.028 |
able | +0.026 |
trap | +0.026 |
Neg logit contributions | |
Daddy | -0.021 |
Peter | -0.021 |
mummy | -0.020 |
int | -0.020 |
der | -0.020 |
Token | ," |
Token ID | 553 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
Daddy | +0.031 |
mummy | +0.030 |
int | +0.030 |
der | +0.029 |
Peter | +0.029 |
Neg logit contributions | |
aking | -0.055 |
ang | -0.050 |
ymes | -0.048 |
able | -0.047 |
itty | -0.045 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
der | +0.026 |
Peter | +0.025 |
int | +0.025 |
Daddy | +0.025 |
mummy | +0.024 |
Neg logit contributions | |
aking | -0.042 |
ang | -0.041 |
ymes | -0.039 |
able | -0.037 |
iffs | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
aking | +0.003 |
ang | +0.003 |
able | +0.002 |
ymes | +0.002 |
ighed | +0.002 |
Neg logit contributions | |
mummy | -0.002 |
Daddy | -0.002 |
moons | -0.002 |
horizon | -0.002 |
Peter | -0.002 |
Token | Mia |
Token ID | 32189 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
aking | +0.037 |
ang | +0.035 |
ymes | +0.033 |
able | +0.031 |
iffs | +0.030 |
Neg logit contributions | |
Daddy | -0.034 |
mummy | -0.032 |
Peter | -0.031 |
der | -0.030 |
Jack | -0.030 |
Token | said |
Token ID | 531 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.007 |
able | +0.007 |
ighed | +0.007 |
ymes | +0.006 |
Neg logit contributions | |
Peter | -0.005 |
omm | -0.005 |
Daddy | -0.005 |
mummy | -0.005 |
der | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
aking | +0.072 |
ang | +0.067 |
ymes | +0.065 |
able | +0.062 |
iffs | +0.061 |
Neg logit contributions | |
Daddy | -0.031 |
oph | -0.031 |
mummy | -0.030 |
Peter | -0.030 |
Jenna | -0.028 |
Token | wore |
Token ID | 12408 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
aking | +0.017 |
ang | +0.016 |
ymes | +0.015 |
able | +0.014 |
ighed | +0.014 |
Neg logit contributions | |
Daddy | -0.012 |
Peter | -0.011 |
mummy | -0.011 |
int | -0.011 |
der | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
der | +0.010 |
omm | +0.009 |
Daddy | +0.009 |
Father | +0.009 |
oph | +0.009 |
Neg logit contributions | |
aking | -0.014 |
ymes | -0.014 |
ang | -0.013 |
able | -0.013 |
iffs | -0.012 |
Token | shirt |
Token ID | 10147 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.006 |
ymes | +0.005 |
able | +0.005 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
Jack | -0.004 |
int | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
Daddy | +0.043 |
Peter | +0.041 |
Father | +0.041 |
Andrew | +0.041 |
der | +0.040 |
Neg logit contributions | |
aking | -0.067 |
ang | -0.061 |
ymes | -0.058 |
able | -0.056 |
iffs | -0.055 |
Token | day |
Token ID | 1110 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
aking | +0.057 |
ang | +0.054 |
ymes | +0.052 |
able | +0.049 |
iffs | +0.048 |
Neg logit contributions | |
Daddy | -0.032 |
mummy | -0.030 |
Peter | -0.029 |
der | -0.028 |
Jack | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
aking | +0.027 |
ang | +0.026 |
ymes | +0.023 |
able | +0.023 |
aring | +0.021 |
Neg logit contributions | |
Daddy | -0.019 |
mummy | -0.019 |
der | -0.019 |
omm | -0.019 |
Peter | -0.018 |
Token | showed |
Token ID | 3751 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
omm | +0.020 |
um | +0.020 |
int | +0.019 |
der | +0.019 |
Daddy | +0.019 |
Neg logit contributions | |
aking | -0.029 |
ang | -0.027 |
ymes | -0.027 |
able | -0.026 |
respectful | -0.024 |
Token | everyone |
Token ID | 2506 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
horizon | +0.030 |
der | +0.029 |
Andrew | +0.028 |
oph | +0.028 |
Father | +0.027 |
Neg logit contributions | |
ymes | -0.039 |
ang | -0.037 |
aking | -0.037 |
able | -0.034 |
iffs | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | -9.85e-04 |
Pos logit contributions | |
aking | +0.040 |
ang | +0.038 |
ymes | +0.037 |
able | +0.035 |
iffs | +0.035 |
Neg logit contributions | |
Daddy | -0.016 |
mummy | -0.015 |
Peter | -0.014 |
Jack | -0.013 |
int | -0.013 |
Token | button |
Token ID | 4936 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
Daddy | +0.001 |
mummy | +0.001 |
Peter | +0.001 |
der | +0.001 |
Jack | +0.001 |
Neg logit contributions | |
aking | -0.002 |
ang | -0.002 |
ymes | -0.002 |
able | -0.002 |
iffs | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +5.29e-04 |
Pos logit contributions | |
Daddy | +0.033 |
mummy | +0.031 |
Peter | +0.031 |
oph | +0.030 |
Andrew | +0.029 |
Neg logit contributions | |
aking | -0.067 |
ang | -0.064 |
ymes | -0.062 |
able | -0.059 |
trap | -0.056 |
Token | 's |
Token ID | 338 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
aking | +0.031 |
ymes | +0.030 |
ang | +0.028 |
able | +0.027 |
trap | +0.025 |
Neg logit contributions | |
Daddy | -0.033 |
Jenna | -0.031 |
Jack | -0.031 |
Peter | -0.031 |
mummy | -0.030 |
Token | not |
Token ID | 407 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
Daddy | +0.006 |
mummy | +0.006 |
Peter | +0.006 |
Jack | +0.006 |
written | +0.005 |
Neg logit contributions | |
aking | -0.009 |
ang | -0.009 |
ymes | -0.008 |
able | -0.008 |
iffs | -0.008 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
aking | +0.034 |
ang | +0.033 |
ymes | +0.030 |
iffs | +0.029 |
itty | +0.028 |
Neg logit contributions | |
Daddy | -0.034 |
Peter | -0.032 |
Jack | -0.032 |
mummy | -0.032 |
written | -0.031 |
Token | ! |
Token ID | 0 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Daddy | +0.012 |
mummy | +0.012 |
Peter | +0.011 |
int | +0.011 |
oph | +0.011 |
Neg logit contributions | |
aking | -0.024 |
ang | -0.023 |
ymes | -0.022 |
able | -0.021 |
iffs | -0.020 |
Token | We |
Token ID | 775 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
aking | +0.039 |
ang | +0.037 |
ymes | +0.036 |
able | +0.033 |
iffs | +0.032 |
Neg logit contributions | |
Daddy | -0.030 |
mummy | -0.028 |
Peter | -0.028 |
Jack | -0.027 |
der | -0.027 |
Token | waited |
Token ID | 13488 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
Daddy | +0.041 |
mummy | +0.039 |
Peter | +0.038 |
Jack | +0.038 |
written | +0.037 |
Neg logit contributions | |
aking | -0.044 |
ang | -0.042 |
ymes | -0.040 |
iffs | -0.036 |
able | -0.035 |
Token | so |
Token ID | 523 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
oph | +0.029 |
Daddy | +0.027 |
mummy | +0.027 |
der | +0.027 |
Peter | +0.026 |
Neg logit contributions | |
aking | -0.040 |
ang | -0.037 |
ymes | -0.036 |
iffs | -0.032 |
able | -0.032 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
aking | +0.062 |
ang | +0.057 |
ymes | +0.055 |
able | +0.049 |
iffs | +0.048 |
Neg logit contributions | |
Daddy | -0.071 |
mummy | -0.068 |
Peter | -0.067 |
Jack | -0.065 |
der | -0.065 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
mummy | +0.026 |
Daddy | +0.026 |
oph | +0.024 |
Father | +0.023 |
omm | +0.023 |
Neg logit contributions | |
aking | -0.033 |
ang | -0.032 |
ymes | -0.028 |
able | -0.027 |
iffs | -0.026 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
der | +0.020 |
oph | +0.018 |
int | +0.018 |
omm | +0.017 |
ongs | +0.017 |
Neg logit contributions | |
ang | -0.024 |
aking | -0.023 |
iffs | -0.021 |
able | -0.021 |
Spot | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
aking | +0.035 |
ang | +0.033 |
ymes | +0.030 |
able | +0.030 |
ighed | +0.029 |
Neg logit contributions | |
mummy | -0.022 |
Daddy | -0.021 |
sunset | -0.020 |
moons | -0.020 |
int | -0.020 |
Token | year |
Token ID | 614 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
aking | +0.054 |
ang | +0.052 |
ymes | +0.051 |
iffs | +0.048 |
able | +0.047 |
Neg logit contributions | |
Daddy | -0.029 |
mummy | -0.028 |
Peter | -0.027 |
Jack | -0.025 |
int | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
aking | +0.137 |
ang | +0.130 |
ymes | +0.122 |
able | +0.120 |
aring | +0.116 |
Neg logit contributions | |
mummy | -0.066 |
Daddy | -0.065 |
oph | -0.061 |
Peter | -0.060 |
der | -0.056 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
der | +0.002 |
mummy | +0.002 |
Daddy | +0.002 |
int | +0.002 |
written | +0.002 |
Neg logit contributions | |
aking | -0.004 |
ang | -0.004 |
iffs | -0.003 |
itty | -0.003 |
Follow | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.38e-04 |
Pos logit contributions | |
aking | +0.131 |
ang | +0.123 |
ymes | +0.119 |
able | +0.111 |
iffs | +0.109 |
Neg logit contributions | |
Daddy | -0.077 |
mummy | -0.073 |
Peter | -0.071 |
Jack | -0.068 |
der | -0.067 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
aking | +0.000 |
ang | +0.000 |
ymes | +0.000 |
able | +0.000 |
iffs | +0.000 |
Neg logit contributions | |
der | -0.000 |
Daddy | -0.000 |
mummy | -0.000 |
written | -0.000 |
oph | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +8.55e-04 |
Pos logit contributions | |
aking | +0.036 |
ang | +0.034 |
ymes | +0.034 |
able | +0.031 |
iffs | +0.031 |
Neg logit contributions | |
Daddy | -0.016 |
mummy | -0.015 |
Peter | -0.015 |
Jack | -0.014 |
der | -0.014 |
Token | time |
Token ID | 640 |
Feature activation | +8.27e-03 |
Pos logit contributions | |
aking | +0.002 |
ang | +0.002 |
ymes | +0.002 |
beh | +0.002 |
iffs | +0.002 |
Neg logit contributions | |
Daddy | -0.001 |
mummy | -0.001 |
Jack | -0.001 |
Peter | -0.001 |
oph | -0.001 |
Token | there |
Token ID | 612 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
aking | +0.022 |
ang | +0.021 |
ymes | +0.021 |
able | +0.020 |
iffs | +0.019 |
Neg logit contributions | |
Daddy | -0.007 |
mummy | -0.006 |
der | -0.006 |
Peter | -0.006 |
int | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
aking | +0.046 |
ang | +0.044 |
ymes | +0.042 |
able | +0.040 |
itty | +0.039 |
Neg logit contributions | |
Daddy | -0.026 |
der | -0.026 |
int | -0.025 |
mummy | -0.025 |
Peter | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
der | +0.036 |
Daddy | +0.036 |
mummy | +0.034 |
int | +0.034 |
oph | +0.033 |
Neg logit contributions | |
aking | -0.060 |
ang | -0.055 |
ymes | -0.053 |
able | -0.051 |
Spot | -0.048 |
Token | brown |
Token ID | 7586 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
aking | +0.070 |
ymes | +0.066 |
beh | +0.065 |
iffs | +0.064 |
ang | +0.063 |
Neg logit contributions | |
Daddy | -0.033 |
mummy | -0.033 |
daddy | -0.027 |
Jack | -0.027 |
Peter | -0.027 |
Token | still |
Token ID | 991 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
Daddy | +0.003 |
mummy | +0.003 |
Peter | +0.003 |
Jack | +0.003 |
der | +0.003 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.005 |
ymes | -0.005 |
iffs | -0.004 |
able | -0.004 |
Token | helpless |
Token ID | 21144 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
aking | +0.019 |
ang | +0.019 |
ymes | +0.018 |
iffs | +0.017 |
ites | +0.016 |
Neg logit contributions | |
Daddy | -0.016 |
mummy | -0.016 |
Peter | -0.015 |
Jack | -0.015 |
written | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
aking | +0.038 |
ang | +0.035 |
ymes | +0.034 |
able | +0.033 |
iffs | +0.031 |
Neg logit contributions | |
Daddy | -0.018 |
mummy | -0.017 |
oph | -0.016 |
Peter | -0.016 |
Jenna | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
Daddy | +0.004 |
mummy | +0.004 |
written | +0.004 |
int | +0.004 |
oph | +0.004 |
Neg logit contributions | |
aking | -0.008 |
ang | -0.008 |
ymes | -0.007 |
iffs | -0.007 |
aring | -0.007 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
aking | +0.023 |
ang | +0.022 |
ymes | +0.021 |
able | +0.020 |
trap | +0.019 |
Neg logit contributions | |
Daddy | -0.013 |
mummy | -0.012 |
Peter | -0.012 |
int | -0.011 |
oph | -0.011 |
Token | 't |
Token ID | 470 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
Daddy | +0.025 |
mummy | +0.024 |
der | +0.023 |
oph | +0.023 |
int | +0.022 |
Neg logit contributions | |
aking | -0.038 |
ang | -0.036 |
ymes | -0.034 |
iffs | -0.033 |
itty | -0.032 |
Token | fly |
Token ID | 6129 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
aking | +0.002 |
ang | +0.002 |
ymes | +0.002 |
able | +0.002 |
trap | +0.002 |
Neg logit contributions | |
Daddy | -0.002 |
mummy | -0.002 |
Peter | -0.002 |
int | -0.002 |
oph | -0.002 |
Token | until |
Token ID | 1566 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
aking | +0.115 |
ang | +0.109 |
ymes | +0.106 |
iffs | +0.098 |
able | +0.098 |
Neg logit contributions | |
Daddy | -0.050 |
mummy | -0.046 |
Peter | -0.046 |
Jack | -0.044 |
der | -0.043 |
Token | his |
Token ID | 465 |
Feature activation | -2.63e-03 |
Pos logit contributions | |
oph | +0.017 |
int | +0.016 |
Daddy | +0.016 |
der | +0.015 |
omm | +0.015 |
Neg logit contributions | |
aking | -0.040 |
ang | -0.037 |
able | -0.037 |
ymes | -0.035 |
trap | -0.035 |
Token | wing |
Token ID | 8539 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
Daddy | +0.004 |
Peter | +0.004 |
mummy | +0.004 |
Jack | +0.004 |
oph | +0.004 |
Neg logit contributions | |
aking | -0.005 |
ang | -0.005 |
ymes | -0.005 |
able | -0.004 |
trap | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
Daddy | +0.020 |
mummy | +0.019 |
Peter | +0.018 |
int | +0.018 |
Andrew | +0.017 |
Neg logit contributions | |
aking | -0.038 |
ang | -0.034 |
ymes | -0.034 |
able | -0.032 |
trap | -0.031 |
Token | carefully |
Token ID | 7773 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
aking | +0.003 |
ang | +0.003 |
ymes | +0.003 |
able | +0.003 |
ites | +0.003 |
Neg logit contributions | |
der | -0.003 |
Peter | -0.003 |
Daddy | -0.003 |
horizon | -0.002 |
omm | -0.002 |
Token | picked |
Token ID | 6497 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
mummy | +0.070 |
Daddy | +0.070 |
Peter | +0.069 |
der | +0.066 |
omm | +0.064 |
Neg logit contributions | |
aking | -0.099 |
ang | -0.089 |
ymes | -0.081 |
able | -0.081 |
arate | -0.076 |
Token | up |
Token ID | 510 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
der | +0.011 |
Daddy | +0.011 |
Father | +0.010 |
oph | +0.010 |
couldn | +0.010 |
Neg logit contributions | |
aking | -0.014 |
ymes | -0.014 |
ang | -0.013 |
able | -0.013 |
iffs | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
aking | +0.008 |
ang | +0.008 |
ymes | +0.008 |
able | +0.007 |
iffs | +0.007 |
Neg logit contributions | |
Daddy | -0.005 |
Peter | -0.004 |
mummy | -0.004 |
der | -0.004 |
int | -0.004 |
Token | pink |
Token ID | 11398 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
Daddy | +0.008 |
Peter | +0.008 |
der | +0.008 |
mummy | +0.007 |
Father | +0.007 |
Neg logit contributions | |
aking | -0.011 |
ymes | -0.010 |
ang | -0.010 |
able | -0.009 |
trap | -0.009 |
Token | cr |
Token ID | 1067 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
Peter | +0.091 |
Andrew | +0.089 |
Jason | +0.089 |
Father | +0.087 |
Daddy | +0.087 |
Neg logit contributions | |
aking | -0.115 |
ang | -0.106 |
ymes | -0.104 |
able | -0.098 |
iffs | -0.098 |
Token | ay |
Token ID | 323 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
father | +0.118 |
Daddy | +0.118 |
Father | +0.116 |
Peter | +0.115 |
mummy | +0.114 |
Neg logit contributions | |
aking | -0.099 |
ang | -0.083 |
iffs | -0.078 |
ymes | -0.074 |
itty | -0.072 |
Token | on |
Token ID | 261 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Daddy | +0.018 |
der | +0.017 |
mummy | +0.017 |
Peter | +0.016 |
Father | +0.016 |
Neg logit contributions | |
aking | -0.043 |
ang | -0.041 |
ymes | -0.040 |
able | -0.038 |
iffs | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
Daddy | +0.055 |
Father | +0.054 |
mummy | +0.052 |
Peter | +0.052 |
Andrew | +0.051 |
Neg logit contributions | |
aking | -0.077 |
ang | -0.070 |
ymes | -0.064 |
able | -0.064 |
iffs | -0.062 |
Token | drew |
Token ID | 9859 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
omm | +0.042 |
um | +0.039 |
horizon | +0.039 |
der | +0.038 |
int | +0.037 |
Neg logit contributions | |
aking | -0.043 |
ang | -0.041 |
ymes | -0.037 |
etchup | -0.036 |
ites | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
Daddy | +0.071 |
Father | +0.070 |
oph | +0.068 |
Peter | +0.068 |
der | +0.067 |
Neg logit contributions | |
ymes | -0.095 |
aking | -0.094 |
ang | -0.087 |
able | -0.081 |
aks | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
Daddy | +0.085 |
Father | +0.083 |
oph | +0.081 |
Peter | +0.081 |
mummy | +0.079 |
Neg logit contributions | |
aking | -0.086 |
ang | -0.077 |
ymes | -0.074 |
able | -0.069 |
iffs | -0.066 |
Token | One |
Token ID | 1881 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
der | +0.043 |
Andrew | +0.042 |
Peter | +0.042 |
Daddy | +0.041 |
int | +0.041 |
Neg logit contributions | |
aking | -0.076 |
iffs | -0.068 |
ang | -0.067 |
ymes | -0.066 |
itty | -0.063 |
Token | day |
Token ID | 1110 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.005 |
ymes | +0.005 |
able | +0.005 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.003 |
mummy | -0.003 |
Peter | -0.003 |
der | -0.003 |
int | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
aking | +0.032 |
ang | +0.031 |
iffs | +0.029 |
ymes | +0.029 |
able | +0.029 |
Neg logit contributions | |
int | -0.016 |
der | -0.015 |
Peter | -0.015 |
Daddy | -0.015 |
horizon | -0.015 |
Token | she |
Token ID | 673 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
der | +0.040 |
int | +0.039 |
Peter | +0.038 |
Andrew | +0.038 |
oph | +0.037 |
Neg logit contributions | |
aking | -0.068 |
ang | -0.065 |
ymes | -0.064 |
able | -0.060 |
iffs | -0.060 |
Token | drew |
Token ID | 9859 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
der | +0.005 |
int | +0.005 |
Daddy | +0.005 |
Peter | +0.005 |
mummy | +0.005 |
Neg logit contributions | |
aking | -0.008 |
ymes | -0.007 |
able | -0.007 |
ang | -0.007 |
itty | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
Daddy | +0.079 |
Peter | +0.077 |
Father | +0.076 |
der | +0.075 |
horizon | +0.075 |
Neg logit contributions | |
aking | -0.090 |
ymes | -0.086 |
ang | -0.079 |
able | -0.072 |
aks | -0.070 |
Token | triangle |
Token ID | 22950 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
der | +0.008 |
Daddy | +0.008 |
Peter | +0.008 |
oph | +0.008 |
Jack | +0.008 |
Neg logit contributions | |
aking | -0.009 |
ang | -0.009 |
ymes | -0.008 |
able | -0.007 |
trap | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
Daddy | +0.064 |
Peter | +0.060 |
oph | +0.060 |
Father | +0.059 |
mummy | +0.059 |
Neg logit contributions | |
aking | -0.060 |
ang | -0.056 |
ymes | -0.051 |
able | -0.047 |
iffs | -0.046 |
Token | She |
Token ID | 1375 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
der | +0.043 |
Andrew | +0.041 |
int | +0.041 |
Father | +0.040 |
father | +0.040 |
Neg logit contributions | |
aking | -0.049 |
iffs | -0.047 |
ang | -0.044 |
itty | -0.042 |
ymes | -0.040 |
Token | showed |
Token ID | 3751 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
horizon | +0.015 |
Father | +0.014 |
Daddy | +0.014 |
Kevin | +0.014 |
int | +0.014 |
Neg logit contributions | |
aking | -0.014 |
ymes | -0.013 |
ang | -0.012 |
able | -0.012 |
ike | -0.011 |
Token | paints |
Token ID | 32281 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
aking | +0.029 |
ymes | +0.028 |
ang | +0.026 |
able | +0.025 |
ites | +0.023 |
Neg logit contributions | |
der | -0.027 |
oph | -0.026 |
Daddy | -0.026 |
Peter | -0.026 |
mummy | -0.026 |
Token | that |
Token ID | 326 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
Daddy | +0.076 |
oph | +0.075 |
mummy | +0.075 |
Peter | +0.074 |
Father | +0.074 |
Neg logit contributions | |
aking | -0.094 |
ang | -0.085 |
able | -0.082 |
ymes | -0.079 |
ites | -0.078 |
Token | he |
Token ID | 339 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
aking | +0.011 |
able | +0.010 |
ang | +0.010 |
ymes | +0.009 |
aks | +0.009 |
Neg logit contributions | |
oph | -0.007 |
der | -0.007 |
int | -0.006 |
um | -0.006 |
omm | -0.006 |
Token | used |
Token ID | 973 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
Daddy | +0.015 |
mummy | +0.014 |
Peter | +0.014 |
der | +0.014 |
int | +0.014 |
Neg logit contributions | |
aking | -0.028 |
ang | -0.026 |
ymes | -0.025 |
able | -0.024 |
trap | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
oph | +0.026 |
Daddy | +0.026 |
mummy | +0.025 |
Peter | +0.025 |
der | +0.024 |
Neg logit contributions | |
aking | -0.034 |
ang | -0.031 |
ymes | -0.030 |
able | -0.029 |
trap | -0.027 |
Token | paint |
Token ID | 7521 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
aking | +0.011 |
ang | +0.010 |
ymes | +0.010 |
able | +0.009 |
trap | +0.009 |
Neg logit contributions | |
Daddy | -0.008 |
Peter | -0.007 |
mummy | -0.007 |
der | -0.007 |
oph | -0.007 |
Token | pictures |
Token ID | 5986 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
oph | +0.074 |
Daddy | +0.069 |
mummy | +0.068 |
der | +0.068 |
Father | +0.067 |
Neg logit contributions | |
aking | -0.096 |
ymes | -0.089 |
ang | -0.086 |
able | -0.085 |
ites | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
oph | +0.091 |
Daddy | +0.085 |
Father | +0.085 |
mummy | +0.085 |
father | +0.081 |
Neg logit contributions | |
aking | -0.098 |
ang | -0.085 |
able | -0.080 |
ites | -0.079 |
ymes | -0.078 |
Token | He |
Token ID | 679 |
Feature activation | +6.40e-04 |
Pos logit contributions | |
oph | +0.012 |
der | +0.012 |
lit | +0.012 |
written | +0.012 |
int | +0.012 |
Neg logit contributions | |
aking | -0.021 |
ang | -0.021 |
itty | -0.018 |
iffs | -0.018 |
Spot | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
aking | +0.001 |
ang | +0.001 |
ymes | +0.001 |
able | +0.001 |
itty | +0.001 |
Neg logit contributions | |
Daddy | -0.001 |
Peter | -0.001 |
mummy | -0.001 |
der | -0.001 |
Andrew | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Daddy | +0.028 |
der | +0.027 |
oph | +0.026 |
Peter | +0.026 |
mummy | +0.026 |
Neg logit contributions | |
aking | -0.034 |
ang | -0.031 |
ymes | -0.029 |
able | -0.026 |
cautious | -0.026 |
Token | eros |
Token ID | 27498 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
aking | +0.038 |
able | +0.036 |
ang | +0.036 |
ymes | +0.035 |
Spot | +0.034 |
Neg logit contributions | |
um | -0.055 |
mummy | -0.052 |
Daddy | -0.052 |
int | -0.050 |
oph | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
aking | +0.077 |
ang | +0.073 |
ymes | +0.070 |
iffs | +0.068 |
able | +0.066 |
Neg logit contributions | |
Daddy | -0.039 |
mummy | -0.037 |
Peter | -0.036 |
Jack | -0.035 |
int | -0.034 |
Token | She |
Token ID | 1375 |
Feature activation | +3.15e-03 |
Pos logit contributions | |
oph | +0.013 |
mummy | +0.013 |
Andrew | +0.013 |
Daddy | +0.013 |
written | +0.013 |
Neg logit contributions | |
aking | -0.021 |
ang | -0.019 |
ymes | -0.018 |
itty | -0.018 |
iffs | -0.018 |
Token | tried |
Token ID | 3088 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.006 |
ymes | +0.006 |
able | +0.005 |
itty | +0.005 |
Neg logit contributions | |
Daddy | -0.005 |
Peter | -0.004 |
oph | -0.004 |
Father | -0.004 |
Jenna | -0.004 |
Token | different |
Token ID | 1180 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
Daddy | +0.003 |
oph | +0.003 |
mummy | +0.003 |
Peter | +0.003 |
Father | +0.003 |
Neg logit contributions | |
aking | -0.004 |
ymes | -0.003 |
ang | -0.003 |
iffs | -0.003 |
able | -0.003 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
Daddy | +0.042 |
mummy | +0.041 |
oph | +0.041 |
der | +0.040 |
Father | +0.040 |
Neg logit contributions | |
aking | -0.042 |
ymes | -0.040 |
ang | -0.037 |
able | -0.036 |
ites | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Daddy | +0.069 |
Father | +0.067 |
mummy | +0.066 |
Peter | +0.063 |
Andrew | +0.063 |
Neg logit contributions | |
aking | -0.122 |
ang | -0.112 |
ymes | -0.108 |
able | -0.104 |
iffs | -0.100 |
Token | different |
Token ID | 1180 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
oph | +0.017 |
Daddy | +0.017 |
um | +0.016 |
Father | +0.016 |
omm | +0.016 |
Neg logit contributions | |
aking | -0.021 |
ymes | -0.020 |
ang | -0.019 |
able | -0.019 |
respectful | -0.018 |
Token | shapes |
Token ID | 15268 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
Daddy | +0.064 |
mummy | +0.062 |
oph | +0.061 |
Father | +0.060 |
Jason | +0.060 |
Neg logit contributions | |
aking | -0.064 |
ymes | -0.062 |
ang | -0.058 |
able | -0.056 |
ites | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
Daddy | +0.061 |
mummy | +0.058 |
Father | +0.057 |
Peter | +0.056 |
oph | +0.055 |
Neg logit contributions | |
aking | -0.119 |
ang | -0.111 |
ymes | -0.109 |
able | -0.105 |
trap | -0.100 |
Token | but |
Token ID | 475 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
Daddy | +0.056 |
mummy | +0.054 |
oph | +0.053 |
Peter | +0.052 |
um | +0.051 |
Neg logit contributions | |
aking | -0.088 |
ang | -0.082 |
ymes | -0.080 |
able | -0.075 |
trap | -0.073 |
Token | words |
Token ID | 2456 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
aking | +0.018 |
ang | +0.017 |
ymes | +0.017 |
able | +0.015 |
trap | +0.015 |
Neg logit contributions | |
Daddy | -0.015 |
mummy | -0.014 |
Peter | -0.014 |
Jack | -0.013 |
oph | -0.013 |
Token | together |
Token ID | 1978 |
Feature activation | -1.59e-04 |
Pos logit contributions | |
Daddy | +0.033 |
mummy | +0.031 |
Peter | +0.030 |
Jack | +0.028 |
oph | +0.028 |
Neg logit contributions | |
aking | -0.063 |
ang | -0.060 |
ymes | -0.058 |
able | -0.055 |
iffs | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Daddy | +0.000 |
mummy | +0.000 |
Peter | +0.000 |
oph | +0.000 |
Jack | +0.000 |
Neg logit contributions | |
aking | -0.000 |
ang | -0.000 |
ymes | -0.000 |
able | -0.000 |
trap | -0.000 |
Token | holding |
Token ID | 4769 |
Feature activation | +6.53e-03 |
Pos logit contributions | |
Daddy | +0.014 |
mummy | +0.012 |
int | +0.012 |
Peter | +0.012 |
der | +0.012 |
Neg logit contributions | |
aking | -0.028 |
ang | -0.026 |
ymes | -0.026 |
able | -0.024 |
iffs | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
aking | +0.016 |
ang | +0.015 |
ymes | +0.014 |
iffs | +0.013 |
able | +0.013 |
Neg logit contributions | |
Daddy | -0.008 |
mummy | -0.008 |
Peter | -0.008 |
Jack | -0.007 |
int | -0.007 |
Token | paper |
Token ID | 3348 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
aking | +0.006 |
ang | +0.005 |
ymes | +0.005 |
able | +0.005 |
iffs | +0.005 |
Neg logit contributions | |
Daddy | -0.004 |
mummy | -0.004 |
Peter | -0.004 |
Jack | -0.004 |
der | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
Daddy | +0.063 |
mummy | +0.059 |
Peter | +0.058 |
oph | +0.056 |
Jack | +0.056 |
Neg logit contributions | |
aking | -0.110 |
ang | -0.103 |
ymes | -0.101 |
able | -0.094 |
iffs | -0.092 |
Token | As |
Token ID | 1081 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
aking | +0.036 |
ang | +0.034 |
ymes | +0.033 |
iffs | +0.032 |
able | +0.030 |
Neg logit contributions | |
Daddy | -0.025 |
mummy | -0.025 |
Peter | -0.024 |
oph | -0.023 |
int | -0.023 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
aking | +0.147 |
ang | +0.143 |
ymes | +0.141 |
able | +0.132 |
trap | +0.125 |
Neg logit contributions | |
Daddy | -0.082 |
oph | -0.079 |
mummy | -0.078 |
der | -0.078 |
int | -0.077 |
Token | as |
Token ID | 355 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
Daddy | +0.024 |
mummy | +0.023 |
Peter | +0.023 |
int | +0.022 |
Father | +0.021 |
Neg logit contributions | |
aking | -0.040 |
ang | -0.039 |
able | -0.036 |
ymes | -0.034 |
ites | -0.034 |
Token | they |
Token ID | 484 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
aking | +0.155 |
ang | +0.153 |
ymes | +0.149 |
able | +0.141 |
ites | +0.132 |
Neg logit contributions | |
int | -0.091 |
der | -0.091 |
oph | -0.089 |
Daddy | -0.089 |
Peter | -0.085 |