Token | asked |
Token ID | 1965 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
tant | +0.002 |
sc | +0.002 |
baths | +0.002 |
tests | +0.002 |
videos | +0.002 |
Neg logit contributions | |
ich | -0.002 |
opsy | -0.002 |
field | -0.002 |
ster | -0.002 |
flower | -0.002 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
sc | +0.014 |
tant | +0.013 |
igators | +0.012 |
baths | +0.012 |
igator | +0.011 |
Neg logit contributions | |
ich | -0.020 |
ster | -0.019 |
opsy | -0.019 |
� | -0.018 |
illa | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e-03 |
Pos logit contributions | |
tant | +0.018 |
sc | +0.017 |
baths | +0.016 |
videos | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.025 |
opsy | -0.022 |
ster | -0.021 |
field | -0.021 |
sters | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | +5.81e-04 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.006 |
field | +0.006 |
ster | +0.006 |
flower | +0.005 |
Neg logit contributions | |
tant | -0.004 |
sc | -0.004 |
baths | -0.004 |
videos | -0.003 |
tests | -0.003 |
Token | Which |
Token ID | 13828 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ich | +0.001 |
opsy | +0.001 |
field | +0.001 |
ster | +0.001 |
sters | +0.001 |
Neg logit contributions | |
sc | -0.001 |
tant | -0.001 |
baths | -0.001 |
videos | -0.001 |
tests | -0.001 |
Token | leash |
Token ID | 40529 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
ich | +0.033 |
opsy | +0.030 |
field | +0.029 |
ster | +0.027 |
flower | +0.025 |
Neg logit contributions | |
tant | -0.022 |
sc | -0.021 |
baths | -0.021 |
videos | -0.020 |
tests | -0.020 |
Token | do |
Token ID | 466 |
Feature activation | +8.03e-03 |
Pos logit contributions | |
ich | +0.152 |
opsy | +0.131 |
field | +0.130 |
ster | +0.125 |
sters | +0.117 |
Neg logit contributions | |
tant | -0.110 |
baths | -0.105 |
sc | -0.105 |
videos | -0.100 |
tests | -0.098 |
Token | you |
Token ID | 345 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.014 |
field | +0.013 |
ster | +0.013 |
sters | +0.012 |
Neg logit contributions | |
tant | -0.014 |
sc | -0.013 |
baths | -0.012 |
videos | -0.012 |
bang | -0.012 |
Token | want |
Token ID | 765 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
sc | +0.008 |
baths | +0.008 |
tant | +0.008 |
tests | +0.008 |
around | +0.008 |
Neg logit contributions | |
ich | -0.026 |
opsy | -0.023 |
field | -0.022 |
ster | -0.022 |
sters | -0.021 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.30e-03 |
Pos logit contributions | |
ich | +0.015 |
opsy | +0.014 |
field | +0.013 |
ster | +0.012 |
flower | +0.011 |
Neg logit contributions | |
tant | -0.011 |
sc | -0.011 |
baths | -0.011 |
videos | -0.010 |
tests | -0.010 |
Token | Max |
Token ID | 5436 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
tant | +0.007 |
sc | +0.007 |
igators | +0.007 |
baths | +0.006 |
igator | +0.006 |
Neg logit contributions | |
ich | -0.018 |
opsy | -0.017 |
field | -0.016 |
� | -0.016 |
ster | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
ich | +0.060 |
ster | +0.051 |
opsy | +0.050 |
field | +0.049 |
� | +0.047 |
Neg logit contributions | |
baths | -0.050 |
videos | -0.048 |
tests | -0.048 |
tant | -0.047 |
bang | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ich | +0.005 |
ster | +0.004 |
opsy | +0.004 |
� | +0.004 |
field | +0.004 |
Neg logit contributions | |
tant | -0.005 |
sc | -0.005 |
err | -0.004 |
bench | -0.004 |
baths | -0.004 |
Token | escaped |
Token ID | 13537 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ich | +0.037 |
opsy | +0.032 |
field | +0.031 |
ster | +0.030 |
sters | +0.028 |
Neg logit contributions | |
tant | -0.029 |
sc | -0.028 |
baths | -0.027 |
videos | -0.027 |
tests | -0.026 |
Token | from |
Token ID | 422 |
Feature activation | +5.68e-03 |
Pos logit contributions | |
ich | +0.063 |
opsy | +0.053 |
field | +0.052 |
ster | +0.050 |
ese | +0.046 |
Neg logit contributions | |
baths | -0.047 |
tant | -0.046 |
tests | -0.046 |
sc | -0.046 |
videos | -0.045 |
Token | his |
Token ID | 465 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
ich | +0.013 |
opsy | +0.011 |
field | +0.011 |
ster | +0.010 |
ese | +0.010 |
Neg logit contributions | |
sc | -0.008 |
tant | -0.007 |
baths | -0.007 |
taker | -0.007 |
aids | -0.007 |
Token | leash |
Token ID | 40529 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
ich | +0.018 |
opsy | +0.016 |
field | +0.015 |
ster | +0.015 |
flower | +0.014 |
Neg logit contributions | |
tant | -0.016 |
baths | -0.016 |
sc | -0.016 |
videos | -0.015 |
tests | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
ich | +0.152 |
opsy | +0.132 |
field | +0.129 |
ster | +0.124 |
sters | +0.114 |
Neg logit contributions | |
tant | -0.106 |
baths | -0.104 |
sc | -0.103 |
videos | -0.100 |
tests | -0.099 |
Token | He |
Token ID | 679 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ich | +0.004 |
ster | +0.003 |
opsy | +0.003 |
� | +0.003 |
field | +0.003 |
Neg logit contributions | |
tant | -0.002 |
sc | -0.002 |
err | -0.002 |
baths | -0.002 |
igsaw | -0.002 |
Token | is |
Token ID | 318 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
ich | +0.034 |
opsy | +0.030 |
field | +0.029 |
ster | +0.028 |
sters | +0.026 |
Neg logit contributions | |
tant | -0.027 |
sc | -0.026 |
baths | -0.026 |
videos | -0.025 |
tests | -0.024 |
Token | usually |
Token ID | 3221 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ich | +0.005 |
opsy | +0.004 |
ster | +0.004 |
anut | +0.004 |
pper | +0.004 |
Neg logit contributions | |
sc | -0.004 |
tant | -0.004 |
igsaw | -0.004 |
head | -0.004 |
baths | -0.003 |
Token | friendly |
Token ID | 8030 |
Feature activation | -1.49e-03 |
Pos logit contributions | |
ich | +0.039 |
opsy | +0.034 |
field | +0.033 |
ster | +0.032 |
ese | +0.031 |
Neg logit contributions | |
tant | -0.028 |
sc | -0.026 |
igsaw | -0.025 |
aids | -0.024 |
baths | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | -9.90e-03 |
Pos logit contributions | |
sc | +0.011 |
tant | +0.011 |
baths | +0.011 |
videos | +0.011 |
tests | +0.011 |
Neg logit contributions | |
ich | -0.018 |
opsy | -0.016 |
field | -0.015 |
ster | -0.015 |
flower | -0.014 |
Token | into |
Token ID | 656 |
Feature activation | -4.86e-03 |
Pos logit contributions | |
tant | +0.012 |
sc | +0.011 |
aids | +0.010 |
igators | +0.010 |
taker | +0.010 |
Neg logit contributions | |
ich | -0.024 |
field | -0.021 |
opsy | -0.021 |
ster | -0.020 |
wife | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
sc | +0.006 |
tant | +0.006 |
baths | +0.005 |
igators | +0.005 |
taker | +0.005 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.010 |
ster | -0.009 |
sters | -0.009 |
Token | woods |
Token ID | 16479 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
ich | +0.026 |
opsy | +0.021 |
field | +0.020 |
ster | +0.018 |
flower | +0.017 |
Neg logit contributions | |
sc | -0.039 |
tant | -0.037 |
taker | -0.036 |
baths | -0.035 |
bang | -0.035 |
Token | collecting |
Token ID | 13157 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ich | +0.016 |
field | +0.014 |
opsy | +0.014 |
ster | +0.013 |
flower | +0.012 |
Neg logit contributions | |
tant | -0.011 |
baths | -0.010 |
sc | -0.010 |
videos | -0.010 |
bang | -0.010 |
Token | berries |
Token ID | 36322 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
ich | +0.019 |
opsy | +0.018 |
ster | +0.017 |
sters | +0.017 |
field | +0.016 |
Neg logit contributions | |
James | -0.024 |
aids | -0.024 |
bang | -0.024 |
videos | -0.023 |
crash | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ich | +0.164 |
opsy | +0.148 |
field | +0.141 |
ster | +0.136 |
sters | +0.127 |
Neg logit contributions | |
tant | -0.094 |
sc | -0.093 |
baths | -0.091 |
videos | -0.087 |
tests | -0.087 |
Token | nuts |
Token ID | 14380 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
ich | +0.022 |
opsy | +0.020 |
field | +0.020 |
ster | +0.018 |
sters | +0.017 |
Neg logit contributions | |
tant | -0.022 |
sc | -0.021 |
baths | -0.020 |
videos | -0.020 |
taker | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
ich | +0.117 |
opsy | +0.105 |
field | +0.100 |
ster | +0.096 |
sters | +0.090 |
Neg logit contributions | |
sc | -0.062 |
tant | -0.061 |
baths | -0.060 |
tests | -0.056 |
videos | -0.056 |
Token | One |
Token ID | 1881 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
tests | +0.001 |
baths | +0.001 |
sc | +0.001 |
videos | +0.001 |
Everywhere | +0.001 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.003 |
ster | -0.003 |
field | -0.003 |
sters | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ich | +0.035 |
opsy | +0.032 |
field | +0.030 |
ster | +0.029 |
sters | +0.028 |
Neg logit contributions | |
tant | -0.016 |
sc | -0.016 |
baths | -0.015 |
videos | -0.015 |
tests | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ich | +0.004 |
opsy | +0.004 |
field | +0.004 |
ster | +0.003 |
� | +0.003 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
tests | -0.001 |
baths | -0.001 |
videos | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.15e-04 |
Pos logit contributions | |
ich | +0.032 |
opsy | +0.030 |
field | +0.029 |
ster | +0.027 |
sters | +0.027 |
Neg logit contributions | |
sc | -0.013 |
tant | -0.013 |
baths | -0.013 |
videos | -0.013 |
around | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
opsy | +0.001 |
ich | +0.001 |
flower | +0.001 |
field | +0.001 |
� | +0.001 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
tests | -0.001 |
baths | -0.000 |
bang | -0.000 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.99e-04 |
Pos logit contributions | |
ich | +0.028 |
opsy | +0.025 |
field | +0.024 |
ster | +0.023 |
sters | +0.021 |
Neg logit contributions | |
sc | -0.019 |
baths | -0.019 |
tant | -0.019 |
videos | -0.019 |
tests | -0.018 |
Token | picking |
Token ID | 10868 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ich | +0.001 |
opsy | +0.001 |
field | +0.001 |
ster | +0.001 |
sters | +0.001 |
Neg logit contributions | |
sc | -0.000 |
tant | -0.000 |
taker | -0.000 |
aids | -0.000 |
igators | -0.000 |
Token | berries |
Token ID | 36322 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
ich | +0.045 |
opsy | +0.040 |
ster | +0.036 |
field | +0.035 |
sters | +0.034 |
Neg logit contributions | |
tant | -0.047 |
sc | -0.047 |
tests | -0.044 |
aids | -0.044 |
bang | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ich | +0.171 |
opsy | +0.154 |
field | +0.148 |
ster | +0.143 |
flower | +0.134 |
Neg logit contributions | |
tant | -0.083 |
sc | -0.082 |
baths | -0.080 |
videos | -0.077 |
tests | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ich | +0.049 |
opsy | +0.045 |
field | +0.043 |
ster | +0.041 |
flower | +0.039 |
Neg logit contributions | |
sc | -0.021 |
tant | -0.021 |
baths | -0.019 |
tests | -0.019 |
videos | -0.018 |
Token | forest |
Token ID | 8222 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
ich | +0.067 |
opsy | +0.059 |
field | +0.056 |
ster | +0.053 |
flower | +0.049 |
Neg logit contributions | |
tant | -0.060 |
sc | -0.059 |
baths | -0.058 |
videos | -0.056 |
tests | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +9.38e-04 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.007 |
field | +0.007 |
ster | +0.006 |
flower | +0.006 |
Neg logit contributions | |
tant | -0.005 |
baths | -0.005 |
sc | -0.005 |
bang | -0.005 |
videos | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.003 |
field | +0.003 |
ster | +0.002 |
sters | +0.002 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
baths | -0.001 |
videos | -0.000 |
tests | -0.000 |
Token | when |
Token ID | 618 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
ich | +0.030 |
field | +0.026 |
opsy | +0.026 |
ster | +0.025 |
flower | +0.023 |
Neg logit contributions | |
tant | -0.021 |
videos | -0.019 |
baths | -0.019 |
sc | -0.019 |
tests | -0.018 |
Token | they |
Token ID | 484 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
ich | +0.020 |
opsy | +0.018 |
field | +0.017 |
ster | +0.017 |
flower | +0.016 |
Neg logit contributions | |
tant | -0.011 |
sc | -0.011 |
baths | -0.011 |
tests | -0.010 |
videos | -0.010 |
Token | bought |
Token ID | 5839 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
ich | +0.013 |
opsy | +0.011 |
field | +0.011 |
ster | +0.010 |
flower | +0.009 |
Neg logit contributions | |
tant | -0.010 |
sc | -0.010 |
baths | -0.010 |
videos | -0.009 |
tests | -0.009 |
Token | Sunshine |
Token ID | 32210 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
sc | +0.002 |
tant | +0.002 |
videos | +0.002 |
bang | +0.002 |
baths | +0.002 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.004 |
field | -0.004 |
ster | -0.003 |
wife | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.014 |
field | +0.014 |
ster | +0.013 |
sters | +0.012 |
Neg logit contributions | |
tant | -0.009 |
sc | -0.009 |
baths | -0.009 |
videos | -0.008 |
tests | -0.008 |
Token | leash |
Token ID | 40529 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
sc | +0.008 |
baths | +0.008 |
tant | +0.008 |
loud | +0.007 |
tests | +0.007 |
Neg logit contributions | |
ich | -0.012 |
opsy | -0.011 |
field | -0.010 |
ster | -0.010 |
sters | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-03 |
Pos logit contributions | |
ich | +0.145 |
opsy | +0.126 |
field | +0.125 |
ster | +0.119 |
flower | +0.110 |
Neg logit contributions | |
tant | -0.108 |
baths | -0.104 |
sc | -0.101 |
videos | -0.101 |
tests | -0.100 |
Token | Sunshine |
Token ID | 32210 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
ich | +0.009 |
opsy | +0.008 |
field | +0.008 |
ster | +0.008 |
sters | +0.007 |
Neg logit contributions | |
sc | -0.004 |
baths | -0.004 |
tant | -0.004 |
videos | -0.004 |
tests | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
ich | +0.022 |
opsy | +0.019 |
field | +0.018 |
ster | +0.017 |
sters | +0.016 |
Neg logit contributions | |
sc | -0.013 |
baths | -0.012 |
tant | -0.012 |
tests | -0.011 |
around | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
sc | +0.003 |
tant | +0.003 |
baths | +0.003 |
videos | +0.003 |
tests | +0.003 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.005 |
field | -0.005 |
ster | -0.005 |
flower | -0.005 |
Token | too |
Token ID | 1165 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ich | +0.040 |
opsy | +0.036 |
field | +0.035 |
ster | +0.034 |
sters | +0.032 |
Neg logit contributions | |
baths | -0.015 |
tant | -0.015 |
sc | -0.015 |
videos | -0.014 |
tests | -0.014 |
Token | home |
Token ID | 1363 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
ich | +0.019 |
opsy | +0.016 |
field | +0.016 |
ster | +0.015 |
flower | +0.014 |
Neg logit contributions | |
tant | -0.013 |
sc | -0.013 |
tests | -0.012 |
bang | -0.012 |
aids | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-04 |
Pos logit contributions | |
ich | +0.007 |
field | +0.006 |
opsy | +0.006 |
ster | +0.006 |
flower | +0.005 |
Neg logit contributions | |
tant | -0.007 |
sc | -0.006 |
baths | -0.006 |
videos | -0.006 |
bang | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +8.56e-03 |
Pos logit contributions | |
tant | +0.000 |
sc | +0.000 |
baths | +0.000 |
tests | +0.000 |
bang | +0.000 |
Neg logit contributions | |
ich | -0.000 |
field | -0.000 |
opsy | -0.000 |
� | -0.000 |
ster | -0.000 |
Token | put |
Token ID | 1234 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.014 |
field | +0.013 |
ster | +0.013 |
flower | +0.011 |
Neg logit contributions | |
tant | -0.015 |
sc | -0.015 |
baths | -0.014 |
videos | -0.014 |
tests | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-03 |
Pos logit contributions | |
villains | +0.005 |
tant | +0.005 |
sc | +0.005 |
tests | +0.005 |
baths | +0.004 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.005 |
flower | -0.005 |
field | -0.005 |
ster | -0.005 |
Token | leash |
Token ID | 40529 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
tant | +0.007 |
baths | +0.007 |
sc | +0.007 |
tests | +0.006 |
videos | +0.006 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.008 |
ster | -0.007 |
sters | -0.007 |
Token | back |
Token ID | 736 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
ich | +0.136 |
field | +0.115 |
ster | +0.113 |
opsy | +0.111 |
� | +0.110 |
Neg logit contributions | |
tant | -0.105 |
baths | -0.105 |
videos | -0.104 |
tests | -0.101 |
bang | -0.100 |
Token | on |
Token ID | 319 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
ich | +0.095 |
field | +0.083 |
opsy | +0.083 |
ster | +0.078 |
flower | +0.074 |
Neg logit contributions | |
tant | -0.060 |
baths | -0.059 |
videos | -0.057 |
sc | -0.057 |
bang | -0.057 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.015 |
field | +0.015 |
ster | +0.013 |
flower | +0.013 |
Neg logit contributions | |
sc | -0.009 |
tant | -0.009 |
baths | -0.009 |
tests | -0.008 |
bang | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
ich | +0.048 |
opsy | +0.042 |
field | +0.042 |
ster | +0.039 |
flower | +0.036 |
Neg logit contributions | |
tant | -0.042 |
sc | -0.040 |
tests | -0.039 |
baths | -0.039 |
videos | -0.039 |
Token | they |
Token ID | 484 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
tant | +0.016 |
sc | +0.016 |
baths | +0.015 |
videos | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.015 |
field | -0.014 |
ster | -0.013 |
flower | -0.012 |
Token | home |
Token ID | 1363 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
ich | +0.019 |
opsy | +0.016 |
field | +0.016 |
ster | +0.015 |
flower | +0.014 |
Neg logit contributions | |
tant | -0.013 |
sc | -0.013 |
tests | -0.012 |
bang | -0.012 |
aids | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-04 |
Pos logit contributions | |
ich | +0.007 |
field | +0.006 |
opsy | +0.006 |
ster | +0.006 |
flower | +0.005 |
Neg logit contributions | |
tant | -0.007 |
sc | -0.006 |
baths | -0.006 |
videos | -0.006 |
bang | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +8.56e-03 |
Pos logit contributions | |
tant | +0.000 |
sc | +0.000 |
baths | +0.000 |
tests | +0.000 |
bang | +0.000 |
Neg logit contributions | |
ich | -0.000 |
field | -0.000 |
opsy | -0.000 |
� | -0.000 |
ster | -0.000 |
Token | put |
Token ID | 1234 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.014 |
field | +0.013 |
ster | +0.013 |
flower | +0.011 |
Neg logit contributions | |
tant | -0.015 |
sc | -0.015 |
baths | -0.014 |
videos | -0.014 |
tests | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-03 |
Pos logit contributions | |
villains | +0.005 |
tant | +0.005 |
sc | +0.005 |
tests | +0.005 |
baths | +0.004 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.005 |
flower | -0.005 |
field | -0.005 |
ster | -0.005 |
Token | leash |
Token ID | 40529 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
tant | +0.007 |
baths | +0.007 |
sc | +0.007 |
tests | +0.006 |
videos | +0.006 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.008 |
ster | -0.007 |
sters | -0.007 |
Token | back |
Token ID | 736 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
ich | +0.136 |
field | +0.115 |
ster | +0.113 |
opsy | +0.111 |
� | +0.110 |
Neg logit contributions | |
tant | -0.105 |
baths | -0.105 |
videos | -0.104 |
tests | -0.101 |
bang | -0.100 |
Token | on |
Token ID | 319 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
ich | +0.095 |
field | +0.083 |
opsy | +0.083 |
ster | +0.078 |
flower | +0.074 |
Neg logit contributions | |
tant | -0.060 |
baths | -0.059 |
videos | -0.057 |
sc | -0.057 |
bang | -0.057 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.015 |
field | +0.015 |
ster | +0.013 |
flower | +0.013 |
Neg logit contributions | |
sc | -0.009 |
tant | -0.009 |
baths | -0.009 |
tests | -0.008 |
bang | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
ich | +0.048 |
opsy | +0.042 |
field | +0.042 |
ster | +0.039 |
flower | +0.036 |
Neg logit contributions | |
tant | -0.042 |
sc | -0.040 |
tests | -0.039 |
baths | -0.039 |
videos | -0.039 |
Token | they |
Token ID | 484 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
tant | +0.016 |
sc | +0.016 |
baths | +0.015 |
videos | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.015 |
field | -0.014 |
ster | -0.013 |
flower | -0.012 |
Token | forest |
Token ID | 8222 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
ich | +0.039 |
opsy | +0.033 |
field | +0.030 |
ster | +0.028 |
flower | +0.026 |
Neg logit contributions | |
tant | -0.050 |
sc | -0.050 |
tests | -0.046 |
taker | -0.046 |
baths | -0.046 |
Token | where |
Token ID | 810 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
tant | +0.002 |
baths | +0.002 |
bang | +0.002 |
sc | +0.002 |
videos | +0.002 |
Neg logit contributions | |
ich | -0.003 |
field | -0.003 |
opsy | -0.003 |
ster | -0.003 |
flower | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | +9.39e-03 |
Pos logit contributions | |
ich | +0.037 |
opsy | +0.032 |
field | +0.031 |
flower | +0.028 |
ster | +0.027 |
Neg logit contributions | |
sc | -0.041 |
tant | -0.040 |
channel | -0.036 |
bang | -0.035 |
riend | -0.035 |
Token | would |
Token ID | 561 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
ich | +0.019 |
opsy | +0.017 |
field | +0.016 |
ster | +0.016 |
flower | +0.014 |
Neg logit contributions | |
tant | -0.014 |
sc | -0.014 |
baths | -0.014 |
videos | -0.013 |
tests | -0.013 |
Token | pick |
Token ID | 2298 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
ich | +0.037 |
opsy | +0.033 |
field | +0.032 |
ster | +0.030 |
flower | +0.028 |
Neg logit contributions | |
tant | -0.027 |
sc | -0.027 |
baths | -0.026 |
videos | -0.025 |
tests | -0.024 |
Token | berries |
Token ID | 36322 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
ich | +0.075 |
opsy | +0.065 |
ster | +0.058 |
field | +0.058 |
sters | +0.054 |
Neg logit contributions | |
tant | -0.095 |
sc | -0.090 |
tests | -0.089 |
videos | -0.088 |
bang | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
ich | +0.164 |
opsy | +0.148 |
field | +0.141 |
ster | +0.137 |
flower | +0.127 |
Neg logit contributions | |
sc | -0.082 |
tant | -0.081 |
baths | -0.079 |
videos | -0.075 |
tests | -0.075 |
Token | One |
Token ID | 1881 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.003 |
field | +0.003 |
ster | +0.003 |
sters | +0.003 |
Neg logit contributions | |
sc | -0.001 |
tant | -0.001 |
baths | -0.001 |
videos | -0.001 |
tests | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ich | +0.042 |
opsy | +0.037 |
field | +0.037 |
ster | +0.036 |
sters | +0.035 |
Neg logit contributions | |
baths | -0.015 |
sc | -0.015 |
tant | -0.015 |
videos | -0.014 |
around | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
tant | +0.041 |
sc | +0.041 |
baths | +0.040 |
videos | +0.038 |
tests | +0.038 |
Neg logit contributions | |
ich | -0.080 |
opsy | -0.072 |
field | -0.070 |
ster | -0.067 |
flower | -0.062 |
Token | she |
Token ID | 673 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
sc | +0.002 |
tant | +0.002 |
baths | +0.002 |
tests | +0.002 |
igators | +0.002 |
Neg logit contributions | |
ich | -0.005 |
opsy | -0.004 |
field | -0.004 |
ster | -0.004 |
� | -0.004 |
Token | up |
Token ID | 510 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
opsy | +0.019 |
ich | +0.018 |
field | +0.017 |
ige | +0.016 |
ster | +0.016 |
Neg logit contributions | |
villains | -0.016 |
sc | -0.014 |
bang | -0.014 |
crashes | -0.014 |
crash | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ich | +0.049 |
opsy | +0.046 |
field | +0.044 |
ster | +0.041 |
sters | +0.038 |
Neg logit contributions | |
sc | -0.030 |
tant | -0.030 |
bang | -0.029 |
igators | -0.029 |
videos | -0.028 |
Token | basket |
Token ID | 7988 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
tant | +0.013 |
sc | +0.012 |
baths | +0.012 |
tests | +0.011 |
videos | +0.011 |
Neg logit contributions | |
ich | -0.024 |
opsy | -0.021 |
field | -0.020 |
ster | -0.019 |
sters | -0.018 |
Token | full |
Token ID | 1336 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ich | +0.093 |
opsy | +0.085 |
field | +0.082 |
ster | +0.079 |
flower | +0.075 |
Neg logit contributions | |
tant | -0.039 |
sc | -0.037 |
baths | -0.037 |
videos | -0.035 |
tests | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | -2.70e-03 |
Pos logit contributions | |
tant | +0.013 |
sc | +0.012 |
baths | +0.012 |
videos | +0.012 |
tests | +0.011 |
Neg logit contributions | |
ich | -0.049 |
opsy | -0.047 |
field | -0.045 |
ster | -0.044 |
flower | -0.042 |
Token | berries |
Token ID | 36322 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
sc | +0.005 |
tant | +0.004 |
videos | +0.004 |
baths | +0.004 |
bang | +0.004 |
Neg logit contributions | |
ich | -0.005 |
opsy | -0.004 |
field | -0.004 |
ster | -0.004 |
sters | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
ich | +0.154 |
opsy | +0.139 |
field | +0.133 |
ster | +0.128 |
sters | +0.119 |
Neg logit contributions | |
tant | -0.090 |
sc | -0.088 |
baths | -0.087 |
videos | -0.083 |
tests | -0.083 |
Token | carried |
Token ID | 5281 |
Feature activation | -3.86e-03 |
Pos logit contributions | |
ich | +0.005 |
opsy | +0.005 |
field | +0.004 |
ster | +0.004 |
sters | +0.004 |
Neg logit contributions | |
tant | -0.004 |
sc | -0.004 |
videos | -0.004 |
tests | -0.004 |
baths | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
videos | +0.005 |
tests | +0.005 |
igators | +0.005 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.008 |
field | -0.007 |
ster | -0.007 |
pper | -0.007 |
Token | back |
Token ID | 736 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
tant | +0.004 |
videos | +0.004 |
sc | +0.004 |
bang | +0.004 |
tests | +0.004 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.006 |
field | -0.005 |
ster | -0.005 |
flower | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
ich | +0.077 |
opsy | +0.069 |
field | +0.066 |
ster | +0.063 |
flower | +0.059 |
Neg logit contributions | |
tant | -0.046 |
sc | -0.045 |
baths | -0.045 |
videos | -0.043 |
tests | -0.043 |
Token | outside |
Token ID | 2354 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
tant | +0.008 |
sc | +0.007 |
baths | +0.007 |
videos | +0.007 |
tests | +0.007 |
Neg logit contributions | |
ich | -0.020 |
opsy | -0.018 |
field | -0.017 |
ster | -0.017 |
flower | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ich | +0.013 |
field | +0.012 |
opsy | +0.011 |
ster | +0.011 |
flower | +0.010 |
Neg logit contributions | |
tant | -0.010 |
sc | -0.010 |
baths | -0.010 |
videos | -0.010 |
aids | -0.010 |
Token | look |
Token ID | 804 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
ich | +0.022 |
field | +0.020 |
opsy | +0.020 |
ster | +0.018 |
flower | +0.017 |
Neg logit contributions | |
tant | -0.016 |
sc | -0.016 |
baths | -0.015 |
videos | -0.015 |
taker | -0.014 |
Token | at |
Token ID | 379 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ich | +0.008 |
opsy | +0.007 |
field | +0.007 |
ster | +0.007 |
flower | +0.006 |
Neg logit contributions | |
tant | -0.005 |
sc | -0.005 |
baths | -0.005 |
videos | -0.004 |
tests | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ich | +0.029 |
opsy | +0.026 |
field | +0.025 |
ster | +0.024 |
flower | +0.022 |
Neg logit contributions | |
sc | -0.014 |
tant | -0.013 |
baths | -0.013 |
videos | -0.012 |
tests | -0.012 |
Token | cher |
Token ID | 21382 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
ich | +0.044 |
opsy | +0.043 |
field | +0.042 |
ster | +0.041 |
pper | +0.040 |
Neg logit contributions | |
loud | -0.018 |
tant | -0.017 |
traffic | -0.016 |
around | -0.016 |
noise | -0.016 |
Token | ries |
Token ID | 1678 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
wife | +0.133 |
opsy | +0.132 |
ich | +0.131 |
iya | +0.125 |
field | +0.122 |
Neg logit contributions | |
around | -0.071 |
tant | -0.070 |
iren | -0.067 |
chairs | -0.066 |
head | -0.065 |
Token | on |
Token ID | 319 |
Feature activation | +8.97e-03 |
Pos logit contributions | |
ich | +0.149 |
opsy | +0.137 |
field | +0.125 |
ster | +0.123 |
iya | +0.117 |
Neg logit contributions | |
sc | -0.064 |
tant | -0.062 |
baths | -0.061 |
tests | -0.059 |
around | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
ich | +0.022 |
opsy | +0.019 |
field | +0.019 |
ster | +0.018 |
flower | +0.017 |
Neg logit contributions | |
sc | -0.011 |
tant | -0.010 |
baths | -0.010 |
videos | -0.009 |
tests | -0.009 |
Token | tree |
Token ID | 5509 |
Feature activation | +5.67e-03 |
Pos logit contributions | |
ich | +0.014 |
opsy | +0.013 |
field | +0.012 |
ster | +0.012 |
ipper | +0.012 |
Neg logit contributions | |
loud | -0.007 |
around | -0.007 |
tant | -0.007 |
sc | -0.006 |
baths | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.40e-04 |
Pos logit contributions | |
ich | +0.012 |
field | +0.010 |
opsy | +0.010 |
ster | +0.009 |
flower | +0.009 |
Neg logit contributions | |
tant | -0.009 |
baths | -0.009 |
sc | -0.008 |
videos | -0.008 |
tests | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
tant | +0.019 |
sc | +0.017 |
baths | +0.016 |
tests | +0.016 |
videos | +0.016 |
Neg logit contributions | |
ich | -0.075 |
opsy | -0.071 |
field | -0.068 |
ster | -0.067 |
flower | -0.063 |
Token | juicy |
Token ID | 35075 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
sc | +0.016 |
tant | +0.015 |
videos | +0.015 |
aids | +0.015 |
bang | +0.015 |
Neg logit contributions | |
ich | -0.013 |
opsy | -0.013 |
field | -0.011 |
ster | -0.010 |
sters | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ich | +0.081 |
opsy | +0.070 |
field | +0.067 |
ster | +0.064 |
flower | +0.058 |
Neg logit contributions | |
tant | -0.067 |
sc | -0.067 |
baths | -0.066 |
videos | -0.063 |
tests | -0.063 |
Token | tasty |
Token ID | 25103 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
ich | +0.041 |
opsy | +0.037 |
field | +0.035 |
ster | +0.035 |
sters | +0.032 |
Neg logit contributions | |
tant | -0.032 |
sc | -0.030 |
tests | -0.030 |
baths | -0.029 |
videos | -0.029 |
Token | looking |
Token ID | 2045 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
ich | +0.062 |
opsy | +0.055 |
field | +0.051 |
ster | +0.049 |
sters | +0.045 |
Neg logit contributions | |
tant | -0.053 |
sc | -0.053 |
baths | -0.052 |
videos | -0.050 |
tests | -0.050 |
Token | berries |
Token ID | 36322 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.015 |
ster | +0.014 |
field | +0.014 |
sters | +0.013 |
Neg logit contributions | |
tests | -0.013 |
tant | -0.013 |
baths | -0.012 |
videos | -0.012 |
sc | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-04 |
Pos logit contributions | |
ich | +0.157 |
opsy | +0.140 |
field | +0.133 |
ster | +0.128 |
flower | +0.119 |
Neg logit contributions | |
sc | -0.088 |
baths | -0.084 |
tant | -0.084 |
videos | -0.078 |
tests | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
ich | +0.001 |
opsy | +0.001 |
field | +0.001 |
ster | +0.001 |
� | +0.001 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
baths | -0.001 |
videos | -0.001 |
tests | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +9.95e-03 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.003 |
field | +0.003 |
ster | +0.003 |
flower | +0.003 |
Neg logit contributions | |
sc | -0.002 |
tant | -0.002 |
baths | -0.002 |
tests | -0.002 |
videos | -0.002 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ich | +0.018 |
opsy | +0.016 |
field | +0.015 |
ster | +0.014 |
sters | +0.013 |
Neg logit contributions | |
tant | -0.017 |
sc | -0.017 |
baths | -0.017 |
videos | -0.016 |
tests | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
tant | +0.016 |
sc | +0.016 |
baths | +0.015 |
videos | +0.015 |
tests | +0.014 |
Neg logit contributions | |
ich | -0.024 |
opsy | -0.021 |
field | -0.020 |
ster | -0.020 |
sters | -0.018 |
Token | walk |
Token ID | 2513 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
tant | +0.024 |
sc | +0.024 |
baths | +0.023 |
tests | +0.022 |
taker | +0.022 |
Neg logit contributions | |
ich | -0.024 |
opsy | -0.021 |
field | -0.020 |
ster | -0.019 |
� | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
ich | +0.028 |
field | +0.025 |
opsy | +0.023 |
ster | +0.022 |
flower | +0.021 |
Neg logit contributions | |
tant | -0.025 |
baths | -0.024 |
bang | -0.023 |
tests | -0.023 |
aids | -0.022 |
Token | they |
Token ID | 484 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ich | +0.006 |
opsy | +0.005 |
field | +0.005 |
ster | +0.005 |
� | +0.004 |
Neg logit contributions | |
tant | -0.006 |
sc | -0.006 |
baths | -0.006 |
videos | -0.006 |
igsaw | -0.006 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
ich | +0.031 |
opsy | +0.027 |
field | +0.026 |
ster | +0.026 |
sters | +0.024 |
Neg logit contributions | |
sc | -0.015 |
tant | -0.015 |
baths | -0.015 |
around | -0.014 |
bang | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
sc | +0.003 |
tant | +0.003 |
baths | +0.003 |
channel | +0.003 |
igsaw | +0.003 |
Neg logit contributions | |
ich | -0.005 |
opsy | -0.004 |
field | -0.004 |
ster | -0.004 |
sters | -0.004 |
Token | leash |
Token ID | 40529 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
ich | +0.021 |
opsy | +0.019 |
field | +0.018 |
ster | +0.017 |
flower | +0.016 |
Neg logit contributions | |
sc | -0.017 |
tant | -0.016 |
baths | -0.016 |
tests | -0.015 |
videos | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
ich | +0.145 |
opsy | +0.129 |
field | +0.123 |
ster | +0.118 |
flower | +0.109 |
Neg logit contributions | |
tant | -0.097 |
sc | -0.096 |
baths | -0.095 |
videos | -0.091 |
tests | -0.090 |
Token | broken |
Token ID | 5445 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
tant | +0.013 |
sc | +0.013 |
igsaw | +0.012 |
baths | +0.012 |
tests | +0.012 |
Neg logit contributions | |
ich | -0.017 |
field | -0.014 |
opsy | -0.014 |
ster | -0.012 |
flower | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
tant | +0.045 |
baths | +0.043 |
sc | +0.042 |
tests | +0.042 |
aids | +0.042 |
Neg logit contributions | |
ich | -0.041 |
field | -0.034 |
opsy | -0.033 |
ster | -0.032 |
flower | -0.030 |
Token | The |
Token ID | 383 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
tests | +0.004 |
baths | +0.004 |
videos | +0.004 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
field | -0.007 |
� | -0.007 |
ster | -0.006 |
Token | owner |
Token ID | 4870 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
tant | +0.003 |
loud | +0.003 |
baths | +0.003 |
videos | +0.003 |
sc | +0.003 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
sters | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -9.58e-03 |
Pos logit contributions | |
ich | +0.059 |
opsy | +0.052 |
field | +0.050 |
ster | +0.050 |
flower | +0.046 |
Neg logit contributions | |
tant | -0.035 |
baths | -0.034 |
sc | -0.034 |
videos | -0.033 |
tests | -0.032 |
Token | able |
Token ID | 1498 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
sc | +0.015 |
tant | +0.015 |
baths | +0.014 |
videos | +0.014 |
tests | +0.014 |
Neg logit contributions | |
ich | -0.020 |
opsy | -0.017 |
field | -0.016 |
ster | -0.016 |
flower | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
ich | +0.088 |
opsy | +0.080 |
field | +0.077 |
ster | +0.075 |
sters | +0.071 |
Neg logit contributions | |
tant | -0.027 |
sc | -0.027 |
baths | -0.025 |
videos | -0.024 |
tests | -0.023 |
Token | restore |
Token ID | 11169 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
ich | +0.013 |
opsy | +0.012 |
field | +0.011 |
ster | +0.011 |
pper | +0.010 |
Neg logit contributions | |
tant | -0.009 |
sc | -0.008 |
baths | -0.008 |
igators | -0.008 |
videos | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +8.92e-03 |
Pos logit contributions | |
sc | +0.025 |
tant | +0.024 |
riend | +0.023 |
igators | +0.023 |
bang | +0.023 |
Neg logit contributions | |
ich | -0.031 |
opsy | -0.028 |
field | -0.026 |
ster | -0.025 |
illa | -0.023 |
Token | leash |
Token ID | 40529 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
ich | +0.018 |
opsy | +0.016 |
field | +0.016 |
ster | +0.015 |
sters | +0.014 |
Neg logit contributions | |
tant | -0.014 |
sc | -0.014 |
baths | -0.014 |
tests | -0.013 |
videos | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
ich | +0.131 |
field | +0.115 |
ster | +0.109 |
opsy | +0.107 |
flower | +0.099 |
Neg logit contributions | |
tant | -0.108 |
baths | -0.106 |
igators | -0.099 |
tests | -0.099 |
showers | -0.099 |
Token | it |
Token ID | 340 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
ich | +0.008 |
field | +0.007 |
opsy | +0.007 |
ster | +0.007 |
wife | +0.007 |
Neg logit contributions | |
tant | -0.007 |
sc | -0.007 |
igsaw | -0.006 |
aids | -0.006 |
baths | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.25e-03 |
Pos logit contributions | |
tant | +0.023 |
videos | +0.021 |
igsaw | +0.021 |
sc | +0.021 |
igators | +0.021 |
Neg logit contributions | |
ich | -0.021 |
field | -0.019 |
opsy | -0.019 |
ster | -0.018 |
flower | -0.017 |
Token | as |
Token ID | 355 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
sc | +0.003 |
tant | +0.003 |
baths | +0.003 |
tests | +0.003 |
videos | +0.003 |
Neg logit contributions | |
ich | -0.005 |
opsy | -0.005 |
field | -0.004 |
ster | -0.004 |
flower | -0.004 |
Token | good |
Token ID | 922 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ich | +0.041 |
opsy | +0.035 |
ster | +0.035 |
field | +0.033 |
husband | +0.032 |
Neg logit contributions | |
sc | -0.030 |
tant | -0.029 |
aids | -0.029 |
aled | -0.028 |
bang | -0.028 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
baths | +0.004 |
tests | +0.004 |
videos | +0.004 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
field | -0.007 |
ster | -0.007 |
� | -0.006 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ich | +0.021 |
opsy | +0.019 |
field | +0.018 |
ster | +0.017 |
flower | +0.016 |
Neg logit contributions | |
sc | -0.012 |
baths | -0.012 |
tant | -0.012 |
videos | -0.011 |
tests | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
wife | +0.025 |
opsy | +0.025 |
husband | +0.024 |
ich | +0.024 |
ster | +0.023 |
Neg logit contributions | |
sc | -0.026 |
villains | -0.024 |
outage | -0.024 |
| | -0.023 |
storms | -0.023 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
sc | +0.023 |
tant | +0.023 |
baths | +0.022 |
tests | +0.021 |
videos | +0.021 |
Neg logit contributions | |
ich | -0.030 |
opsy | -0.026 |
field | -0.025 |
ster | -0.024 |
sters | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ich | +0.031 |
opsy | +0.027 |
ster | +0.025 |
field | +0.024 |
flower | +0.022 |
Neg logit contributions | |
tant | -0.030 |
aids | -0.028 |
igators | -0.028 |
tests | -0.028 |
taker | -0.028 |
Token | leash |
Token ID | 40529 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
igators | +0.050 |
tests | +0.049 |
tant | +0.049 |
head | +0.049 |
sc | +0.049 |
Neg logit contributions | |
ich | -0.047 |
opsy | -0.039 |
ster | -0.038 |
field | -0.037 |
� | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
ich | +0.124 |
field | +0.105 |
opsy | +0.104 |
ster | +0.102 |
� | +0.091 |
Neg logit contributions | |
tant | -0.117 |
baths | -0.114 |
tests | -0.110 |
igators | -0.109 |
videos | -0.109 |
Token | started |
Token ID | 2067 |
Feature activation | +5.38e-03 |
Pos logit contributions | |
tant | +0.003 |
aids | +0.003 |
sc | +0.003 |
igsaw | +0.003 |
tests | +0.003 |
Neg logit contributions | |
ich | -0.003 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
sters | -0.002 |
Token | marching |
Token ID | 26409 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ich | +0.010 |
opsy | +0.008 |
field | +0.008 |
ster | +0.007 |
� | +0.007 |
Neg logit contributions | |
tant | -0.009 |
igator | -0.009 |
igators | -0.009 |
sc | -0.009 |
igsaw | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | -7.30e-03 |
Pos logit contributions | |
aids | +0.058 |
igators | +0.056 |
igsaw | +0.054 |
x | +0.054 |
tant | +0.053 |
Neg logit contributions | |
ich | -0.052 |
� | -0.045 |
ster | -0.043 |
field | -0.043 |
opsy | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
sc | +0.014 |
auc | +0.013 |
riend | +0.012 |
ro | +0.012 |
| | +0.012 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.009 |
mum | -0.009 |
husband | -0.009 |
pearl | -0.009 |
Token | that |
Token ID | 326 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
tant | +0.002 |
sc | +0.002 |
baths | +0.001 |
bang | +0.001 |
aids | +0.001 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.004 |
field | -0.004 |
ster | -0.003 |
sters | -0.003 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ich | +0.010 |
field | +0.009 |
ster | +0.008 |
opsy | +0.008 |
� | +0.008 |
Neg logit contributions | |
tant | -0.012 |
sc | -0.011 |
igsaw | -0.011 |
riend | -0.011 |
igators | -0.010 |
Token | understood |
Token ID | 7247 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
ich | +0.026 |
opsy | +0.023 |
field | +0.022 |
ster | +0.021 |
sters | +0.019 |
Neg logit contributions | |
tant | -0.019 |
sc | -0.019 |
baths | -0.018 |
videos | -0.018 |
tests | -0.018 |
Token | what |
Token ID | 644 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ich | +0.038 |
opsy | +0.034 |
field | +0.033 |
ster | +0.032 |
sters | +0.029 |
Neg logit contributions | |
sc | -0.025 |
tant | -0.024 |
baths | -0.023 |
videos | -0.022 |
igators | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
ich | +0.053 |
opsy | +0.046 |
ster | +0.045 |
field | +0.045 |
wife | +0.042 |
Neg logit contributions | |
tant | -0.036 |
sc | -0.034 |
aled | -0.029 |
head | -0.029 |
bang | -0.029 |
Token | leash |
Token ID | 40529 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
ich | +0.014 |
opsy | +0.012 |
field | +0.012 |
ster | +0.011 |
sters | +0.010 |
Neg logit contributions | |
tant | -0.014 |
sc | -0.014 |
baths | -0.014 |
videos | -0.014 |
tests | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ich | +0.133 |
opsy | +0.115 |
field | +0.113 |
ster | +0.108 |
flower | +0.100 |
Neg logit contributions | |
tant | -0.109 |
baths | -0.104 |
sc | -0.104 |
videos | -0.102 |
tests | -0.099 |
Token | for |
Token ID | 329 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ich | +0.029 |
opsy | +0.026 |
field | +0.025 |
ster | +0.024 |
sters | +0.023 |
Neg logit contributions | |
tant | -0.016 |
sc | -0.016 |
baths | -0.016 |
videos | -0.015 |
tests | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
tant | +0.019 |
sc | +0.019 |
baths | +0.017 |
igators | +0.016 |
tests | +0.016 |
Neg logit contributions | |
ich | -0.031 |
opsy | -0.027 |
field | -0.026 |
ster | -0.026 |
sters | -0.024 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
sc | +0.025 |
tant | +0.024 |
igsaw | +0.022 |
x | +0.022 |
channel | +0.021 |
Neg logit contributions | |
ich | -0.028 |
field | -0.024 |
opsy | -0.024 |
ster | -0.024 |
wife | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ich | +0.024 |
opsy | +0.021 |
field | +0.021 |
ster | +0.020 |
sters | +0.018 |
Neg logit contributions | |
tant | -0.013 |
sc | -0.013 |
baths | -0.011 |
igators | -0.011 |
videos | -0.011 |
Token | helped |
Token ID | 4193 |
Feature activation | -6.80e-03 |
Pos logit contributions | |
ich | +0.075 |
opsy | +0.069 |
field | +0.066 |
ster | +0.064 |
ese | +0.060 |
Neg logit contributions | |
tant | -0.033 |
sc | -0.032 |
baths | -0.030 |
videos | -0.030 |
tests | -0.029 |
Token | someone |
Token ID | 2130 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
tant | +0.010 |
sc | +0.010 |
igators | +0.009 |
igsaw | +0.009 |
taker | +0.009 |
Neg logit contributions | |
ich | -0.014 |
opsy | -0.013 |
field | -0.012 |
ster | -0.012 |
wife | -0.011 |
Token | find |
Token ID | 1064 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
tant | +0.039 |
sc | +0.038 |
baths | +0.037 |
videos | +0.036 |
tests | +0.035 |
Neg logit contributions | |
ich | -0.070 |
opsy | -0.063 |
field | -0.061 |
ster | -0.059 |
sters | -0.055 |
Token | their |
Token ID | 511 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
ich | +0.014 |
opsy | +0.013 |
ster | +0.012 |
field | +0.012 |
ese | +0.011 |
Neg logit contributions | |
tant | -0.008 |
sc | -0.008 |
bang | -0.008 |
baths | -0.008 |
videos | -0.008 |
Token | lost |
Token ID | 2626 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
ich | +0.006 |
opsy | +0.006 |
field | +0.005 |
ster | +0.005 |
sters | +0.005 |
Neg logit contributions | |
tant | -0.005 |
baths | -0.005 |
sc | -0.004 |
tests | -0.004 |
videos | -0.004 |
Token | pet |
Token ID | 4273 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
ich | +0.015 |
opsy | +0.013 |
field | +0.012 |
ster | +0.012 |
flower | +0.011 |
Neg logit contributions | |
sc | -0.013 |
tant | -0.013 |
baths | -0.012 |
tests | -0.012 |
videos | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
ich | +0.150 |
opsy | +0.135 |
field | +0.128 |
ster | +0.123 |
sters | +0.115 |
Neg logit contributions | |
sc | -0.090 |
tant | -0.089 |
baths | -0.087 |
videos | -0.084 |
tests | -0.083 |
Token | She |
Token ID | 1375 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.003 |
field | +0.003 |
ster | +0.003 |
sters | +0.003 |
Neg logit contributions | |
sc | -0.001 |
tant | -0.001 |
baths | -0.001 |
videos | -0.001 |
tests | -0.001 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ich | +0.030 |
opsy | +0.025 |
field | +0.024 |
sters | +0.023 |
ese | +0.023 |
Neg logit contributions | |
baths | -0.015 |
Lily | -0.015 |
around | -0.014 |
sc | -0.014 |
bang | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
ich | +0.024 |
opsy | +0.021 |
field | +0.020 |
ster | +0.020 |
sters | +0.018 |
Neg logit contributions | |
sc | -0.014 |
tant | -0.014 |
bang | -0.012 |
videos | -0.012 |
baths | -0.012 |
Token | being |
Token ID | 852 |
Feature activation | -6.82e-04 |
Pos logit contributions | |
ich | +0.006 |
opsy | +0.006 |
field | +0.005 |
ster | +0.005 |
flower | +0.005 |
Neg logit contributions | |
tant | -0.005 |
sc | -0.005 |
igsaw | -0.005 |
aled | -0.005 |
bang | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
sc | +0.003 |
baths | +0.003 |
tant | +0.003 |
tests | +0.003 |
igators | +0.003 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.004 |
field | -0.004 |
ster | -0.003 |
� | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -7.07e-04 |
Pos logit contributions | |
sc | +0.010 |
tant | +0.010 |
baths | +0.009 |
videos | +0.009 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.019 |
opsy | -0.017 |
field | -0.017 |
ster | -0.016 |
flower | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
sc | +0.001 |
tant | +0.001 |
baths | +0.001 |
videos | +0.001 |
tests | +0.001 |
Neg logit contributions | |
ich | -0.001 |
opsy | -0.001 |
field | -0.001 |
ster | -0.001 |
flower | -0.001 |
Token | What |
Token ID | 2061 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
ich | +0.038 |
opsy | +0.034 |
field | +0.032 |
ster | +0.031 |
sters | +0.028 |
Neg logit contributions | |
sc | -0.029 |
tant | -0.029 |
baths | -0.028 |
videos | -0.027 |
tests | -0.027 |
Token | are |
Token ID | 389 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ich | +0.078 |
opsy | +0.071 |
field | +0.069 |
ster | +0.064 |
flower | +0.061 |
Neg logit contributions | |
videos | -0.038 |
baths | -0.037 |
sc | -0.037 |
tests | -0.037 |
tant | -0.036 |
Token | peanuts |
Token ID | 45612 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
ich | +0.059 |
opsy | +0.054 |
field | +0.051 |
ster | +0.049 |
flower | +0.048 |
Neg logit contributions | |
baths | -0.030 |
sc | -0.030 |
videos | -0.028 |
tests | -0.028 |
tant | -0.027 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.86e-03 |
Pos logit contributions | |
ich | +0.117 |
opsy | +0.102 |
field | +0.095 |
ster | +0.090 |
flower | +0.082 |
Neg logit contributions | |
sc | -0.122 |
tant | -0.121 |
baths | -0.120 |
videos | -0.116 |
tests | -0.116 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
sc | +0.006 |
baths | +0.006 |
tant | +0.006 |
igators | +0.005 |
nob | +0.005 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.007 |
field | -0.006 |
wife | -0.006 |
� | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
tant | +0.003 |
baths | +0.003 |
sc | +0.003 |
videos | +0.003 |
tests | +0.003 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
field | -0.007 |
ster | -0.007 |
flower | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
sc | +0.015 |
tant | +0.015 |
baths | +0.014 |
videos | +0.013 |
tests | +0.013 |
Neg logit contributions | |
ich | -0.022 |
opsy | -0.020 |
field | -0.019 |
ster | -0.018 |
sters | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -7.86e-03 |
Pos logit contributions | |
sc | +0.019 |
tant | +0.018 |
baths | +0.018 |
igators | +0.018 |
videos | +0.017 |
Neg logit contributions | |
ich | -0.024 |
opsy | -0.020 |
field | -0.019 |
� | -0.019 |
ster | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
ich | +0.026 |
opsy | +0.023 |
field | +0.022 |
ster | +0.021 |
sters | +0.020 |
Neg logit contributions | |
tant | -0.014 |
sc | -0.014 |
baths | -0.013 |
videos | -0.013 |
tests | -0.013 |
Token | get |
Token ID | 651 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
tant | +0.006 |
sc | +0.006 |
videos | +0.006 |
baths | +0.006 |
tests | +0.006 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.008 |
ster | -0.007 |
pper | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
ich | +0.035 |
opsy | +0.032 |
field | +0.029 |
wife | +0.029 |
ster | +0.028 |
Neg logit contributions | |
sc | -0.026 |
tant | -0.025 |
igsaw | -0.025 |
aids | -0.023 |
bang | -0.023 |
Token | pet |
Token ID | 4273 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
ich | +0.004 |
opsy | +0.003 |
field | +0.003 |
ster | +0.003 |
sters | +0.003 |
Neg logit contributions | |
tant | -0.004 |
baths | -0.004 |
sc | -0.004 |
tests | -0.003 |
videos | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ich | +0.121 |
opsy | +0.108 |
field | +0.103 |
ster | +0.099 |
sters | +0.092 |
Neg logit contributions | |
tant | -0.081 |
sc | -0.081 |
baths | -0.079 |
videos | -0.076 |
tests | -0.075 |
Token | leash |
Token ID | 40529 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
tant | +0.031 |
sc | +0.031 |
baths | +0.030 |
videos | +0.029 |
tests | +0.029 |
Neg logit contributions | |
ich | -0.032 |
opsy | -0.028 |
field | -0.027 |
ster | -0.025 |
flower | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-03 |
Pos logit contributions | |
ich | +0.141 |
opsy | +0.123 |
field | +0.121 |
ster | +0.116 |
flower | +0.106 |
Neg logit contributions | |
tant | -0.100 |
baths | -0.097 |
sc | -0.095 |
tests | -0.093 |
videos | -0.093 |
Token | It |
Token ID | 632 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
tant | +0.003 |
sc | +0.003 |
baths | +0.003 |
videos | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.007 |
field | -0.007 |
ster | -0.006 |
� | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -8.07e-03 |
Pos logit contributions | |
igsaw | +0.038 |
videos | +0.037 |
tant | +0.037 |
baths | +0.036 |
tests | +0.035 |
Neg logit contributions | |
ich | -0.026 |
field | -0.023 |
opsy | -0.023 |
flower | -0.021 |
ster | -0.020 |
Token | purple |
Token ID | 14032 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
sc | +0.012 |
tant | +0.012 |
igsaw | +0.012 |
and | +0.011 |
head | +0.011 |
Neg logit contributions | |
ich | -0.015 |
opsy | -0.013 |
field | -0.013 |
pper | -0.011 |
remembered | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
tant | +0.025 |
sc | +0.024 |
aids | +0.023 |
videos | +0.023 |
tests | +0.023 |
Neg logit contributions | |
ich | -0.024 |
opsy | -0.020 |
ster | -0.019 |
field | -0.019 |
flower | -0.018 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.002 |
field | +0.002 |
ster | +0.002 |
flower | +0.002 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
baths | -0.001 |
videos | -0.001 |
tests | -0.001 |
Token | L |
Token ID | 43 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
ich | +0.002 |
opsy | +0.002 |
field | +0.001 |
ster | +0.001 |
sters | +0.001 |
Neg logit contributions | |
sc | -0.002 |
tant | -0.002 |
baths | -0.002 |
videos | -0.002 |
tests | -0.002 |
Token | ily |
Token ID | 813 |
Feature activation | +7.52e-03 |
Pos logit contributions | |
tant | +0.058 |
sc | +0.058 |
baths | +0.057 |
videos | +0.056 |
tests | +0.055 |
Neg logit contributions | |
ich | -0.127 |
opsy | -0.112 |
field | -0.112 |
ster | -0.103 |
flower | -0.100 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.015 |
field | +0.014 |
ster | +0.013 |
sters | +0.012 |
Neg logit contributions | |
tant | -0.010 |
sc | -0.010 |
baths | -0.010 |
videos | -0.010 |
tests | -0.010 |
Token | pe |
Token ID | 613 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
ich | +0.005 |
opsy | +0.005 |
field | +0.005 |
ster | +0.004 |
sters | +0.004 |
Neg logit contributions | |
sc | -0.003 |
tant | -0.003 |
taker | -0.003 |
aids | -0.003 |
tests | -0.003 |
Token | aches |
Token ID | 3694 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
ich | +0.036 |
opsy | +0.031 |
field | +0.030 |
ster | +0.027 |
flower | +0.025 |
Neg logit contributions | |
tant | -0.044 |
baths | -0.043 |
sc | -0.043 |
tests | -0.042 |
videos | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +6.84e-03 |
Pos logit contributions | |
ich | +0.163 |
opsy | +0.146 |
field | +0.139 |
ster | +0.134 |
sters | +0.126 |
Neg logit contributions | |
tant | -0.075 |
sc | -0.075 |
baths | -0.074 |
videos | -0.070 |
around | -0.068 |
Token | She |
Token ID | 1375 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
opsy | +0.012 |
ich | +0.012 |
flower | +0.012 |
� | +0.012 |
field | +0.011 |
Neg logit contributions | |
tant | -0.010 |
sc | -0.009 |
tests | -0.009 |
crashes | -0.009 |
bang | -0.009 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
ich | +0.033 |
opsy | +0.028 |
field | +0.027 |
ster | +0.026 |
sters | +0.025 |
Neg logit contributions | |
sc | -0.019 |
baths | -0.019 |
tant | -0.018 |
tests | -0.018 |
bang | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
sc | +0.003 |
tant | +0.003 |
baths | +0.002 |
videos | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.005 |
opsy | -0.005 |
field | -0.005 |
ster | -0.004 |
sters | -0.004 |
Token | eat |
Token ID | 4483 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ich | +0.033 |
opsy | +0.031 |
field | +0.030 |
ster | +0.028 |
flower | +0.027 |
Neg logit contributions | |
sc | -0.026 |
tant | -0.026 |
baths | -0.024 |
videos | -0.023 |
tests | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
ich | +0.008 |
opsy | +0.007 |
field | +0.007 |
ster | +0.007 |
flower | +0.006 |
Neg logit contributions | |
tant | -0.007 |
sc | -0.007 |
baths | -0.007 |
videos | -0.007 |
tests | -0.007 |
Token | relieved |
Token ID | 22598 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
sc | +0.015 |
tant | +0.014 |
baths | +0.013 |
videos | +0.013 |
igsaw | +0.013 |
Neg logit contributions | |
ich | -0.020 |
opsy | -0.018 |
field | -0.017 |
ster | -0.016 |
husband | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
ich | +0.025 |
opsy | +0.022 |
field | +0.021 |
ster | +0.021 |
� | +0.018 |
Neg logit contributions | |
tant | -0.021 |
sc | -0.021 |
igators | -0.020 |
baths | -0.020 |
videos | -0.020 |
Token | she |
Token ID | 673 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
tant | +0.010 |
sc | +0.010 |
baths | +0.009 |
videos | +0.009 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.008 |
ster | -0.007 |
� | -0.007 |
Token | filled |
Token ID | 5901 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
ich | +0.032 |
opsy | +0.028 |
field | +0.026 |
ster | +0.025 |
sters | +0.024 |
Neg logit contributions | |
sc | -0.020 |
tant | -0.020 |
baths | -0.020 |
bang | -0.019 |
tests | -0.019 |
Token | Fl |
Token ID | 1610 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
tant | +0.037 |
sc | +0.037 |
igators | +0.035 |
igsaw | +0.035 |
riend | +0.034 |
Neg logit contributions | |
ich | -0.055 |
opsy | -0.052 |
field | -0.048 |
ster | -0.046 |
illa | -0.046 |
Token | uffy |
Token ID | 15352 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
ich | +0.097 |
field | +0.084 |
opsy | +0.080 |
ster | +0.077 |
sters | +0.069 |
Neg logit contributions | |
tant | -0.131 |
baths | -0.129 |
sc | -0.129 |
tests | -0.125 |
videos | -0.121 |
Token | 's |
Token ID | 338 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
ich | +0.054 |
opsy | +0.050 |
field | +0.047 |
ster | +0.047 |
sters | +0.042 |
Neg logit contributions | |
tant | -0.043 |
sc | -0.042 |
igators | -0.041 |
videos | -0.040 |
tests | -0.039 |
Token | bowl |
Token ID | 9396 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
sc | +0.008 |
tant | +0.007 |
igators | +0.007 |
tests | +0.007 |
videos | +0.007 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
field | -0.007 |
ster | -0.007 |
� | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
ich | +0.035 |
opsy | +0.033 |
ster | +0.031 |
field | +0.031 |
flower | +0.029 |
Neg logit contributions | |
videos | -0.021 |
tant | -0.021 |
tests | -0.021 |
bang | -0.021 |
sc | -0.021 |
Token | medicine |
Token ID | 9007 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
sc | +0.001 |
igsaw | +0.001 |
igators | +0.001 |
videos | +0.001 |
tant | +0.001 |
Neg logit contributions | |
opsy | -0.002 |
ich | -0.002 |
field | -0.002 |
ster | -0.002 |
wife | -0.002 |
Token | watched |
Token ID | 7342 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
sc | +0.005 |
tant | +0.005 |
baths | +0.005 |
tests | +0.005 |
videos | +0.005 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.008 |
ster | -0.007 |
sters | -0.007 |
Token | as |
Token ID | 355 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
sc | +0.015 |
tant | +0.014 |
igators | +0.013 |
riend | +0.013 |
bench | +0.013 |
Neg logit contributions | |
ich | -0.015 |
opsy | -0.014 |
ble | -0.013 |
ster | -0.012 |
field | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
ich | +0.046 |
opsy | +0.042 |
field | +0.038 |
ster | +0.037 |
flower | +0.035 |
Neg logit contributions | |
sc | -0.025 |
tant | -0.022 |
baths | -0.020 |
aids | -0.019 |
tests | -0.019 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.56e-03 |
Pos logit contributions | |
sc | +0.036 |
tant | +0.035 |
baths | +0.034 |
videos | +0.033 |
tests | +0.033 |
Neg logit contributions | |
ich | -0.029 |
opsy | -0.025 |
field | -0.022 |
ster | -0.022 |
flower | -0.020 |
Token | carefully |
Token ID | 7773 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
tant | +0.012 |
sc | +0.012 |
baths | +0.011 |
videos | +0.011 |
tests | +0.011 |
Neg logit contributions | |
ich | -0.022 |
opsy | -0.020 |
field | -0.019 |
ster | -0.018 |
sters | -0.017 |
Token | se |
Token ID | 384 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
tant | +0.039 |
igators | +0.038 |
sc | +0.038 |
baths | +0.038 |
videos | +0.038 |
Neg logit contributions | |
ich | -0.050 |
opsy | -0.046 |
field | -0.043 |
ster | -0.043 |
flower | -0.039 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
baths | +0.196 |
videos | +0.189 |
tests | +0.188 |
sc | +0.188 |
TV | +0.183 |
Neg logit contributions | |
ich | -0.162 |
opsy | -0.154 |
ese | -0.135 |
pper | -0.135 |
ster | -0.132 |
Token | Ted |
Token ID | 11396 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ich | +0.031 |
opsy | +0.031 |
ster | +0.027 |
flower | +0.026 |
ble | +0.026 |
Neg logit contributions | |
aids | -0.033 |
villains | -0.032 |
igators | -0.030 |
riend | -0.030 |
Lots | -0.029 |
Token | 's |
Token ID | 338 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
videos | +0.034 |
igators | +0.034 |
tant | +0.034 |
iren | +0.032 |
showers | +0.032 |
Neg logit contributions | |
ich | -0.027 |
ster | -0.025 |
opsy | -0.025 |
field | -0.023 |
flower | -0.023 |
Token | arm |
Token ID | 3211 |
Feature activation | -9.74e-03 |
Pos logit contributions | |
igators | +0.029 |
sc | +0.029 |
videos | +0.028 |
tant | +0.028 |
baths | +0.028 |
Neg logit contributions | |
ich | -0.044 |
opsy | -0.040 |
ster | -0.037 |
field | -0.037 |
flower | -0.034 |
Token | back |
Token ID | 736 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
igators | +0.022 |
aids | +0.020 |
igator | +0.020 |
videos | +0.019 |
villains | +0.019 |
Neg logit contributions | |
ich | -0.009 |
ster | -0.008 |
field | -0.007 |
flower | -0.007 |
opsy | -0.007 |
Token | Joe |
Token ID | 5689 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
sc | +0.014 |
tant | +0.014 |
tests | +0.014 |
igators | +0.013 |
baths | +0.013 |
Neg logit contributions | |
ich | -0.021 |
opsy | -0.020 |
ster | -0.018 |
field | -0.018 |
� | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
tant | +0.020 |
sc | +0.020 |
baths | +0.019 |
videos | +0.019 |
tests | +0.019 |
Neg logit contributions | |
ich | -0.027 |
opsy | -0.024 |
field | -0.023 |
ster | -0.023 |
flower | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
tant | +0.007 |
sc | +0.007 |
baths | +0.007 |
tests | +0.007 |
videos | +0.007 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.010 |
ster | -0.009 |
flower | -0.009 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
sc | +0.020 |
baths | +0.020 |
tant | +0.019 |
videos | +0.019 |
tests | +0.019 |
Neg logit contributions | |
ich | -0.035 |
opsy | -0.031 |
field | -0.030 |
ster | -0.029 |
� | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
baths | +0.097 |
sc | +0.095 |
videos | +0.094 |
tests | +0.090 |
igsaw | +0.088 |
Neg logit contributions | |
ich | -0.135 |
opsy | -0.120 |
ster | -0.113 |
field | -0.113 |
ese | -0.107 |
Token | year |
Token ID | 1941 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
baths | +0.117 |
videos | +0.112 |
TV | +0.101 |
tant | +0.100 |
tests | +0.099 |
Neg logit contributions | |
ich | -0.191 |
opsy | -0.167 |
illa | -0.159 |
ster | -0.158 |
pper | -0.154 |
Token | - |
Token ID | 12 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
sc | +0.193 |
videos | +0.188 |
baths | +0.181 |
Math | +0.178 |
Emma | +0.176 |
Neg logit contributions | |
ich | -0.186 |
ster | -0.159 |
opsy | -0.158 |
field | -0.143 |
wife | -0.141 |
Token | old |
Token ID | 727 |
Feature activation | -9.08e-03 |
Pos logit contributions | |
baths | +0.117 |
videos | +0.113 |
tant | +0.113 |
bang | +0.106 |
TV | +0.105 |
Neg logit contributions | |
ich | -0.151 |
opsy | -0.128 |
ster | -0.122 |
illa | -0.120 |
field | -0.118 |
Token | boy |
Token ID | 2933 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
tant | +0.017 |
sc | +0.017 |
baths | +0.017 |
videos | +0.016 |
tests | +0.016 |
Neg logit contributions | |
ich | -0.015 |
opsy | -0.013 |
ster | -0.012 |
field | -0.012 |
flower | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
tant | +0.016 |
sc | +0.015 |
baths | +0.015 |
videos | +0.015 |
tests | +0.014 |
Neg logit contributions | |
ich | -0.020 |
opsy | -0.017 |
field | -0.017 |
ster | -0.016 |
flower | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
tant | +0.013 |
sc | +0.013 |
baths | +0.013 |
videos | +0.012 |
tests | +0.012 |
Neg logit contributions | |
ich | -0.025 |
opsy | -0.022 |
field | -0.021 |
ster | -0.020 |
flower | -0.019 |
Token | twenty |
Token ID | 8208 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
sc | +0.025 |
tant | +0.023 |
baths | +0.022 |
videos | +0.021 |
tests | +0.020 |
Neg logit contributions | |
ich | -0.040 |
opsy | -0.037 |
field | -0.035 |
ster | -0.033 |
� | -0.033 |
Token | - |
Token ID | 12 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
tant | +0.082 |
sc | +0.081 |
baths | +0.079 |
tests | +0.077 |
videos | +0.076 |
Neg logit contributions | |
ich | -0.117 |
opsy | -0.103 |
field | -0.099 |
ster | -0.094 |
flower | -0.087 |
Token | eight |
Token ID | 26022 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
baths | +0.155 |
videos | +0.146 |
sc | +0.145 |
tant | +0.143 |
showers | +0.136 |
Neg logit contributions | |
ich | -0.207 |
opsy | -0.182 |
illa | -0.171 |
field | -0.165 |
ster | -0.164 |
Token | , |
Token ID | 11 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
tant | +0.030 |
sc | +0.030 |
baths | +0.029 |
videos | +0.028 |
tests | +0.027 |
Neg logit contributions | |
ich | -0.050 |
opsy | -0.045 |
field | -0.043 |
ster | -0.041 |
sters | -0.039 |
Token | twenty |
Token ID | 8208 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
sc | +0.039 |
tant | +0.036 |
baths | +0.035 |
videos | +0.032 |
igators | +0.032 |
Neg logit contributions | |
ich | -0.061 |
opsy | -0.056 |
field | -0.053 |
ster | -0.051 |
� | -0.050 |
Token | - |
Token ID | 12 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
sc | +0.084 |
baths | +0.083 |
tant | +0.083 |
videos | +0.080 |
tests | +0.075 |
Neg logit contributions | |
ich | -0.123 |
opsy | -0.111 |
field | -0.104 |
ster | -0.101 |
sters | -0.094 |
Token | nine |
Token ID | 30888 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
baths | +0.175 |
videos | +0.167 |
tant | +0.163 |
sc | +0.163 |
showers | +0.155 |
Neg logit contributions | |
ich | -0.194 |
opsy | -0.169 |
illa | -0.161 |
field | -0.153 |
ster | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
tant | +0.053 |
sc | +0.052 |
baths | +0.051 |
videos | +0.049 |
tests | +0.049 |
Neg logit contributions | |
ich | -0.087 |
opsy | -0.079 |
field | -0.075 |
ster | -0.072 |
sters | -0.067 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
sc | +0.045 |
tant | +0.042 |
baths | +0.041 |
videos | +0.037 |
igators | +0.037 |
Neg logit contributions | |
ich | -0.070 |
opsy | -0.063 |
field | -0.060 |
ster | -0.058 |
� | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
sc | +0.069 |
baths | +0.067 |
tant | +0.067 |
videos | +0.065 |
tests | +0.061 |
Neg logit contributions | |
ich | -0.108 |
opsy | -0.098 |
field | -0.092 |
ster | -0.090 |
sters | -0.085 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
sc | +0.048 |
tant | +0.045 |
baths | +0.044 |
igators | +0.040 |
videos | +0.040 |
Neg logit contributions | |
ich | -0.075 |
opsy | -0.067 |
field | -0.064 |
ster | -0.062 |
� | -0.061 |
Token | nine |
Token ID | 30888 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
baths | +0.175 |
videos | +0.167 |
tant | +0.163 |
sc | +0.163 |
showers | +0.155 |
Neg logit contributions | |
ich | -0.194 |
opsy | -0.169 |
illa | -0.161 |
field | -0.153 |
ster | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
tant | +0.053 |
sc | +0.052 |
baths | +0.051 |
videos | +0.049 |
tests | +0.049 |
Neg logit contributions | |
ich | -0.087 |
opsy | -0.079 |
field | -0.075 |
ster | -0.072 |
sters | -0.067 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
sc | +0.045 |
tant | +0.042 |
baths | +0.041 |
videos | +0.037 |
igators | +0.037 |
Neg logit contributions | |
ich | -0.070 |
opsy | -0.063 |
field | -0.060 |
ster | -0.058 |
� | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
sc | +0.069 |
baths | +0.067 |
tant | +0.067 |
videos | +0.065 |
tests | +0.061 |
Neg logit contributions | |
ich | -0.108 |
opsy | -0.098 |
field | -0.092 |
ster | -0.090 |
sters | -0.085 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
sc | +0.048 |
tant | +0.045 |
baths | +0.044 |
igators | +0.040 |
videos | +0.040 |
Neg logit contributions | |
ich | -0.075 |
opsy | -0.067 |
field | -0.064 |
ster | -0.062 |
� | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
sc | +0.067 |
baths | +0.066 |
tant | +0.066 |
videos | +0.063 |
tests | +0.059 |
Neg logit contributions | |
ich | -0.107 |
opsy | -0.097 |
field | -0.091 |
ster | -0.089 |
sters | -0.084 |
Token | one |
Token ID | 505 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
baths | +0.181 |
videos | +0.173 |
tant | +0.170 |
sc | +0.168 |
showers | +0.161 |
Neg logit contributions | |
ich | -0.182 |
opsy | -0.156 |
illa | -0.149 |
field | -0.144 |
pper | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
sc | +0.053 |
baths | +0.052 |
tant | +0.051 |
videos | +0.050 |
showers | +0.047 |
Neg logit contributions | |
ich | -0.059 |
opsy | -0.052 |
field | -0.050 |
ster | -0.048 |
flower | -0.044 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
sc | +0.050 |
tant | +0.047 |
baths | +0.045 |
igators | +0.041 |
videos | +0.041 |
Neg logit contributions | |
ich | -0.077 |
opsy | -0.069 |
field | -0.065 |
ster | -0.064 |
� | -0.063 |
Token | - |
Token ID | 12 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
sc | +0.064 |
baths | +0.063 |
tant | +0.063 |
videos | +0.060 |
tests | +0.057 |
Neg logit contributions | |
ich | -0.106 |
opsy | -0.096 |
field | -0.091 |
ster | -0.089 |
sters | -0.083 |
Token | two |
Token ID | 11545 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
baths | +0.173 |
videos | +0.167 |
tant | +0.165 |
sc | +0.162 |
showers | +0.155 |
Neg logit contributions | |
ich | -0.180 |
opsy | -0.153 |
illa | -0.146 |
field | -0.142 |
pper | -0.136 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
baths | +0.033 |
sc | +0.033 |
tant | +0.032 |
videos | +0.032 |
tests | +0.031 |
Neg logit contributions | |
ich | -0.060 |
opsy | -0.054 |
field | -0.051 |
ster | -0.048 |
iri | -0.046 |
Token | shouted |
Token ID | 17293 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.006 |
field | +0.006 |
ster | +0.006 |
sters | +0.005 |
Neg logit contributions | |
sc | -0.007 |
tant | -0.007 |
baths | -0.006 |
tests | -0.006 |
videos | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
sc | +0.014 |
tant | +0.013 |
igators | +0.012 |
videos | +0.012 |
tests | +0.012 |
Neg logit contributions | |
ich | -0.017 |
opsy | -0.016 |
field | -0.014 |
ster | -0.014 |
flower | -0.013 |
Token | three |
Token ID | 1115 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
tant | +0.025 |
sc | +0.025 |
baths | +0.025 |
videos | +0.024 |
tests | +0.024 |
Neg logit contributions | |
ich | -0.025 |
opsy | -0.022 |
field | -0.021 |
ster | -0.020 |
sters | -0.018 |
Token | - |
Token ID | 12 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
sc | +0.094 |
baths | +0.085 |
videos | +0.082 |
tant | +0.082 |
tests | +0.082 |
Neg logit contributions | |
ich | -0.126 |
opsy | -0.118 |
ster | -0.108 |
field | -0.104 |
sters | -0.101 |
Token | year |
Token ID | 1941 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
baths | +0.098 |
videos | +0.098 |
tant | +0.093 |
TV | +0.087 |
bang | +0.087 |
Neg logit contributions | |
ich | -0.190 |
opsy | -0.176 |
illa | -0.165 |
ster | -0.165 |
field | -0.157 |
Token | - |
Token ID | 12 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
sc | +0.186 |
videos | +0.166 |
bang | +0.166 |
baths | +0.164 |
tests | +0.160 |
Neg logit contributions | |
ich | -0.193 |
opsy | -0.175 |
ster | -0.171 |
ama | -0.154 |
field | -0.153 |
Token | old |
Token ID | 727 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
tant | +0.104 |
videos | +0.102 |
baths | +0.102 |
sc | +0.101 |
bang | +0.100 |
Neg logit contributions | |
ich | -0.148 |
opsy | -0.136 |
ster | -0.128 |
illa | -0.123 |
field | -0.120 |
Token | son |
Token ID | 3367 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
sc | +0.020 |
tant | +0.020 |
baths | +0.019 |
tests | +0.019 |
videos | +0.019 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.009 |
ster | -0.009 |
field | -0.008 |
flower | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
tant | +0.014 |
sc | +0.014 |
baths | +0.013 |
tests | +0.013 |
videos | +0.012 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.014 |
ster | -0.013 |
field | -0.013 |
flower | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | +9.74e-03 |
Pos logit contributions | |
sc | +0.004 |
tant | +0.004 |
baths | +0.004 |
videos | +0.003 |
tests | +0.003 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.005 |
field | -0.005 |
ster | -0.004 |
flower | -0.004 |
Token | watched |
Token ID | 7342 |
Feature activation | -8.52e-03 |
Pos logit contributions | |
tant | +0.021 |
sc | +0.021 |
baths | +0.021 |
tests | +0.020 |
videos | +0.020 |
Neg logit contributions | |
ich | -0.031 |
opsy | -0.028 |
field | -0.026 |
ster | -0.025 |
sters | -0.023 |
Token | as |
Token ID | 355 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
sc | +0.018 |
igators | +0.017 |
tant | +0.015 |
bench | +0.015 |
| | +0.015 |
Neg logit contributions | |
ich | -0.012 |
ble | -0.011 |
opsy | -0.010 |
ster | -0.009 |
icking | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ich | +0.044 |
opsy | +0.041 |
field | +0.037 |
ster | +0.036 |
ble | +0.036 |
Neg logit contributions | |
sc | -0.025 |
tant | -0.021 |
baths | -0.020 |
channel | -0.019 |
igators | -0.019 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
sc | +0.027 |
tant | +0.025 |
igators | +0.025 |
baths | +0.024 |
videos | +0.024 |
Neg logit contributions | |
ich | -0.020 |
opsy | -0.017 |
ster | -0.015 |
field | -0.015 |
flower | -0.013 |
Token | carefully |
Token ID | 7773 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
tant | +0.019 |
sc | +0.018 |
baths | +0.018 |
videos | +0.017 |
tests | +0.017 |
Neg logit contributions | |
ich | -0.025 |
opsy | -0.022 |
field | -0.021 |
ster | -0.020 |
flower | -0.019 |
Token | se |
Token ID | 384 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
igators | +0.043 |
videos | +0.041 |
tant | +0.041 |
sc | +0.040 |
igsaw | +0.039 |
Neg logit contributions | |
ich | -0.042 |
opsy | -0.040 |
field | -0.039 |
ster | -0.037 |
flower | -0.034 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
baths | +0.189 |
videos | +0.182 |
TV | +0.179 |
tests | +0.179 |
sc | +0.177 |
Neg logit contributions | |
ich | -0.153 |
opsy | -0.148 |
ese | -0.137 |
pper | -0.133 |
ige | -0.127 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
ich | +0.027 |
opsy | +0.026 |
ble | +0.024 |
ster | +0.024 |
flower | +0.023 |
Neg logit contributions | |
aids | -0.028 |
villains | -0.028 |
igators | -0.027 |
Lots | -0.026 |
videos | -0.025 |
Token | stitch |
Token ID | 24695 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
sc | +0.005 |
videos | +0.005 |
aids | +0.005 |
igators | +0.005 |
tant | +0.005 |
Neg logit contributions | |
ich | -0.006 |
ster | -0.005 |
opsy | -0.005 |
field | -0.005 |
sters | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +9.87e-04 |
Pos logit contributions | |
Many | +0.022 |
tant | +0.022 |
aids | +0.022 |
videos | +0.022 |
tests | +0.021 |
Neg logit contributions | |
ich | -0.021 |
field | -0.019 |
ster | -0.019 |
opsy | -0.018 |
flower | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ich | +0.002 |
field | +0.002 |
opsy | +0.002 |
flower | +0.002 |
ster | +0.002 |
Neg logit contributions | |
sc | -0.001 |
igators | -0.001 |
baths | -0.001 |
tests | -0.001 |
videos | -0.001 |
Token | place |
Token ID | 1295 |
Feature activation | -6.93e-03 |
Pos logit contributions | |
ich | +0.045 |
opsy | +0.039 |
ster | +0.038 |
field | +0.036 |
flower | +0.034 |
Neg logit contributions | |
sc | -0.033 |
tant | -0.032 |
aled | -0.030 |
baths | -0.029 |
Everywhere | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
tant | +0.012 |
baths | +0.011 |
sc | +0.011 |
videos | +0.011 |
tests | +0.010 |
Neg logit contributions | |
ich | -0.013 |
field | -0.011 |
opsy | -0.011 |
ster | -0.010 |
flower | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
sc | +0.027 |
tant | +0.026 |
taker | +0.021 |
riend | +0.021 |
bench | +0.021 |
Neg logit contributions | |
ich | -0.035 |
opsy | -0.032 |
field | -0.030 |
ster | -0.028 |
sters | -0.027 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
aled | +0.040 |
sc | +0.038 |
videos | +0.038 |
tant | +0.037 |
igators | +0.036 |
Neg logit contributions | |
ich | -0.071 |
opsy | -0.064 |
field | -0.061 |
ster | -0.059 |
wife | -0.054 |
Token | - |
Token ID | 12 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
sc | +0.118 |
aled | +0.117 |
Everywhere | +0.116 |
backward | +0.115 |
videos | +0.115 |
Neg logit contributions | |
ich | -0.118 |
opsy | -0.104 |
ster | -0.098 |
ese | -0.095 |
field | -0.091 |
Token | year |
Token ID | 1941 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
baths | +0.119 |
videos | +0.118 |
channel | +0.111 |
TV | +0.110 |
cartoons | +0.109 |
Neg logit contributions | |
ich | -0.168 |
opsy | -0.142 |
ster | -0.139 |
illa | -0.135 |
pper | -0.128 |
Token | - |
Token ID | 12 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
sc | +0.200 |
videos | +0.192 |
Emma | +0.186 |
Math | +0.184 |
| | +0.183 |
Neg logit contributions | |
ich | -0.169 |
ster | -0.145 |
opsy | -0.136 |
field | -0.124 |
ama | -0.123 |
Token | old |
Token ID | 727 |
Feature activation | -9.94e-03 |
Pos logit contributions | |
videos | +0.116 |
baths | +0.113 |
bang | +0.110 |
channel | +0.110 |
tant | +0.109 |
Neg logit contributions | |
ich | -0.134 |
opsy | -0.111 |
ster | -0.108 |
illa | -0.104 |
ese | -0.100 |
Token | to |
Token ID | 284 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
tant | +0.017 |
sc | +0.016 |
baths | +0.016 |
videos | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.018 |
opsy | -0.015 |
ster | -0.015 |
field | -0.015 |
flower | -0.013 |
Token | be |
Token ID | 307 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.007 |
field | +0.007 |
ster | +0.006 |
pper | +0.005 |
Neg logit contributions | |
sc | -0.006 |
tant | -0.006 |
videos | -0.005 |
baths | -0.005 |
taker | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ich | +0.046 |
opsy | +0.040 |
field | +0.038 |
ster | +0.037 |
ese | +0.036 |
Neg logit contributions | |
sc | -0.034 |
tant | -0.033 |
videos | -0.031 |
baths | -0.031 |
igsaw | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
outage | +0.023 |
bench | +0.022 |
riend | +0.022 |
villains | +0.022 |
gru | +0.022 |
Neg logit contributions | |
opsy | -0.016 |
husband | -0.014 |
ich | -0.013 |
daughter | -0.013 |
ige | -0.013 |
Token | t |
Token ID | 256 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
sc | +0.024 |
videos | +0.024 |
aids | +0.023 |
tests | +0.023 |
igators | +0.023 |
Neg logit contributions | |
ich | -0.037 |
opsy | -0.032 |
ster | -0.031 |
field | -0.030 |
flower | -0.029 |
Token | eddy |
Token ID | 21874 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
tant | +0.014 |
sc | +0.014 |
baths | +0.013 |
videos | +0.013 |
tests | +0.013 |
Neg logit contributions | |
ich | -0.017 |
opsy | -0.015 |
field | -0.015 |
ster | -0.014 |
sters | -0.013 |
Token | bear |
Token ID | 6842 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
tant | +0.026 |
sc | +0.025 |
baths | +0.025 |
videos | +0.024 |
tests | +0.024 |
Neg logit contributions | |
ich | -0.046 |
opsy | -0.042 |
field | -0.040 |
ster | -0.038 |
sters | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -7.97e-03 |
Pos logit contributions | |
tant | +0.007 |
sc | +0.006 |
baths | +0.006 |
tests | +0.006 |
videos | +0.006 |
Neg logit contributions | |
ich | -0.010 |
opsy | -0.009 |
ster | -0.009 |
field | -0.009 |
flower | -0.008 |
Token | se |
Token ID | 384 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
tant | +0.012 |
sc | +0.012 |
baths | +0.011 |
aids | +0.011 |
tests | +0.011 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.015 |
field | -0.014 |
ster | -0.014 |
sters | -0.012 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
baths | +0.196 |
tests | +0.192 |
videos | +0.189 |
sc | +0.189 |
TV | +0.183 |
Neg logit contributions | |
ich | -0.146 |
opsy | -0.138 |
ese | -0.119 |
ster | -0.117 |
pper | -0.115 |
Token | up |
Token ID | 510 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ich | +0.024 |
opsy | +0.022 |
ster | +0.019 |
ble | +0.018 |
field | +0.018 |
Neg logit contributions | |
aids | -0.030 |
igators | -0.030 |
riend | -0.028 |
villains | -0.028 |
videos | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
ich | +0.026 |
opsy | +0.026 |
field | +0.022 |
ster | +0.022 |
husband | +0.021 |
Neg logit contributions | |
sc | -0.029 |
igators | -0.027 |
bench | -0.027 |
riend | -0.026 |
igator | -0.026 |
Token | hole |
Token ID | 7604 |
Feature activation | -3.68e-03 |
Pos logit contributions | |
sc | +0.005 |
videos | +0.005 |
tant | +0.005 |
tests | +0.004 |
baths | +0.004 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.007 |
ster | -0.007 |
flower | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +8.76e-03 |
Pos logit contributions | |
baths | +0.007 |
tant | +0.007 |
tests | +0.007 |
bang | +0.007 |
showers | +0.007 |
Neg logit contributions | |
ich | -0.005 |
ster | -0.005 |
field | -0.005 |
opsy | -0.005 |
flower | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
sc | +0.047 |
tant | +0.043 |
channels | +0.037 |
videos | +0.036 |
igators | +0.035 |
Neg logit contributions | |
ich | -0.086 |
opsy | -0.082 |
field | -0.077 |
ster | -0.073 |
illa | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | -7.52e-03 |
Pos logit contributions | |
sc | +0.033 |
tant | +0.029 |
tests | +0.027 |
igators | +0.027 |
baths | +0.026 |
Neg logit contributions | |
ich | -0.035 |
� | -0.031 |
opsy | -0.031 |
ster | -0.030 |
flower | -0.029 |
Token | young |
Token ID | 1862 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
sc | +0.012 |
aled | +0.012 |
igators | +0.011 |
baths | +0.011 |
tant | +0.011 |
Neg logit contributions | |
ich | -0.015 |
opsy | -0.013 |
ster | -0.013 |
field | -0.013 |
� | -0.012 |
Token | three |
Token ID | 1115 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
sc | +0.034 |
tant | +0.033 |
baths | +0.032 |
tests | +0.032 |
aled | +0.032 |
Neg logit contributions | |
ich | -0.027 |
opsy | -0.023 |
ster | -0.022 |
field | -0.021 |
flower | -0.019 |
Token | - |
Token ID | 12 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
sc | +0.083 |
baths | +0.077 |
aled | +0.074 |
tests | +0.073 |
videos | +0.073 |
Neg logit contributions | |
ich | -0.107 |
opsy | -0.096 |
ster | -0.091 |
field | -0.086 |
� | -0.083 |
Token | year |
Token ID | 1941 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
baths | +0.107 |
videos | +0.095 |
showers | +0.092 |
tant | +0.091 |
TV | +0.089 |
Neg logit contributions | |
ich | -0.172 |
illa | -0.147 |
opsy | -0.146 |
ster | -0.144 |
flower | -0.134 |
Token | - |
Token ID | 12 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
sc | +0.186 |
baths | +0.167 |
videos | +0.166 |
bang | +0.164 |
Chloe | +0.159 |
Neg logit contributions | |
ich | -0.192 |
ster | -0.165 |
opsy | -0.165 |
wife | -0.146 |
field | -0.145 |
Token | old |
Token ID | 727 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
baths | +0.113 |
tant | +0.107 |
videos | +0.105 |
bang | +0.104 |
showers | +0.102 |
Neg logit contributions | |
ich | -0.137 |
opsy | -0.114 |
ster | -0.111 |
illa | -0.111 |
field | -0.104 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
sc | +0.010 |
tant | +0.010 |
baths | +0.010 |
tests | +0.010 |
videos | +0.010 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
ster | -0.007 |
field | -0.007 |
flower | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -8.16e-03 |
Pos logit contributions | |
tant | +0.029 |
sc | +0.028 |
baths | +0.027 |
tests | +0.026 |
videos | +0.026 |
Neg logit contributions | |
ich | -0.036 |
opsy | -0.032 |
field | -0.030 |
ster | -0.029 |
flower | -0.028 |
Token | excitement |
Token ID | 14067 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
sc | +0.017 |
auc | +0.016 |
taker | +0.015 |
igators | +0.015 |
riend | +0.014 |
Neg logit contributions | |
ich | -0.010 |
opsy | -0.010 |
field | -0.009 |
wife | -0.009 |
iya | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-03 |
Pos logit contributions | |
tant | +0.050 |
sc | +0.048 |
videos | +0.045 |
baths | +0.044 |
tests | +0.044 |
Neg logit contributions | |
ich | -0.057 |
opsy | -0.052 |
field | -0.048 |
ster | -0.048 |
� | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
tant | +0.002 |
sc | +0.002 |
baths | +0.001 |
tests | +0.001 |
videos | +0.001 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
flower | -0.003 |
Token | tiny |
Token ID | 7009 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
sc | +0.011 |
tant | +0.011 |
baths | +0.011 |
igators | +0.010 |
tests | +0.010 |
Neg logit contributions | |
ich | -0.019 |
opsy | -0.017 |
field | -0.016 |
ster | -0.016 |
� | -0.015 |
Token | three |
Token ID | 1115 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
sc | +0.050 |
aled | +0.048 |
baths | +0.046 |
tant | +0.046 |
tests | +0.045 |
Neg logit contributions | |
ich | -0.040 |
opsy | -0.037 |
ster | -0.034 |
field | -0.032 |
flower | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
sc | +0.087 |
aled | +0.079 |
backward | +0.079 |
baths | +0.078 |
videos | +0.076 |
Neg logit contributions | |
ich | -0.101 |
opsy | -0.097 |
ster | -0.088 |
sters | -0.082 |
field | -0.082 |
Token | year |
Token ID | 1941 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
baths | +0.117 |
tant | +0.106 |
videos | +0.105 |
showers | +0.100 |
sc | +0.099 |
Neg logit contributions | |
ich | -0.194 |
opsy | -0.169 |
illa | -0.165 |
ster | -0.163 |
flower | -0.156 |
Token | - |
Token ID | 12 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
sc | +0.184 |
videos | +0.166 |
baths | +0.166 |
bang | +0.164 |
tant | +0.163 |
Neg logit contributions | |
ich | -0.194 |
opsy | -0.166 |
ster | -0.165 |
field | -0.152 |
ama | -0.147 |
Token | old |
Token ID | 727 |
Feature activation | -6.41e-03 |
Pos logit contributions | |
tant | +0.113 |
baths | +0.112 |
sc | +0.108 |
videos | +0.106 |
bang | +0.105 |
Neg logit contributions | |
ich | -0.150 |
opsy | -0.128 |
ster | -0.122 |
illa | -0.120 |
field | -0.119 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
tant | +0.011 |
sc | +0.011 |
baths | +0.011 |
videos | +0.011 |
tests | +0.011 |
Neg logit contributions | |
ich | -0.012 |
opsy | -0.010 |
field | -0.009 |
ster | -0.009 |
flower | -0.008 |
Token | came |
Token ID | 1625 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
tant | +0.027 |
sc | +0.025 |
baths | +0.025 |
videos | +0.024 |
tests | +0.024 |
Neg logit contributions | |
ich | -0.032 |
opsy | -0.029 |
field | -0.027 |
ster | -0.026 |
flower | -0.024 |
Token | across |
Token ID | 1973 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
tant | +0.012 |
sc | +0.011 |
baths | +0.011 |
videos | +0.010 |
tests | +0.010 |
Neg logit contributions | |
ich | -0.030 |
opsy | -0.027 |
field | -0.026 |
ster | -0.025 |
flower | -0.025 |
Token | needle |
Token ID | 17598 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
aids | +0.010 |
tant | +0.010 |
sc | +0.010 |
| | +0.010 |
igators | +0.010 |
Neg logit contributions | |
opsy | -0.015 |
ich | -0.014 |
field | -0.013 |
ster | -0.013 |
flower | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +4.41e-05 |
Pos logit contributions | |
tant | +0.054 |
videos | +0.052 |
tests | +0.052 |
aids | +0.051 |
igators | +0.050 |
Neg logit contributions | |
ich | -0.049 |
ster | -0.044 |
opsy | -0.041 |
field | -0.040 |
flower | -0.040 |
Token | thread |
Token ID | 4704 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
ich | +0.000 |
opsy | +0.000 |
field | +0.000 |
ster | +0.000 |
flower | +0.000 |
Neg logit contributions | |
tant | -0.000 |
sc | -0.000 |
aids | -0.000 |
channel | -0.000 |
igators | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
videos | +0.035 |
tant | +0.034 |
tests | +0.034 |
aids | +0.033 |
igators | +0.032 |
Neg logit contributions | |
ich | -0.043 |
opsy | -0.038 |
ster | -0.037 |
field | -0.036 |
flower | -0.035 |
Token | carefully |
Token ID | 7773 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
tant | +0.011 |
sc | +0.011 |
igsaw | +0.010 |
aids | +0.010 |
channel | +0.010 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.011 |
field | -0.010 |
ster | -0.010 |
wife | -0.009 |
Token | se |
Token ID | 384 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
tant | +0.028 |
igators | +0.026 |
videos | +0.026 |
sc | +0.026 |
baths | +0.025 |
Neg logit contributions | |
ich | -0.026 |
opsy | -0.024 |
field | -0.024 |
ster | -0.023 |
sters | -0.021 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
baths | +0.192 |
videos | +0.188 |
sc | +0.186 |
tests | +0.184 |
TV | +0.183 |
Neg logit contributions | |
ich | -0.145 |
opsy | -0.137 |
ese | -0.122 |
pper | -0.118 |
ster | -0.116 |
Token | the |
Token ID | 262 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
ich | +0.038 |
opsy | +0.036 |
ster | +0.033 |
field | +0.032 |
ble | +0.031 |
Neg logit contributions | |
aids | -0.030 |
igators | -0.029 |
videos | -0.028 |
tant | -0.028 |
villains | -0.028 |
Token | hole |
Token ID | 7604 |
Feature activation | -4.43e-04 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
igators | +0.005 |
videos | +0.005 |
baths | +0.004 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.007 |
field | -0.006 |
ster | -0.006 |
flower | -0.006 |
Token | shut |
Token ID | 4423 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
baths | +0.001 |
tests | +0.001 |
videos | +0.001 |
tant | +0.001 |
bang | +0.001 |
Neg logit contributions | |
ich | -0.001 |
ster | -0.001 |
field | -0.001 |
opsy | -0.001 |
flower | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +6.45e-04 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.002 |
field | +0.002 |
ster | +0.002 |
� | +0.002 |
Neg logit contributions | |
sc | -0.002 |
igators | -0.002 |
bang | -0.002 |
videos | -0.002 |
tests | -0.002 |
Token | Billy |
Token ID | 15890 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
tant | +0.012 |
sc | +0.012 |
baths | +0.012 |
tests | +0.011 |
videos | +0.011 |
Neg logit contributions | |
ich | -0.024 |
opsy | -0.022 |
field | -0.021 |
ster | -0.020 |
flower | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
tant | +0.009 |
sc | +0.009 |
baths | +0.008 |
tests | +0.008 |
videos | +0.008 |
Neg logit contributions | |
ich | -0.013 |
opsy | -0.011 |
field | -0.011 |
ster | -0.011 |
flower | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
sc | +0.002 |
tant | +0.002 |
baths | +0.002 |
tests | +0.002 |
videos | +0.002 |
Neg logit contributions | |
ich | -0.003 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
flower | -0.003 |
Token | three |
Token ID | 1115 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
sc | +0.018 |
baths | +0.017 |
tant | +0.017 |
tests | +0.017 |
videos | +0.017 |
Neg logit contributions | |
ich | -0.031 |
opsy | -0.028 |
field | -0.027 |
ster | -0.026 |
� | -0.024 |
Token | - |
Token ID | 12 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
sc | +0.088 |
baths | +0.082 |
aled | +0.080 |
videos | +0.080 |
tests | +0.079 |
Neg logit contributions | |
ich | -0.113 |
opsy | -0.106 |
ster | -0.097 |
field | -0.094 |
flower | -0.089 |
Token | year |
Token ID | 1941 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
baths | +0.132 |
videos | +0.121 |
TV | +0.114 |
showers | +0.114 |
tests | +0.112 |
Neg logit contributions | |
ich | -0.169 |
opsy | -0.148 |
illa | -0.147 |
ster | -0.141 |
flower | -0.135 |
Token | - |
Token ID | 12 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
sc | +0.186 |
videos | +0.166 |
baths | +0.164 |
Chloe | +0.162 |
tests | +0.162 |
Neg logit contributions | |
ich | -0.185 |
opsy | -0.168 |
ster | -0.165 |
wife | -0.149 |
ama | -0.146 |
Token | old |
Token ID | 727 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
baths | +0.121 |
videos | +0.115 |
bang | +0.114 |
tant | +0.113 |
sc | +0.110 |
Neg logit contributions | |
ich | -0.143 |
opsy | -0.124 |
illa | -0.119 |
ster | -0.118 |
wife | -0.111 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
sc | +0.012 |
tant | +0.012 |
baths | +0.012 |
tests | +0.011 |
videos | +0.011 |
Neg logit contributions | |
ich | -0.010 |
opsy | -0.008 |
ster | -0.008 |
field | -0.007 |
flower | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
tant | +0.018 |
sc | +0.017 |
baths | +0.017 |
tests | +0.016 |
videos | +0.016 |
Neg logit contributions | |
ich | -0.022 |
opsy | -0.019 |
field | -0.018 |
ster | -0.018 |
flower | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
tant | +0.019 |
sc | +0.018 |
baths | +0.018 |
tests | +0.017 |
videos | +0.016 |
Neg logit contributions | |
ich | -0.035 |
opsy | -0.031 |
field | -0.030 |
ster | -0.029 |
� | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
tant | +0.054 |
sc | +0.053 |
videos | +0.049 |
baths | +0.049 |
tests | +0.049 |
Neg logit contributions | |
ich | -0.060 |
opsy | -0.054 |
field | -0.051 |
ster | -0.050 |
� | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
sc | +0.006 |
tant | +0.006 |
baths | +0.006 |
tests | +0.005 |
aids | +0.005 |
Neg logit contributions | |
ich | -0.013 |
opsy | -0.011 |
field | -0.011 |
ster | -0.011 |
� | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
sc | +0.019 |
tant | +0.018 |
baths | +0.018 |
aled | +0.017 |
igators | +0.017 |
Neg logit contributions | |
ich | -0.030 |
opsy | -0.026 |
ster | -0.025 |
field | -0.024 |
� | -0.023 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
aled | +0.009 |
sc | +0.009 |
tant | +0.009 |
baths | +0.008 |
nob | +0.008 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.004 |
ster | -0.004 |
flower | -0.004 |
field | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
sc | +0.090 |
baths | +0.085 |
videos | +0.082 |
igsaw | +0.081 |
backward | +0.081 |
Neg logit contributions | |
ich | -0.121 |
opsy | -0.105 |
ster | -0.101 |
field | -0.096 |
ese | -0.093 |
Token | year |
Token ID | 1941 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
baths | +0.121 |
videos | +0.108 |
tant | +0.108 |
showers | +0.104 |
sc | +0.103 |
Neg logit contributions | |
ich | -0.185 |
illa | -0.160 |
ster | -0.158 |
opsy | -0.158 |
pper | -0.144 |
Token | - |
Token ID | 12 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
sc | +0.183 |
baths | +0.161 |
videos | +0.161 |
bang | +0.159 |
tant | +0.158 |
Neg logit contributions | |
ich | -0.196 |
ster | -0.166 |
opsy | -0.166 |
wife | -0.150 |
ama | -0.147 |
Token | old |
Token ID | 727 |
Feature activation | -5.75e-03 |
Pos logit contributions | |
baths | +0.121 |
tant | +0.119 |
sc | +0.116 |
videos | +0.114 |
bang | +0.113 |
Neg logit contributions | |
ich | -0.147 |
opsy | -0.124 |
ster | -0.122 |
illa | -0.120 |
field | -0.113 |
Token | boy |
Token ID | 2933 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
tant | +0.010 |
sc | +0.010 |
baths | +0.009 |
videos | +0.009 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.009 |
field | -0.009 |
ster | -0.009 |
flower | -0.008 |
Token | named |
Token ID | 3706 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
tant | +0.012 |
sc | +0.011 |
baths | +0.011 |
videos | +0.011 |
tests | +0.010 |
Neg logit contributions | |
ich | -0.017 |
opsy | -0.015 |
field | -0.015 |
ster | -0.014 |
flower | -0.013 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
tant | +0.013 |
sc | +0.013 |
baths | +0.011 |
videos | +0.011 |
aids | +0.011 |
Neg logit contributions | |
ich | -0.019 |
opsy | -0.016 |
ster | -0.016 |
illa | -0.016 |
field | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
tant | +0.014 |
sc | +0.013 |
igsaw | +0.013 |
tests | +0.013 |
baths | +0.013 |
Neg logit contributions | |
ich | -0.017 |
opsy | -0.014 |
ster | -0.014 |
field | -0.013 |
flower | -0.012 |
Token | waves |
Token ID | 9813 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
sc | +0.043 |
chair | +0.040 |
aids | +0.038 |
tant | +0.038 |
nob | +0.038 |
Neg logit contributions | |
ich | -0.063 |
opsy | -0.056 |
field | -0.055 |
ster | -0.052 |
wife | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -2.70e-03 |
Pos logit contributions | |
tant | +0.007 |
tests | +0.007 |
sc | +0.007 |
baths | +0.007 |
igators | +0.007 |
Neg logit contributions | |
ich | -0.007 |
ster | -0.006 |
opsy | -0.006 |
field | -0.006 |
flower | -0.006 |
Token | wind |
Token ID | 2344 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.004 |
igsaw | +0.004 |
x | +0.004 |
If | +0.004 |
Neg logit contributions | |
ich | -0.004 |
field | -0.004 |
ster | -0.004 |
sters | -0.004 |
wife | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +7.66e-04 |
Pos logit contributions | |
tant | +0.037 |
sc | +0.037 |
baths | +0.036 |
tests | +0.035 |
videos | +0.034 |
Neg logit contributions | |
ich | -0.049 |
opsy | -0.042 |
field | -0.041 |
ster | -0.040 |
flower | -0.037 |
Token | se |
Token ID | 384 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ich | +0.001 |
field | +0.001 |
ster | +0.001 |
wife | +0.001 |
sters | +0.001 |
Neg logit contributions | |
sc | -0.001 |
igsaw | -0.001 |
tant | -0.001 |
Everywhere | -0.001 |
aback | -0.001 |
Token | ag |
Token ID | 363 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
baths | +0.171 |
tests | +0.166 |
sc | +0.166 |
videos | +0.164 |
igsaw | +0.163 |
Neg logit contributions | |
ich | -0.165 |
opsy | -0.151 |
ese | -0.146 |
pper | -0.135 |
ster | -0.132 |
Token | ull |
Token ID | 724 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
baths | +0.005 |
videos | +0.004 |
tests | +0.004 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.006 |
field | -0.005 |
ster | -0.005 |
sters | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
tant | +0.061 |
sc | +0.060 |
tests | +0.059 |
baths | +0.059 |
videos | +0.058 |
Neg logit contributions | |
ich | -0.052 |
opsy | -0.044 |
field | -0.041 |
ster | -0.040 |
sters | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
tant | +0.008 |
sc | +0.008 |
baths | +0.008 |
tests | +0.008 |
videos | +0.007 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.010 |
ster | -0.009 |
flower | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
tant | +0.010 |
sc | +0.010 |
baths | +0.010 |
videos | +0.010 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.019 |
opsy | -0.017 |
field | -0.016 |
ster | -0.016 |
flower | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
sc | +0.117 |
tant | +0.107 |
baths | +0.107 |
tests | +0.104 |
bang | +0.103 |
Neg logit contributions | |
ich | -0.119 |
opsy | -0.103 |
ster | -0.094 |
field | -0.091 |
sters | -0.090 |
Token | like |
Token ID | 588 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
tant | +0.056 |
sc | +0.056 |
baths | +0.050 |
tests | +0.049 |
bang | +0.048 |
Neg logit contributions | |
ich | -0.056 |
opsy | -0.049 |
field | -0.047 |
ster | -0.045 |
� | -0.041 |
Token | all |
Token ID | 477 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
sc | +0.010 |
tant | +0.009 |
aids | +0.008 |
igators | +0.008 |
aled | +0.008 |
Neg logit contributions | |
ich | -0.015 |
opsy | -0.013 |
field | -0.012 |
ster | -0.012 |
wife | -0.011 |
Token | three |
Token ID | 1115 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
sc | +0.004 |
tant | +0.004 |
bang | +0.004 |
driver | +0.004 |
ro | +0.004 |
Neg logit contributions | |
ich | -0.005 |
field | -0.004 |
flower | -0.004 |
opsy | -0.004 |
ster | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
sc | +0.109 |
tant | +0.100 |
baths | +0.096 |
tests | +0.096 |
bang | +0.095 |
Neg logit contributions | |
ich | -0.115 |
opsy | -0.101 |
sters | -0.092 |
ster | -0.091 |
field | -0.090 |
Token | year |
Token ID | 1941 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
tant | +0.121 |
sc | +0.120 |
baths | +0.115 |
bang | +0.113 |
TV | +0.113 |
Neg logit contributions | |
ich | -0.148 |
opsy | -0.124 |
anut | -0.118 |
illa | -0.117 |
ll | -0.113 |
Token | - |
Token ID | 12 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
sc | +0.173 |
bang | +0.157 |
tant | +0.148 |
James | +0.148 |
Emma | +0.147 |
Neg logit contributions | |
ich | -0.202 |
opsy | -0.173 |
ster | -0.164 |
sters | -0.162 |
wife | -0.155 |
Token | olds |
Token ID | 10119 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
sc | +0.109 |
tant | +0.109 |
bang | +0.106 |
TV | +0.100 |
baths | +0.100 |
Neg logit contributions | |
ich | -0.135 |
opsy | -0.112 |
anut | -0.106 |
ese | -0.106 |
ll | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
ich | +0.034 |
opsy | +0.029 |
sters | +0.028 |
ster | +0.028 |
field | +0.027 |
Neg logit contributions | |
sc | -0.032 |
tant | -0.031 |
igsaw | -0.029 |
bang | -0.028 |
baths | -0.028 |
Token | he |
Token ID | 339 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
ich | +0.008 |
opsy | +0.007 |
field | +0.007 |
ster | +0.006 |
wife | +0.006 |
Neg logit contributions | |
sc | -0.008 |
tant | -0.008 |
aled | -0.007 |
igsaw | -0.007 |
baths | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ich | +0.005 |
opsy | +0.005 |
field | +0.004 |
ster | +0.004 |
flower | +0.004 |
Neg logit contributions | |
tant | -0.004 |
sc | -0.004 |
baths | -0.004 |
videos | -0.004 |
tests | -0.004 |
Token | izzy |
Token ID | 40593 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
tant | +0.027 |
baths | +0.026 |
sc | +0.026 |
videos | +0.026 |
tests | +0.026 |
Neg logit contributions | |
ich | -0.034 |
opsy | -0.030 |
field | -0.028 |
ster | -0.027 |
flower | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
sc | +0.030 |
tant | +0.030 |
baths | +0.029 |
videos | +0.028 |
tests | +0.027 |
Neg logit contributions | |
ich | -0.036 |
opsy | -0.032 |
field | -0.031 |
ster | -0.029 |
sters | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
sc | +0.022 |
tant | +0.020 |
head | +0.019 |
igsaw | +0.019 |
videos | +0.018 |
Neg logit contributions | |
ich | -0.026 |
opsy | -0.024 |
field | -0.021 |
ster | -0.020 |
ble | -0.019 |
Token | three |
Token ID | 1115 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
sc | +0.012 |
igators | +0.011 |
aled | +0.011 |
videos | +0.011 |
baths | +0.011 |
Neg logit contributions | |
ich | -0.017 |
opsy | -0.016 |
ster | -0.015 |
field | -0.015 |
� | -0.014 |
Token | - |
Token ID | 12 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
sc | +0.083 |
videos | +0.078 |
baths | +0.078 |
aled | +0.076 |
igators | +0.075 |
Neg logit contributions | |
ich | -0.107 |
opsy | -0.099 |
ster | -0.092 |
field | -0.087 |
� | -0.085 |
Token | year |
Token ID | 1941 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
baths | +0.118 |
videos | +0.113 |
TV | +0.106 |
showers | +0.104 |
cartoons | +0.101 |
Neg logit contributions | |
ich | -0.172 |
opsy | -0.151 |
illa | -0.141 |
ster | -0.141 |
pper | -0.139 |
Token | - |
Token ID | 12 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
sc | +0.188 |
videos | +0.177 |
bang | +0.170 |
baths | +0.169 |
| | +0.169 |
Neg logit contributions | |
ich | -0.182 |
opsy | -0.158 |
ster | -0.157 |
ama | -0.140 |
field | -0.139 |
Token | old |
Token ID | 727 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
baths | +0.115 |
videos | +0.114 |
tant | +0.110 |
bang | +0.110 |
TV | +0.109 |
Neg logit contributions | |
ich | -0.130 |
opsy | -0.112 |
ster | -0.104 |
illa | -0.104 |
ll | -0.099 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
sc | +0.009 |
tant | +0.009 |
baths | +0.009 |
videos | +0.009 |
igators | +0.009 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.006 |
ster | -0.006 |
field | -0.005 |
flower | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.50e-03 |
Pos logit contributions | |
tant | +0.024 |
sc | +0.023 |
baths | +0.023 |
videos | +0.022 |
igators | +0.022 |
Neg logit contributions | |
ich | -0.030 |
opsy | -0.027 |
field | -0.025 |
ster | -0.025 |
flower | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
tant | +0.007 |
sc | +0.006 |
tests | +0.006 |
igators | +0.006 |
bang | +0.006 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.009 |
� | -0.008 |
field | -0.008 |
ama | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
sc | +0.031 |
igators | +0.027 |
baths | +0.025 |
aids | +0.025 |
villains | +0.025 |
Neg logit contributions | |
ich | -0.036 |
opsy | -0.035 |
ster | -0.031 |
wife | -0.030 |
ige | -0.029 |
Token | needle |
Token ID | 17598 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
igators | +0.021 |
baths | +0.021 |
videos | +0.020 |
aled | +0.020 |
sc | +0.020 |
Neg logit contributions | |
ich | -0.033 |
opsy | -0.030 |
field | -0.029 |
ster | -0.029 |
� | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -6.44e-04 |
Pos logit contributions | |
baths | +0.049 |
igators | +0.048 |
videos | +0.048 |
tests | +0.047 |
aids | +0.047 |
Neg logit contributions | |
ich | -0.038 |
ster | -0.031 |
flower | -0.029 |
field | -0.028 |
opsy | -0.028 |
Token | thread |
Token ID | 4704 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
tant | +0.001 |
sc | +0.001 |
aids | +0.001 |
baths | +0.001 |
igators | +0.001 |
Neg logit contributions | |
ich | -0.001 |
opsy | -0.001 |
ster | -0.001 |
field | -0.001 |
sters | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -8.36e-03 |
Pos logit contributions | |
videos | +0.034 |
tant | +0.033 |
aids | +0.032 |
igators | +0.032 |
baths | +0.032 |
Neg logit contributions | |
ich | -0.042 |
opsy | -0.036 |
ster | -0.035 |
field | -0.034 |
flower | -0.033 |
Token | se |
Token ID | 384 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
tant | +0.013 |
aids | +0.013 |
sc | +0.013 |
igators | +0.013 |
baths | +0.012 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.014 |
ster | -0.014 |
field | -0.013 |
sters | -0.012 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
baths | +0.196 |
videos | +0.188 |
tests | +0.188 |
sc | +0.187 |
TV | +0.184 |
Neg logit contributions | |
ich | -0.143 |
opsy | -0.132 |
ese | -0.118 |
ster | -0.115 |
pper | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
ich | +0.027 |
opsy | +0.025 |
ster | +0.023 |
field | +0.022 |
� | +0.022 |
Neg logit contributions | |
igators | -0.024 |
aids | -0.024 |
videos | -0.023 |
tant | -0.023 |
baths | -0.023 |
Token | t |
Token ID | 256 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
sc | +0.004 |
videos | +0.004 |
tant | +0.004 |
igators | +0.004 |
baths | +0.004 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.007 |
ster | -0.006 |
field | -0.006 |
flower | -0.006 |
Token | eddy |
Token ID | 21874 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ich | +0.004 |
opsy | +0.003 |
field | +0.003 |
ster | +0.003 |
flower | +0.003 |
Neg logit contributions | |
tant | -0.003 |
sc | -0.003 |
baths | -0.003 |
videos | -0.003 |
tests | -0.003 |
Token | bear |
Token ID | 6842 |
Feature activation | -2.17e-03 |
Pos logit contributions | |
tant | +0.016 |
sc | +0.015 |
baths | +0.015 |
videos | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.024 |
opsy | -0.021 |
field | -0.020 |
ster | -0.020 |
flower | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ich | +0.026 |
opsy | +0.024 |
field | +0.024 |
ster | +0.021 |
flower | +0.020 |
Neg logit contributions | |
tant | -0.024 |
sc | -0.024 |
videos | -0.022 |
baths | -0.022 |
bang | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
tant | +0.053 |
sc | +0.051 |
videos | +0.048 |
tests | +0.047 |
baths | +0.047 |
Neg logit contributions | |
ich | -0.058 |
opsy | -0.054 |
field | -0.050 |
ster | -0.049 |
� | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
tant | +0.002 |
sc | +0.002 |
baths | +0.002 |
videos | +0.001 |
tests | +0.001 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
flower | -0.003 |
Token | three |
Token ID | 1115 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
sc | +0.012 |
tant | +0.011 |
baths | +0.011 |
videos | +0.010 |
tests | +0.010 |
Neg logit contributions | |
ich | -0.019 |
opsy | -0.018 |
field | -0.016 |
ster | -0.016 |
� | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
sc | +0.081 |
baths | +0.075 |
videos | +0.073 |
backward | +0.072 |
aled | +0.071 |
Neg logit contributions | |
ich | -0.104 |
opsy | -0.097 |
ster | -0.090 |
field | -0.085 |
sters | -0.083 |
Token | year |
Token ID | 1941 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
baths | +0.112 |
videos | +0.103 |
tant | +0.102 |
showers | +0.095 |
bang | +0.094 |
Neg logit contributions | |
ich | -0.203 |
opsy | -0.175 |
ster | -0.170 |
illa | -0.168 |
field | -0.162 |
Token | - |
Token ID | 12 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
sc | +0.176 |
videos | +0.162 |
baths | +0.161 |
tant | +0.159 |
bang | +0.156 |
Neg logit contributions | |
ich | -0.200 |
opsy | -0.169 |
ster | -0.169 |
field | -0.159 |
wife | -0.151 |
Token | old |
Token ID | 727 |
Feature activation | -9.82e-03 |
Pos logit contributions | |
baths | +0.107 |
tant | +0.106 |
videos | +0.102 |
sc | +0.101 |
bang | +0.099 |
Neg logit contributions | |
ich | -0.160 |
opsy | -0.137 |
ster | -0.132 |
field | -0.129 |
illa | -0.126 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
tant | +0.017 |
sc | +0.017 |
baths | +0.017 |
videos | +0.016 |
tests | +0.016 |
Neg logit contributions | |
ich | -0.018 |
opsy | -0.016 |
field | -0.015 |
ster | -0.014 |
flower | -0.013 |
Token | decided |
Token ID | 3066 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
tant | +0.016 |
sc | +0.015 |
baths | +0.015 |
videos | +0.014 |
tests | +0.014 |
Neg logit contributions | |
ich | -0.021 |
opsy | -0.018 |
field | -0.017 |
ster | -0.017 |
flower | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.014 |
field | +0.014 |
ster | +0.014 |
sters | +0.013 |
Neg logit contributions | |
tant | -0.007 |
sc | -0.006 |
baths | -0.006 |
videos | -0.005 |
tests | -0.005 |
Token | took |
Token ID | 1718 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
bang | +0.022 |
sc | +0.022 |
baths | +0.022 |
Lily | +0.021 |
around | +0.021 |
Neg logit contributions | |
ich | -0.061 |
opsy | -0.054 |
field | -0.052 |
ster | -0.051 |
sters | -0.049 |
Token | Sara |
Token ID | 24799 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
sc | +0.021 |
igator | +0.020 |
bench | +0.020 |
taker | +0.020 |
riend | +0.020 |
Neg logit contributions | |
ich | -0.025 |
opsy | -0.024 |
iya | -0.022 |
ese | -0.021 |
wife | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ich | +0.017 |
opsy | +0.015 |
field | +0.015 |
ster | +0.014 |
flower | +0.013 |
Neg logit contributions | |
tant | -0.006 |
sc | -0.006 |
baths | -0.006 |
videos | -0.006 |
tests | -0.005 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
aids | +0.028 |
smart | +0.027 |
sc | +0.027 |
tant | +0.027 |
aled | +0.027 |
Neg logit contributions | |
ich | -0.035 |
opsy | -0.028 |
field | -0.028 |
ster | -0.027 |
wife | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
backward | +0.108 |
Everywhere | +0.105 |
sc | +0.103 |
If | +0.102 |
baths | +0.102 |
Neg logit contributions | |
ich | -0.122 |
opsy | -0.104 |
ster | -0.104 |
ese | -0.096 |
iya | -0.096 |
Token | year |
Token ID | 1941 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
baths | +0.092 |
tant | +0.091 |
bang | +0.086 |
videos | +0.086 |
sc | +0.083 |
Neg logit contributions | |
ich | -0.173 |
opsy | -0.153 |
illa | -0.150 |
ster | -0.147 |
ese | -0.141 |
Token | - |
Token ID | 12 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
sc | +0.173 |
bang | +0.165 |
baths | +0.159 |
videos | +0.158 |
tant | +0.158 |
Neg logit contributions | |
ich | -0.187 |
ster | -0.159 |
opsy | -0.159 |
ama | -0.144 |
field | -0.142 |
Token | old |
Token ID | 727 |
Feature activation | -7.77e-04 |
Pos logit contributions | |
tant | +0.107 |
baths | +0.103 |
bang | +0.103 |
sc | +0.101 |
videos | +0.100 |
Neg logit contributions | |
ich | -0.138 |
opsy | -0.117 |
illa | -0.114 |
ster | -0.114 |
ese | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
tant | +0.002 |
sc | +0.002 |
baths | +0.002 |
tests | +0.002 |
bang | +0.002 |
Neg logit contributions | |
ich | -0.001 |
opsy | -0.001 |
ster | -0.001 |
field | -0.001 |
sters | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.003 |
field | +0.003 |
wife | +0.003 |
iya | +0.003 |
Neg logit contributions | |
sc | -0.003 |
tant | -0.003 |
taker | -0.002 |
igators | -0.002 |
aids | -0.002 |
Token | park |
Token ID | 3952 |
Feature activation | +9.77e-03 |
Pos logit contributions | |
ich | +0.027 |
opsy | +0.023 |
field | +0.022 |
ster | +0.021 |
� | +0.019 |
Neg logit contributions | |
sc | -0.023 |
tant | -0.022 |
baths | -0.022 |
igators | -0.021 |
videos | -0.020 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
sc | +0.048 |
tant | +0.045 |
baths | +0.044 |
igators | +0.040 |
videos | +0.040 |
Neg logit contributions | |
ich | -0.075 |
opsy | -0.067 |
field | -0.064 |
ster | -0.062 |
� | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
sc | +0.067 |
baths | +0.066 |
tant | +0.066 |
videos | +0.063 |
tests | +0.059 |
Neg logit contributions | |
ich | -0.107 |
opsy | -0.097 |
field | -0.091 |
ster | -0.089 |
sters | -0.084 |
Token | one |
Token ID | 505 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
baths | +0.181 |
videos | +0.173 |
tant | +0.170 |
sc | +0.168 |
showers | +0.161 |
Neg logit contributions | |
ich | -0.182 |
opsy | -0.156 |
illa | -0.149 |
field | -0.144 |
pper | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
sc | +0.053 |
baths | +0.052 |
tant | +0.051 |
videos | +0.050 |
showers | +0.047 |
Neg logit contributions | |
ich | -0.059 |
opsy | -0.052 |
field | -0.050 |
ster | -0.048 |
flower | -0.044 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
sc | +0.050 |
tant | +0.047 |
baths | +0.045 |
igators | +0.041 |
videos | +0.041 |
Neg logit contributions | |
ich | -0.077 |
opsy | -0.069 |
field | -0.065 |
ster | -0.064 |
� | -0.063 |
Token | - |
Token ID | 12 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
sc | +0.064 |
baths | +0.063 |
tant | +0.063 |
videos | +0.060 |
tests | +0.057 |
Neg logit contributions | |
ich | -0.106 |
opsy | -0.096 |
field | -0.091 |
ster | -0.089 |
sters | -0.083 |
Token | two |
Token ID | 11545 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
baths | +0.173 |
videos | +0.167 |
tant | +0.165 |
sc | +0.162 |
showers | +0.155 |
Neg logit contributions | |
ich | -0.180 |
opsy | -0.153 |
illa | -0.146 |
field | -0.142 |
pper | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
sc | +0.055 |
tant | +0.053 |
baths | +0.053 |
videos | +0.051 |
tests | +0.048 |
Neg logit contributions | |
ich | -0.077 |
opsy | -0.069 |
field | -0.065 |
ster | -0.063 |
sters | -0.059 |
Token | thirty |
Token ID | 12277 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
sc | +0.044 |
tant | +0.042 |
baths | +0.040 |
igators | +0.037 |
videos | +0.036 |
Neg logit contributions | |
ich | -0.066 |
opsy | -0.059 |
field | -0.056 |
ster | -0.055 |
� | -0.053 |
Token | - |
Token ID | 12 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
sc | +0.056 |
tant | +0.055 |
baths | +0.055 |
videos | +0.052 |
tests | +0.050 |
Neg logit contributions | |
ich | -0.100 |
opsy | -0.090 |
field | -0.086 |
ster | -0.084 |
sters | -0.079 |
Token | three |
Token ID | 15542 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
baths | +0.151 |
tant | +0.147 |
videos | +0.146 |
sc | +0.143 |
showers | +0.136 |
Neg logit contributions | |
ich | -0.169 |
opsy | -0.144 |
field | -0.135 |
illa | -0.134 |
ster | -0.133 |
Token | over |
Token ID | 625 |
Feature activation | +4.85e-04 |
Pos logit contributions | |
tant | +0.007 |
aids | +0.006 |
igators | +0.006 |
videos | +0.006 |
tests | +0.006 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.009 |
ster | -0.009 |
� | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e-03 |
Pos logit contributions | |
ich | +0.001 |
field | +0.001 |
opsy | +0.001 |
ster | +0.001 |
flower | +0.001 |
Neg logit contributions | |
tant | -0.001 |
videos | -0.001 |
aids | -0.001 |
baths | -0.001 |
taker | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
baths | +0.001 |
sc | +0.001 |
tant | +0.001 |
bang | +0.001 |
tests | +0.001 |
Neg logit contributions | |
ich | -0.003 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
sters | -0.003 |
Token | cookie |
Token ID | 19751 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.003 |
field | +0.003 |
ster | +0.003 |
flower | +0.002 |
Neg logit contributions | |
tant | -0.002 |
sc | -0.002 |
baths | -0.002 |
videos | -0.002 |
tests | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
ich | +0.049 |
opsy | +0.043 |
field | +0.043 |
ster | +0.040 |
flower | +0.037 |
Neg logit contributions | |
tant | -0.043 |
baths | -0.041 |
sc | -0.041 |
videos | -0.040 |
tests | -0.040 |
Token | pick |
Token ID | 2298 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ich | +0.018 |
opsy | +0.016 |
field | +0.015 |
ster | +0.015 |
flower | +0.014 |
Neg logit contributions | |
tant | -0.012 |
sc | -0.012 |
baths | -0.011 |
videos | -0.011 |
tests | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ich | +0.083 |
opsy | +0.076 |
field | +0.071 |
ster | +0.071 |
sters | +0.066 |
Neg logit contributions | |
tant | -0.050 |
sc | -0.048 |
baths | -0.047 |
videos | -0.047 |
tests | -0.046 |
Token | up |
Token ID | 510 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
tant | +0.019 |
baths | +0.018 |
sc | +0.018 |
tests | +0.018 |
videos | +0.017 |
Neg logit contributions | |
ich | -0.034 |
opsy | -0.032 |
field | -0.030 |
ster | -0.029 |
sters | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ich | +0.028 |
opsy | +0.025 |
field | +0.024 |
ster | +0.023 |
flower | +0.022 |
Neg logit contributions | |
tant | -0.016 |
sc | -0.016 |
baths | -0.016 |
videos | -0.015 |
tests | -0.015 |
Token | but |
Token ID | 475 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
ich | +0.032 |
opsy | +0.028 |
field | +0.027 |
ster | +0.026 |
flower | +0.024 |
Neg logit contributions | |
tant | -0.022 |
sc | -0.022 |
baths | -0.021 |
videos | -0.020 |
tests | -0.020 |
Token | then |
Token ID | 788 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.003 |
field | +0.003 |
ster | +0.003 |
sters | +0.002 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
baths | -0.001 |
tests | -0.001 |
videos | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
ich | +0.044 |
opsy | +0.040 |
field | +0.038 |
ster | +0.037 |
sters | +0.037 |
Neg logit contributions | |
sc | -0.017 |
tant | -0.017 |
baths | -0.017 |
videos | -0.016 |
tests | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
sc | +0.007 |
baths | +0.007 |
around | +0.007 |
tant | +0.006 |
loud | +0.006 |
Neg logit contributions | |
ich | -0.025 |
opsy | -0.023 |
field | -0.023 |
ster | -0.021 |
sters | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ich | +0.011 |
opsy | +0.010 |
field | +0.010 |
ster | +0.009 |
� | +0.009 |
Neg logit contributions | |
tant | -0.008 |
sc | -0.008 |
baths | -0.007 |
videos | -0.007 |
tests | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ich | +0.035 |
opsy | +0.033 |
field | +0.031 |
� | +0.030 |
ster | +0.030 |
Neg logit contributions | |
tant | -0.015 |
sc | -0.015 |
aids | -0.013 |
igators | -0.013 |
tests | -0.013 |
Token | became |
Token ID | 2627 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
ich | +0.063 |
opsy | +0.054 |
ster | +0.052 |
field | +0.052 |
sters | +0.050 |
Neg logit contributions | |
baths | -0.027 |
bang | -0.025 |
tant | -0.025 |
sc | -0.025 |
around | -0.025 |
Token | friends |
Token ID | 2460 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
ich | +0.037 |
opsy | +0.033 |
field | +0.032 |
ster | +0.031 |
sters | +0.029 |
Neg logit contributions | |
baths | -0.019 |
sc | -0.019 |
tant | -0.019 |
videos | -0.018 |
tests | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
ich | +0.083 |
opsy | +0.077 |
field | +0.073 |
ster | +0.070 |
sters | +0.067 |
Neg logit contributions | |
baths | -0.037 |
sc | -0.036 |
tant | -0.035 |
around | -0.035 |
videos | -0.034 |
Token | played |
Token ID | 2826 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
baths | +0.012 |
sc | +0.011 |
tant | +0.011 |
videos | +0.011 |
tests | +0.011 |
Neg logit contributions | |
ich | -0.020 |
opsy | -0.018 |
field | -0.017 |
ster | -0.017 |
sters | -0.016 |
Token | together |
Token ID | 1978 |
Feature activation | -6.93e-03 |
Pos logit contributions | |
ich | +0.025 |
opsy | +0.023 |
field | +0.022 |
ster | +0.021 |
flower | +0.020 |
Neg logit contributions | |
sc | -0.010 |
baths | -0.010 |
tant | -0.009 |
videos | -0.009 |
tests | -0.009 |
Token | every |
Token ID | 790 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
tant | +0.010 |
sc | +0.010 |
baths | +0.009 |
videos | +0.009 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.015 |
opsy | -0.013 |
field | -0.013 |
ster | -0.012 |
flower | -0.011 |
Token | time |
Token ID | 640 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
ich | +0.018 |
opsy | +0.017 |
field | +0.016 |
ster | +0.015 |
flower | +0.014 |
Neg logit contributions | |
tant | -0.010 |
sc | -0.010 |
baths | -0.010 |
tests | -0.009 |
videos | -0.009 |
Token | hands |
Token ID | 2832 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
tant | +0.031 |
sc | +0.029 |
baths | +0.029 |
videos | +0.028 |
tests | +0.028 |
Neg logit contributions | |
ich | -0.046 |
opsy | -0.040 |
field | -0.039 |
ster | -0.037 |
sters | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
ich | +0.031 |
opsy | +0.028 |
field | +0.027 |
ster | +0.026 |
flower | +0.024 |
Neg logit contributions | |
tant | -0.022 |
sc | -0.021 |
baths | -0.021 |
tests | -0.020 |
videos | -0.020 |
Token | picked |
Token ID | 6497 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
tant | +0.010 |
sc | +0.010 |
baths | +0.010 |
videos | +0.009 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.014 |
field | -0.013 |
ster | -0.013 |
flower | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -3.67e-03 |
Pos logit contributions | |
ich | +0.077 |
opsy | +0.070 |
field | +0.067 |
ster | +0.065 |
flower | +0.061 |
Neg logit contributions | |
tant | -0.029 |
sc | -0.029 |
baths | -0.028 |
videos | -0.027 |
tests | -0.026 |
Token | creamy |
Token ID | 27892 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
loud | +0.004 |
tant | +0.004 |
Lily | +0.004 |
around | +0.004 |
hard | +0.004 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.008 |
iya | -0.008 |
ipper | -0.007 |
Token | fruit |
Token ID | 8234 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ich | +0.051 |
opsy | +0.043 |
field | +0.042 |
ster | +0.039 |
iya | +0.037 |
Neg logit contributions | |
tant | -0.033 |
baths | -0.032 |
sc | -0.031 |
around | -0.029 |
videos | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
ich | +0.099 |
opsy | +0.089 |
field | +0.085 |
ster | +0.082 |
flower | +0.077 |
Neg logit contributions | |
tant | -0.055 |
sc | -0.054 |
baths | -0.053 |
videos | -0.051 |
tests | -0.050 |
Token | She |
Token ID | 1375 |
Feature activation | +5.78e-03 |
Pos logit contributions | |
tant | +0.004 |
sc | +0.003 |
tests | +0.003 |
igators | +0.003 |
baths | +0.003 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.006 |
field | -0.006 |
� | -0.006 |
ster | -0.005 |
Token | tasted |
Token ID | 29187 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ich | +0.014 |
opsy | +0.012 |
field | +0.012 |
ster | +0.011 |
ese | +0.010 |
Neg logit contributions | |
tant | -0.007 |
sc | -0.007 |
baths | -0.007 |
tests | -0.007 |
bang | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
ich | +0.086 |
opsy | +0.078 |
field | +0.075 |
ster | +0.072 |
flower | +0.068 |
Neg logit contributions | |
tant | -0.036 |
sc | -0.036 |
baths | -0.035 |
videos | -0.033 |
tests | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -3.44e-03 |
Pos logit contributions | |
tant | +0.003 |
sc | +0.003 |
baths | +0.003 |
videos | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.004 |
field | -0.004 |
ster | -0.004 |
sters | -0.003 |
Token | excited |
Token ID | 6568 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
sc | +0.011 |
tant | +0.011 |
igsaw | +0.010 |
baths | +0.010 |
tests | +0.010 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.014 |
ster | -0.013 |
field | -0.013 |
sters | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.006 |
field | +0.005 |
ster | +0.005 |
flower | +0.005 |
Neg logit contributions | |
tant | -0.007 |
sc | -0.006 |
tests | -0.006 |
bang | -0.006 |
baths | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ich | +0.028 |
opsy | +0.025 |
field | +0.024 |
ster | +0.023 |
flower | +0.021 |
Neg logit contributions | |
tant | -0.023 |
sc | -0.023 |
baths | -0.022 |
tests | -0.021 |
videos | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
ich | +0.032 |
opsy | +0.030 |
field | +0.028 |
ster | +0.027 |
sters | +0.026 |
Neg logit contributions | |
tant | -0.018 |
sc | -0.017 |
videos | -0.016 |
baths | -0.016 |
tests | -0.016 |
Token | new |
Token ID | 649 |
Feature activation | -9.10e-03 |
Pos logit contributions | |
tant | +0.010 |
sc | +0.010 |
baths | +0.009 |
videos | +0.009 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.015 |
opsy | -0.013 |
field | -0.013 |
ster | -0.012 |
sters | -0.011 |
Token | pet |
Token ID | 4273 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
tant | +0.015 |
sc | +0.014 |
baths | +0.014 |
videos | +0.014 |
tests | +0.013 |
Neg logit contributions | |
ich | -0.018 |
opsy | -0.016 |
field | -0.015 |
ster | -0.014 |
sters | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
ich | +0.114 |
opsy | +0.102 |
field | +0.098 |
ster | +0.093 |
sters | +0.087 |
Neg logit contributions | |
sc | -0.065 |
tant | -0.064 |
baths | -0.063 |
videos | -0.060 |
tests | -0.059 |
Token | They |
Token ID | 1119 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
sc | +0.003 |
baths | +0.003 |
tant | +0.003 |
videos | +0.003 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
field | -0.007 |
ster | -0.007 |
pper | -0.007 |
Token | tried |
Token ID | 3088 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ich | +0.028 |
opsy | +0.025 |
field | +0.024 |
ster | +0.023 |
flower | +0.021 |
Neg logit contributions | |
sc | -0.020 |
tant | -0.020 |
baths | -0.020 |
videos | -0.019 |
bang | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ich | +0.028 |
opsy | +0.025 |
field | +0.024 |
ster | +0.023 |
flower | +0.022 |
Neg logit contributions | |
sc | -0.013 |
tant | -0.013 |
taker | -0.012 |
baths | -0.011 |
igators | -0.011 |
Token | grab |
Token ID | 5552 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
tant | +0.021 |
sc | +0.021 |
baths | +0.020 |
videos | +0.019 |
tests | +0.019 |
Neg logit contributions | |
ich | -0.027 |
opsy | -0.024 |
field | -0.023 |
ster | -0.022 |
flower | -0.021 |
Token | he |
Token ID | 339 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
baths | +0.010 |
tant | +0.010 |
sc | +0.010 |
tests | +0.009 |
videos | +0.009 |
Neg logit contributions | |
ich | -0.029 |
opsy | -0.026 |
field | -0.024 |
ster | -0.024 |
flower | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
ich | +0.019 |
opsy | +0.017 |
field | +0.016 |
ster | +0.015 |
sters | +0.015 |
Neg logit contributions | |
sc | -0.009 |
tant | -0.009 |
baths | -0.009 |
tests | -0.008 |
bang | -0.008 |
Token | done |
Token ID | 1760 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
tant | +0.002 |
sc | +0.002 |
videos | +0.002 |
baths | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.002 |
opsy | -0.002 |
field | -0.002 |
ster | -0.002 |
iya | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
tant | +0.011 |
sc | +0.010 |
igators | +0.009 |
videos | +0.009 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.009 |
ster | -0.009 |
� | -0.008 |
Token | went |
Token ID | 1816 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
ich | +0.036 |
opsy | +0.031 |
field | +0.029 |
ster | +0.029 |
flower | +0.028 |
Neg logit contributions | |
sc | -0.019 |
baths | -0.018 |
tests | -0.017 |
around | -0.017 |
tant | -0.017 |
Token | back |
Token ID | 736 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
tant | +0.008 |
sc | +0.007 |
baths | +0.007 |
videos | +0.007 |
tests | +0.007 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.009 |
field | -0.009 |
ster | -0.009 |
sters | -0.008 |
Token | home |
Token ID | 1363 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
ich | +0.071 |
opsy | +0.063 |
field | +0.061 |
ster | +0.058 |
flower | +0.054 |
Neg logit contributions | |
tant | -0.047 |
sc | -0.047 |
baths | -0.045 |
videos | -0.044 |
tests | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ich | +0.005 |
opsy | +0.005 |
field | +0.004 |
ster | +0.004 |
sters | +0.004 |
Neg logit contributions | |
sc | -0.003 |
tant | -0.003 |
baths | -0.003 |
videos | -0.003 |
tests | -0.003 |
Token | much |
Token ID | 881 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ich | +0.051 |
opsy | +0.047 |
field | +0.045 |
ster | +0.043 |
sters | +0.041 |
Neg logit contributions | |
tant | -0.019 |
baths | -0.019 |
sc | -0.019 |
videos | -0.017 |
tests | -0.017 |
Token | richer |
Token ID | 26192 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
ich | +0.027 |
field | +0.024 |
opsy | +0.024 |
ster | +0.023 |
sters | +0.020 |
Neg logit contributions | |
sc | -0.020 |
tant | -0.020 |
igators | -0.018 |
aled | -0.018 |
aids | -0.018 |
Token | for |
Token ID | 329 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
baths | +0.005 |
tests | +0.005 |
videos | +0.005 |
Neg logit contributions | |
ich | -0.009 |
opsy | -0.008 |
field | -0.007 |
ster | -0.007 |
flower | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
| | +0.022 |
sc | +0.022 |
baths | +0.021 |
Everywhere | +0.021 |
aled | +0.021 |
Neg logit contributions | |
ich | -0.025 |
ster | -0.022 |
opsy | -0.021 |
field | -0.021 |
wife | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
sc | +0.063 |
tant | +0.057 |
baths | +0.054 |
tests | +0.053 |
aids | +0.050 |
Neg logit contributions | |
ich | -0.107 |
opsy | -0.101 |
field | -0.093 |
flower | -0.089 |
ster | -0.086 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
sc | +0.020 |
baths | +0.019 |
tant | +0.019 |
videos | +0.019 |
tests | +0.018 |
Neg logit contributions | |
ich | -0.029 |
opsy | -0.026 |
field | -0.025 |
ster | -0.024 |
flower | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +7.63e-04 |
Pos logit contributions | |
ich | +0.024 |
opsy | +0.021 |
field | +0.020 |
ster | +0.020 |
flower | +0.019 |
Neg logit contributions | |
baths | -0.018 |
sc | -0.017 |
tant | -0.017 |
videos | -0.017 |
tests | -0.017 |
Token | goes |
Token ID | 2925 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
ich | +0.002 |
opsy | +0.001 |
field | +0.001 |
ster | +0.001 |
sters | +0.001 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
baths | -0.001 |
taker | -0.001 |
igsaw | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.54e-03 |
Pos logit contributions | |
tant | +0.020 |
aids | +0.018 |
baths | +0.018 |
sc | +0.018 |
videos | +0.017 |
Neg logit contributions | |
ich | -0.037 |
field | -0.032 |
opsy | -0.032 |
ster | -0.031 |
flower | -0.029 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
sc | +0.002 |
tant | +0.002 |
baths | +0.002 |
igators | +0.002 |
taker | +0.002 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
wife | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
ich | +0.031 |
opsy | +0.027 |
field | +0.026 |
ster | +0.025 |
flower | +0.023 |
Neg logit contributions | |
tant | -0.030 |
sc | -0.029 |
baths | -0.028 |
taker | -0.027 |
videos | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
igators | +0.005 |
baths | +0.005 |
igator | +0.004 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.006 |
� | -0.006 |
field | -0.006 |
ster | -0.005 |
Token | says |
Token ID | 1139 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ich | +0.019 |
opsy | +0.017 |
field | +0.016 |
ster | +0.015 |
sters | +0.014 |
Neg logit contributions | |
tant | -0.014 |
sc | -0.014 |
baths | -0.014 |
videos | -0.013 |
taker | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
ich | +0.032 |
ster | +0.028 |
opsy | +0.027 |
sters | +0.026 |
� | +0.025 |
Neg logit contributions | |
sc | -0.035 |
tant | -0.032 |
| | -0.031 |
channel | -0.030 |
igators | -0.030 |
Token | over |
Token ID | 625 |
Feature activation | +4.41e-03 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.004 |
aids | +0.004 |
tests | +0.004 |
baths | +0.004 |
Neg logit contributions | |
ich | -0.010 |
opsy | -0.009 |
field | -0.009 |
ster | -0.009 |
� | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
ich | +0.011 |
opsy | +0.010 |
field | +0.009 |
ster | +0.009 |
flower | +0.008 |
Neg logit contributions | |
tant | -0.005 |
sc | -0.005 |
baths | -0.005 |
videos | -0.005 |
aids | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ich | +0.010 |
opsy | +0.009 |
field | +0.009 |
ster | +0.009 |
sters | +0.008 |
Neg logit contributions | |
baths | -0.003 |
bang | -0.003 |
Lily | -0.002 |
videos | -0.002 |
around | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e-03 |
Pos logit contributions | |
sc | +0.016 |
baths | +0.016 |
tant | +0.016 |
videos | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.029 |
opsy | -0.026 |
field | -0.024 |
ster | -0.024 |
sters | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
baths | +0.002 |
sc | +0.002 |
tant | +0.002 |
videos | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
flower | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
ich | +0.032 |
opsy | +0.029 |
ster | +0.027 |
field | +0.027 |
sters | +0.025 |
Neg logit contributions | |
tant | -0.023 |
sc | -0.023 |
videos | -0.022 |
baths | -0.022 |
tests | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +6.18e-04 |
Pos logit contributions | |
sc | +0.006 |
tant | +0.005 |
igators | +0.005 |
taker | +0.005 |
tests | +0.005 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.009 |
ster | -0.009 |
wife | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ich | +0.001 |
opsy | +0.001 |
field | +0.001 |
ster | +0.001 |
� | +0.001 |
Neg logit contributions | |
baths | -0.001 |
sc | -0.001 |
videos | -0.001 |
tant | -0.001 |
tests | -0.001 |
Token | voice |
Token ID | 3809 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
ich | +0.026 |
opsy | +0.024 |
field | +0.022 |
ster | +0.022 |
wife | +0.021 |
Neg logit contributions | |
sc | -0.018 |
tests | -0.017 |
tant | -0.016 |
igators | -0.016 |
aled | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
tant | +0.067 |
sc | +0.064 |
baths | +0.061 |
tests | +0.059 |
igators | +0.058 |
Neg logit contributions | |
ich | -0.066 |
ster | -0.054 |
opsy | -0.054 |
field | -0.051 |
flower | -0.049 |
Token | " |
Token ID | 366 |
Feature activation | -1.94e-03 |
Pos logit contributions | |
tant | +0.002 |
sc | +0.002 |
baths | +0.002 |
videos | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.004 |
field | -0.004 |
ster | -0.004 |
flower | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
ich | +0.021 |
opsy | +0.019 |
field | +0.018 |
ster | +0.017 |
flower | +0.016 |
Neg logit contributions | |
tant | -0.012 |
sc | -0.012 |
baths | -0.012 |
tests | -0.011 |
videos | -0.011 |
Token | Anna |
Token ID | 31160 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ich | +0.015 |
opsy | +0.013 |
field | +0.012 |
ster | +0.012 |
sters | +0.011 |
Neg logit contributions | |
sc | -0.011 |
tant | -0.011 |
baths | -0.010 |
videos | -0.010 |
tests | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
sc | +0.016 |
baths | +0.016 |
tant | +0.015 |
around | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.035 |
opsy | -0.031 |
field | -0.030 |
ster | -0.028 |
sters | -0.028 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
baths | +0.001 |
tant | +0.001 |
videos | +0.001 |
sc | +0.001 |
Lily | +0.001 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
sters | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
ich | +0.012 |
opsy | +0.011 |
field | +0.010 |
ster | +0.010 |
sters | +0.009 |
Neg logit contributions | |
baths | -0.005 |
Lily | -0.005 |
around | -0.005 |
bang | -0.005 |
sc | -0.005 |
Token | twins |
Token ID | 20345 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
sc | +0.025 |
tant | +0.025 |
baths | +0.024 |
tests | +0.023 |
videos | +0.023 |
Neg logit contributions | |
ich | -0.033 |
opsy | -0.029 |
field | -0.027 |
ster | -0.026 |
flower | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-04 |
Pos logit contributions | |
ich | +0.018 |
opsy | +0.017 |
field | +0.016 |
ster | +0.016 |
sters | +0.015 |
Neg logit contributions | |
around | -0.006 |
baths | -0.006 |
videos | -0.006 |
tant | -0.006 |
tests | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
tant | +0.000 |
sc | +0.000 |
tests | +0.000 |
taker | +0.000 |
baths | +0.000 |
Neg logit contributions | |
opsy | -0.001 |
ich | -0.001 |
field | -0.000 |
� | -0.000 |
flower | -0.000 |
Token | like |
Token ID | 588 |
Feature activation | +6.65e-03 |
Pos logit contributions | |
ich | +0.031 |
opsy | +0.029 |
field | +0.027 |
ster | +0.026 |
flower | +0.025 |
Neg logit contributions | |
tant | -0.018 |
sc | -0.017 |
baths | -0.016 |
tests | -0.016 |
videos | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ich | +0.016 |
opsy | +0.014 |
field | +0.014 |
ster | +0.013 |
wife | +0.013 |
Neg logit contributions | |
sc | -0.007 |
tant | -0.007 |
taker | -0.006 |
igsaw | -0.006 |
baths | -0.006 |
Token | play |
Token ID | 711 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
ich | +0.020 |
opsy | +0.019 |
field | +0.018 |
wife | +0.017 |
flower | +0.017 |
Neg logit contributions | |
sc | -0.021 |
tant | -0.020 |
taker | -0.018 |
aback | -0.017 |
baths | -0.017 |
Token | ran |
Token ID | 4966 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
tant | +0.021 |
sc | +0.020 |
baths | +0.020 |
videos | +0.019 |
tests | +0.019 |
Neg logit contributions | |
ich | -0.023 |
opsy | -0.020 |
field | -0.019 |
ster | -0.019 |
flower | -0.017 |
Token | outside |
Token ID | 2354 |
Feature activation | -6.21e-04 |
Pos logit contributions | |
tant | +0.013 |
aids | +0.013 |
igators | +0.012 |
igsaw | +0.011 |
igator | +0.011 |
Neg logit contributions | |
ich | -0.012 |
field | -0.010 |
� | -0.010 |
opsy | -0.009 |
wife | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -6.69e-04 |
Pos logit contributions | |
tant | +0.001 |
sc | +0.001 |
igators | +0.001 |
baths | +0.001 |
tests | +0.001 |
Neg logit contributions | |
ich | -0.001 |
field | -0.001 |
opsy | -0.001 |
ster | -0.001 |
flower | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
tant | +0.001 |
aids | +0.001 |
sc | +0.001 |
igsaw | +0.001 |
videos | +0.001 |
Neg logit contributions | |
ich | -0.001 |
field | -0.001 |
opsy | -0.001 |
ster | -0.001 |
� | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -8.26e-03 |
Pos logit contributions | |
ich | +0.014 |
opsy | +0.013 |
field | +0.012 |
ster | +0.011 |
� | +0.010 |
Neg logit contributions | |
tant | -0.017 |
videos | -0.016 |
sc | -0.016 |
baths | -0.016 |
igsaw | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | +7.65e-03 |
Pos logit contributions | |
sc | +0.013 |
tant | +0.012 |
igsaw | +0.011 |
videos | +0.011 |
baths | +0.010 |
Neg logit contributions | |
ich | -0.018 |
opsy | -0.015 |
field | -0.015 |
ster | -0.014 |
ese | -0.013 |
Token | wet |
Token ID | 9583 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
ich | +0.013 |
opsy | +0.011 |
field | +0.010 |
ster | +0.010 |
� | +0.010 |
Neg logit contributions | |
sc | -0.015 |
tant | -0.014 |
videos | -0.014 |
baths | -0.013 |
tests | -0.013 |
Token | ! |
Token ID | 0 |
Feature activation | -7.25e-03 |
Pos logit contributions | |
ich | +0.002 |
field | +0.002 |
opsy | +0.002 |
ster | +0.002 |
flower | +0.002 |
Neg logit contributions | |
tant | -0.002 |
sc | -0.002 |
aids | -0.002 |
tests | -0.002 |
videos | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
sc | +0.008 |
tant | +0.008 |
baths | +0.007 |
igators | +0.007 |
bang | +0.007 |
Neg logit contributions | |
ich | -0.016 |
field | -0.015 |
opsy | -0.015 |
� | -0.014 |
ama | -0.014 |
Token | yelled |
Token ID | 22760 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.006 |
field | +0.006 |
ster | +0.006 |
remembered | +0.005 |
Neg logit contributions | |
igsaw | -0.008 |
tant | -0.008 |
sc | -0.008 |
videos | -0.008 |
baths | -0.007 |
Token | from |
Token ID | 422 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
ich | +0.010 |
ster | +0.009 |
opsy | +0.008 |
� | +0.008 |
sters | +0.007 |
Neg logit contributions | |
igators | -0.010 |
sc | -0.010 |
tant | -0.009 |
bench | -0.009 |
igator | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
ich | +0.018 |
opsy | +0.016 |
ster | +0.016 |
field | +0.015 |
� | +0.014 |
Neg logit contributions | |
sc | -0.017 |
tant | -0.017 |
igators | -0.017 |
tests | -0.016 |
baths | -0.016 |
Token | giving |
Token ID | 3501 |
Feature activation | -4.82e-03 |
Pos logit contributions | |
sc | +0.007 |
tant | +0.007 |
baths | +0.007 |
tests | +0.007 |
videos | +0.006 |
Neg logit contributions | |
ich | -0.010 |
opsy | -0.009 |
field | -0.008 |
ster | -0.008 |
flower | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | -4.24e-03 |
Pos logit contributions | |
sc | +0.007 |
tant | +0.007 |
bang | +0.006 |
tests | +0.006 |
igators | +0.006 |
Neg logit contributions | |
ich | -0.010 |
opsy | -0.009 |
ster | -0.009 |
field | -0.008 |
ese | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
sc | +0.004 |
tant | +0.004 |
videos | +0.004 |
baths | +0.004 |
bang | +0.004 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.009 |
ster | -0.009 |
ese | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
sc | +0.021 |
tant | +0.020 |
baths | +0.020 |
videos | +0.019 |
tests | +0.019 |
Neg logit contributions | |
ich | -0.053 |
opsy | -0.049 |
field | -0.047 |
ster | -0.046 |
flower | -0.043 |
Token | hug |
Token ID | 16225 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
sc | +0.017 |
baths | +0.017 |
tant | +0.016 |
videos | +0.016 |
igators | +0.016 |
Neg logit contributions | |
ich | -0.027 |
opsy | -0.025 |
field | -0.024 |
ster | -0.023 |
flower | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
ich | +0.050 |
opsy | +0.042 |
field | +0.042 |
ster | +0.042 |
flower | +0.038 |
Neg logit contributions | |
tant | -0.039 |
baths | -0.039 |
sc | -0.039 |
tests | -0.037 |
videos | -0.037 |
Token | |
Token ID | 220 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
sc | +0.003 |
baths | +0.003 |
tant | +0.003 |
videos | +0.003 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.010 |
ster | -0.010 |
flower | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
ich | +0.022 |
opsy | +0.020 |
field | +0.019 |
ster | +0.018 |
flower | +0.017 |
Neg logit contributions | |
tant | -0.013 |
sc | -0.013 |
baths | -0.013 |
videos | -0.012 |
tests | -0.012 |
Token | Jack |
Token ID | 14295 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
ich | +0.003 |
opsy | +0.002 |
field | +0.002 |
ster | +0.002 |
flower | +0.002 |
Neg logit contributions | |
sc | -0.001 |
baths | -0.001 |
videos | -0.001 |
tant | -0.001 |
tests | -0.001 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
tant | +0.003 |
baths | +0.002 |
sc | +0.002 |
bang | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.004 |
field | -0.003 |
ster | -0.003 |
sters | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
tant | +0.039 |
sc | +0.038 |
baths | +0.037 |
videos | +0.036 |
tests | +0.035 |
Neg logit contributions | |
ich | -0.050 |
opsy | -0.044 |
field | -0.043 |
ster | -0.041 |
sters | -0.038 |
Token | secrets |
Token ID | 13141 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
ich | +0.017 |
opsy | +0.014 |
field | +0.014 |
ster | +0.014 |
sters | +0.013 |
Neg logit contributions | |
tant | -0.012 |
sc | -0.012 |
igsaw | -0.011 |
bench | -0.011 |
baths | -0.011 |
Token | or |
Token ID | 393 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
tant | +0.005 |
baths | +0.005 |
sc | +0.004 |
videos | +0.004 |
bang | +0.004 |
Neg logit contributions | |
ich | -0.006 |
field | -0.005 |
opsy | -0.005 |
ster | -0.005 |
sters | -0.004 |
Token | treasures |
Token ID | 29561 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
ich | +0.048 |
field | +0.041 |
ster | +0.041 |
opsy | +0.040 |
sters | +0.039 |
Neg logit contributions | |
sc | -0.037 |
tant | -0.034 |
igsaw | -0.033 |
bench | -0.032 |
iren | -0.032 |
Token | or |
Token ID | 393 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
ich | +0.007 |
field | +0.006 |
opsy | +0.006 |
ster | +0.006 |
sters | +0.005 |
Neg logit contributions | |
tant | -0.006 |
sc | -0.006 |
baths | -0.006 |
videos | -0.005 |
tests | -0.005 |
Token | magic |
Token ID | 5536 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ich | +0.047 |
ster | +0.041 |
field | +0.041 |
opsy | +0.040 |
sters | +0.040 |
Neg logit contributions | |
sc | -0.038 |
tant | -0.034 |
igsaw | -0.034 |
bench | -0.034 |
iren | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
tant | +0.033 |
baths | +0.032 |
sc | +0.032 |
igsaw | +0.030 |
showers | +0.030 |
Neg logit contributions | |
ich | -0.036 |
ster | -0.032 |
field | -0.031 |
opsy | -0.030 |
sters | -0.030 |
Token | there |
Token ID | 612 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ich | +0.034 |
field | +0.030 |
opsy | +0.029 |
ster | +0.028 |
pearl | +0.026 |
Neg logit contributions | |
sc | -0.030 |
tant | -0.027 |
taker | -0.026 |
baths | -0.026 |
lic | -0.025 |
Token | ," |
Token ID | 553 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
tant | +0.031 |
sc | +0.030 |
baths | +0.030 |
videos | +0.028 |
tests | +0.028 |
Neg logit contributions | |
ich | -0.042 |
opsy | -0.037 |
field | -0.036 |
ster | -0.034 |
flower | -0.032 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ich | +0.033 |
opsy | +0.030 |
field | +0.028 |
ster | +0.027 |
� | +0.025 |
Neg logit contributions | |
sc | -0.021 |
tant | -0.020 |
baths | -0.019 |
tests | -0.018 |
videos | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
tant | +0.028 |
baths | +0.028 |
sc | +0.028 |
showers | +0.027 |
tests | +0.027 |
Neg logit contributions | |
ich | -0.021 |
opsy | -0.019 |
field | -0.018 |
ster | -0.018 |
sters | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.23e-03 |
Pos logit contributions | |
ich | +0.009 |
opsy | +0.007 |
ster | +0.007 |
field | +0.007 |
sters | +0.007 |
Neg logit contributions | |
tant | -0.013 |
sc | -0.012 |
igsaw | -0.012 |
aids | -0.012 |
igators | -0.012 |
Token | His |
Token ID | 2399 |
Feature activation | -6.86e-04 |
Pos logit contributions | |
sc | +0.008 |
tant | +0.008 |
baths | +0.008 |
tests | +0.008 |
videos | +0.008 |
Neg logit contributions | |
ich | -0.017 |
opsy | -0.016 |
field | -0.015 |
ster | -0.014 |
� | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
tant | +0.001 |
baths | +0.001 |
sc | +0.001 |
tests | +0.001 |
videos | +0.001 |
Neg logit contributions | |
ich | -0.001 |
opsy | -0.001 |
field | -0.001 |
ster | -0.001 |
sters | -0.001 |
Token | told |
Token ID | 1297 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
tant | +0.004 |
sc | +0.004 |
baths | +0.004 |
videos | +0.004 |
tests | +0.004 |
Neg logit contributions | |
ich | -0.006 |
opsy | -0.005 |
field | -0.005 |
ster | -0.005 |
flower | -0.004 |
Token | him |
Token ID | 683 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
sc | +0.029 |
tant | +0.026 |
channel | +0.024 |
riend | +0.024 |
igsaw | +0.023 |
Neg logit contributions | |
ich | -0.021 |
opsy | -0.020 |
ese | -0.018 |
iri | -0.017 |
ama | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
sc | +0.030 |
tant | +0.030 |
channel | +0.025 |
aled | +0.024 |
igators | +0.024 |
Neg logit contributions | |
ich | -0.039 |
opsy | -0.035 |
ster | -0.033 |
field | -0.032 |
ama | -0.031 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
tant | +0.036 |
sc | +0.036 |
videos | +0.033 |
baths | +0.033 |
tests | +0.032 |
Neg logit contributions | |
ich | -0.045 |
opsy | -0.042 |
field | -0.039 |
ster | -0.036 |
flower | -0.034 |
Token | inside |
Token ID | 2641 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
ich | +0.029 |
opsy | +0.027 |
field | +0.025 |
ster | +0.025 |
flower | +0.023 |
Neg logit contributions | |
tant | -0.013 |
sc | -0.013 |
baths | -0.012 |
videos | -0.012 |
tests | -0.012 |
Token | until |
Token ID | 1566 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
sc | +0.009 |
tant | +0.009 |
baths | +0.008 |
videos | +0.008 |
bang | +0.008 |
Neg logit contributions | |
ich | -0.012 |
opsy | -0.011 |
field | -0.011 |
ster | -0.010 |
flower | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -2.27e-04 |
Pos logit contributions | |
tant | +0.021 |
sc | +0.021 |
baths | +0.020 |
videos | +0.019 |
tests | +0.019 |
Neg logit contributions | |
ich | -0.047 |
opsy | -0.043 |
field | -0.041 |
ster | -0.040 |
flower | -0.037 |
Token | felt |
Token ID | 2936 |
Feature activation | -6.21e-03 |
Pos logit contributions | |
sc | +0.000 |
baths | +0.000 |
tant | +0.000 |
tests | +0.000 |
Lily | +0.000 |
Neg logit contributions | |
ich | -0.001 |
opsy | -0.000 |
field | -0.000 |
ster | -0.000 |
sters | -0.000 |
Token | Maybe |
Token ID | 13300 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
baths | +0.012 |
tant | +0.012 |
sc | +0.012 |
videos | +0.012 |
tests | +0.012 |
Neg logit contributions | |
ich | -0.013 |
opsy | -0.011 |
field | -0.011 |
ster | -0.010 |
flower | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
baths | +0.014 |
sc | +0.014 |
tant | +0.014 |
tests | +0.013 |
videos | +0.013 |
Neg logit contributions | |
ich | -0.036 |
opsy | -0.033 |
field | -0.031 |
ster | -0.030 |
flower | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
tant | +0.021 |
baths | +0.020 |
videos | +0.020 |
igsaw | +0.020 |
sc | +0.020 |
Neg logit contributions | |
ich | -0.023 |
opsy | -0.020 |
field | -0.019 |
ster | -0.018 |
flower | -0.018 |
Token | just |
Token ID | 655 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.004 |
igsaw | +0.004 |
baths | +0.004 |
taker | +0.004 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
field | -0.006 |
ster | -0.006 |
ese | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ich | +0.048 |
opsy | +0.042 |
field | +0.041 |
ster | +0.039 |
flower | +0.037 |
Neg logit contributions | |
sc | -0.032 |
tant | -0.032 |
igsaw | -0.027 |
bench | -0.026 |
baths | -0.026 |
Token | big |
Token ID | 1263 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
sc | +0.015 |
tant | +0.014 |
baths | +0.014 |
videos | +0.014 |
tests | +0.013 |
Neg logit contributions | |
ich | -0.022 |
opsy | -0.019 |
field | -0.018 |
ster | -0.018 |
flower | -0.016 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
sc | +0.036 |
tant | +0.034 |
baths | +0.034 |
tests | +0.032 |
videos | +0.032 |
Neg logit contributions | |
ich | -0.039 |
opsy | -0.034 |
field | -0.033 |
ster | -0.032 |
flower | -0.030 |
Token | ." |
Token ID | 526 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
ich | +0.021 |
opsy | +0.018 |
ster | +0.018 |
field | +0.018 |
pper | +0.016 |
Neg logit contributions | |
tant | -0.018 |
baths | -0.016 |
sc | -0.016 |
tests | -0.015 |
videos | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
sc | +0.007 |
tant | +0.007 |
baths | +0.007 |
tests | +0.007 |
videos | +0.007 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.015 |
field | -0.014 |
ster | -0.014 |
flower | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-04 |
Pos logit contributions | |
loud | +0.005 |
sc | +0.005 |
baths | +0.005 |
tant | +0.005 |
Lily | +0.005 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.015 |
field | -0.014 |
ster | -0.014 |
flower | -0.014 |
Token | " |
Token ID | 1 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
loud | +0.000 |
Lily | +0.000 |
If | +0.000 |
sc | +0.000 |
traffic | +0.000 |
Neg logit contributions | |
ich | -0.000 |
opsy | -0.000 |
field | -0.000 |
flower | -0.000 |
ster | -0.000 |
Token | flowers |
Token ID | 12734 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
ich | +0.001 |
opsy | +0.001 |
field | +0.001 |
ster | +0.001 |
sters | +0.001 |
Neg logit contributions | |
sc | -0.001 |
tant | -0.001 |
baths | -0.001 |
videos | -0.001 |
bang | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
ich | +0.079 |
opsy | +0.071 |
field | +0.068 |
ster | +0.065 |
sters | +0.061 |
Neg logit contributions | |
sc | -0.043 |
tant | -0.043 |
baths | -0.042 |
videos | -0.040 |
tests | -0.040 |
Token | M |
Token ID | 337 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
baths | +0.001 |
sc | +0.001 |
tant | +0.001 |
videos | +0.001 |
tests | +0.001 |
Neg logit contributions | |
ich | -0.003 |
opsy | -0.003 |
field | -0.003 |
ster | -0.003 |
sters | -0.003 |
Token | imi |
Token ID | 25236 |
Feature activation | -2.69e-04 |
Pos logit contributions | |
baths | +0.002 |
tant | +0.002 |
videos | +0.002 |
tests | +0.002 |
sc | +0.002 |
Neg logit contributions | |
ich | -0.002 |
field | -0.002 |
ster | -0.002 |
opsy | -0.002 |
� | -0.002 |
Token | carried |
Token ID | 5281 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
baths | +0.000 |
sc | +0.000 |
tests | +0.000 |
around | +0.000 |
videos | +0.000 |
Neg logit contributions | |
ich | -0.001 |
opsy | -0.001 |
field | -0.001 |
ster | -0.000 |
iri | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
tant | +0.027 |
bench | +0.026 |
aids | +0.025 |
riend | +0.025 |
crashes | +0.024 |
Neg logit contributions | |
opsy | -0.031 |
ich | -0.030 |
field | -0.027 |
ster | -0.026 |
flower | -0.025 |
Token | honey |
Token ID | 12498 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
sc | +0.026 |
baths | +0.026 |
tests | +0.025 |
around | +0.024 |
loud | +0.024 |
Neg logit contributions | |
ich | -0.037 |
opsy | -0.033 |
field | -0.031 |
ster | -0.030 |
ipper | -0.029 |
Token | from |
Token ID | 422 |
Feature activation | -8.16e-03 |
Pos logit contributions | |
ich | +0.014 |
opsy | +0.013 |
field | +0.012 |
ster | +0.012 |
flower | +0.011 |
Neg logit contributions | |
tant | -0.008 |
baths | -0.007 |
sc | -0.007 |
videos | -0.007 |
tests | -0.007 |
Token | one |
Token ID | 530 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
sc | +0.013 |
tant | +0.012 |
taker | +0.011 |
baths | +0.011 |
head | +0.010 |
Neg logit contributions | |
ich | -0.017 |
field | -0.016 |
opsy | -0.016 |
ster | -0.013 |
flower | -0.013 |
Token | flower |
Token ID | 15061 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
ich | +0.006 |
opsy | +0.005 |
field | +0.005 |
ster | +0.005 |
flower | +0.004 |
Neg logit contributions | |
tant | -0.005 |
sc | -0.005 |
baths | -0.005 |
videos | -0.005 |
tests | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
ich | +0.009 |
opsy | +0.008 |
field | +0.008 |
ster | +0.008 |
flower | +0.007 |
Neg logit contributions | |
tant | -0.004 |
sc | -0.004 |
baths | -0.004 |
videos | -0.004 |
tests | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
sc | +0.018 |
tant | +0.017 |
taker | +0.015 |
igators | +0.015 |
videos | +0.014 |
Neg logit contributions | |
ich | -0.027 |
opsy | -0.024 |
field | -0.024 |
ster | -0.022 |
flower | -0.021 |
Token | sand |
Token ID | 6450 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
sc | +0.005 |
tant | +0.005 |
baths | +0.005 |
videos | +0.004 |
tests | +0.004 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.007 |
field | -0.007 |
ster | -0.006 |
flower | -0.006 |
Token | castle |
Token ID | 16669 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ich | +0.036 |
opsy | +0.032 |
field | +0.031 |
ster | +0.030 |
flower | +0.028 |
Neg logit contributions | |
tant | -0.025 |
sc | -0.024 |
baths | -0.024 |
videos | -0.023 |
tests | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
tant | +0.035 |
sc | +0.032 |
baths | +0.032 |
videos | +0.032 |
bang | +0.031 |
Neg logit contributions | |
ich | -0.039 |
field | -0.034 |
opsy | -0.032 |
ster | -0.031 |
flower | -0.029 |
Token | Mama |
Token ID | 40084 |
Feature activation | +6.43e-03 |
Pos logit contributions | |
tant | +0.001 |
sc | +0.001 |
baths | +0.001 |
videos | +0.001 |
tests | +0.001 |
Neg logit contributions | |
ich | -0.003 |
opsy | -0.003 |
field | -0.003 |
ster | -0.002 |
flower | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
ich | +0.013 |
opsy | +0.012 |
field | +0.011 |
ster | +0.011 |
flower | +0.010 |
Neg logit contributions | |
tant | -0.010 |
sc | -0.010 |
baths | -0.010 |
videos | -0.009 |
tests | -0.009 |
Token | Mia |
Token ID | 32189 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
sc | +0.055 |
tant | +0.052 |
baths | +0.049 |
tests | +0.049 |
videos | +0.048 |
Neg logit contributions | |
ich | -0.087 |
opsy | -0.082 |
field | -0.077 |
ster | -0.073 |
flower | -0.070 |
Token | stayed |
Token ID | 9658 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ich | +0.012 |
opsy | +0.010 |
field | +0.010 |
ster | +0.010 |
sters | +0.009 |
Neg logit contributions | |
sc | -0.007 |
baths | -0.007 |
tant | -0.007 |
bang | -0.007 |
around | -0.007 |
Token | at |
Token ID | 379 |
Feature activation | +2.88e-04 |
Pos logit contributions | |
ich | +0.034 |
opsy | +0.031 |
field | +0.029 |
ster | +0.028 |
sters | +0.027 |
Neg logit contributions | |
tant | -0.014 |
baths | -0.014 |
sc | -0.014 |
videos | -0.013 |
tests | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -2.05e-03 |
Pos logit contributions | |
ich | +0.001 |
opsy | +0.001 |
field | +0.001 |
ster | +0.001 |
flower | +0.001 |
Neg logit contributions | |
sc | -0.000 |
tant | -0.000 |
baths | -0.000 |
videos | -0.000 |
tests | -0.000 |
Token | beach |
Token ID | 10481 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
tant | +0.004 |
sc | +0.004 |
baths | +0.004 |
videos | +0.004 |
tests | +0.004 |
Neg logit contributions | |
ich | -0.003 |
opsy | -0.003 |
field | -0.003 |
ster | -0.002 |
flower | -0.002 |
Token | this |
Token ID | 428 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.005 |
bench | +0.004 |
tests | +0.004 |
aids | +0.004 |
Neg logit contributions | |
ich | -0.005 |
opsy | -0.004 |
field | -0.004 |
ster | -0.004 |
wife | -0.004 |
Token | crib |
Token ID | 48083 |
Feature activation | -9.39e-03 |
Pos logit contributions | |
tant | +0.017 |
sc | +0.016 |
videos | +0.015 |
baths | +0.015 |
tests | +0.015 |
Neg logit contributions | |
ich | -0.020 |
field | -0.018 |
opsy | -0.017 |
ster | -0.016 |
� | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
tant | +0.017 |
baths | +0.017 |
sc | +0.016 |
videos | +0.016 |
tests | +0.016 |
Neg logit contributions | |
ich | -0.016 |
field | -0.014 |
opsy | -0.014 |
ster | -0.013 |
flower | -0.012 |
Token | just |
Token ID | 655 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
tant | +0.005 |
sc | +0.004 |
baths | +0.004 |
tests | +0.004 |
videos | +0.004 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.006 |
field | -0.006 |
ster | -0.006 |
flower | -0.005 |
Token | as |
Token ID | 355 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ich | +0.050 |
field | +0.044 |
opsy | +0.043 |
ster | +0.040 |
flower | +0.040 |
Neg logit contributions | |
tant | -0.039 |
sc | -0.037 |
tests | -0.032 |
baths | -0.032 |
iren | -0.032 |
Token | wide |
Token ID | 3094 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
ich | +0.047 |
opsy | +0.042 |
field | +0.042 |
ster | +0.039 |
wife | +0.037 |
Neg logit contributions | |
tant | -0.030 |
sc | -0.027 |
aids | -0.026 |
aled | -0.025 |
bang | -0.025 |
Token | as |
Token ID | 355 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
tant | +0.116 |
sc | +0.109 |
aids | +0.107 |
rage | +0.104 |
tests | +0.100 |
Neg logit contributions | |
ich | -0.100 |
ster | -0.082 |
opsy | -0.082 |
field | -0.081 |
sters | -0.079 |
Token | my |
Token ID | 616 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
ich | +0.029 |
opsy | +0.025 |
field | +0.025 |
ster | +0.023 |
sters | +0.021 |
Neg logit contributions | |
tant | -0.020 |
sc | -0.018 |
aids | -0.017 |
baths | -0.017 |
bang | -0.016 |
Token | old |
Token ID | 1468 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
sc | +0.010 |
tant | +0.010 |
videos | +0.009 |
igators | +0.009 |
bang | +0.009 |
Neg logit contributions | |
ich | -0.014 |
opsy | -0.013 |
field | -0.012 |
ster | -0.011 |
wife | -0.011 |
Token | one |
Token ID | 530 |
Feature activation | -6.38e-03 |
Pos logit contributions | |
sc | +0.065 |
tant | +0.063 |
videos | +0.058 |
baths | +0.058 |
bang | +0.057 |
Neg logit contributions | |
ich | -0.095 |
field | -0.086 |
opsy | -0.085 |
ster | -0.080 |
flower | -0.076 |
Token | ," |
Token ID | 553 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
tant | +0.010 |
baths | +0.010 |
sc | +0.010 |
videos | +0.010 |
tests | +0.009 |
Neg logit contributions | |
ich | -0.012 |
field | -0.011 |
opsy | -0.011 |
ster | -0.010 |
flower | -0.009 |
Token | Jimmy |
Token ID | 40335 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ich | +0.021 |
opsy | +0.018 |
field | +0.017 |
ster | +0.016 |
sters | +0.015 |
Neg logit contributions | |
sc | -0.021 |
baths | -0.020 |
tant | -0.020 |
videos | -0.019 |
tests | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
ich | +0.026 |
opsy | +0.023 |
field | +0.022 |
ster | +0.021 |
sters | +0.020 |
Neg logit contributions | |
tant | -0.017 |
sc | -0.017 |
baths | -0.017 |
videos | -0.016 |
tests | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
sc | +0.014 |
tant | +0.014 |
baths | +0.013 |
igators | +0.012 |
tests | +0.012 |
Neg logit contributions | |
ich | -0.016 |
opsy | -0.014 |
field | -0.014 |
flower | -0.012 |
ster | -0.012 |
Token | 3 |
Token ID | 513 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
ich | +0.013 |
opsy | +0.012 |
field | +0.011 |
ster | +0.011 |
sters | +0.010 |
Neg logit contributions | |
tant | -0.005 |
sc | -0.005 |
baths | -0.005 |
videos | -0.005 |
tests | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
sc | +0.068 |
tant | +0.064 |
baths | +0.063 |
tests | +0.062 |
videos | +0.059 |
Neg logit contributions | |
ich | -0.106 |
opsy | -0.096 |
field | -0.089 |
ster | -0.088 |
flower | -0.084 |
Token | year |
Token ID | 1941 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
baths | +0.077 |
tant | +0.074 |
videos | +0.074 |
bang | +0.073 |
sc | +0.072 |
Neg logit contributions | |
ich | -0.144 |
opsy | -0.131 |
ster | -0.122 |
illa | -0.119 |
field | -0.115 |
Token | - |
Token ID | 12 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
sc | +0.138 |
bang | +0.125 |
tant | +0.125 |
videos | +0.125 |
baths | +0.122 |
Neg logit contributions | |
ich | -0.169 |
opsy | -0.152 |
ster | -0.147 |
field | -0.139 |
wife | -0.132 |
Token | old |
Token ID | 727 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
tant | +0.085 |
bang | +0.084 |
baths | +0.084 |
sc | +0.083 |
videos | +0.081 |
Neg logit contributions | |
ich | -0.118 |
opsy | -0.106 |
ster | -0.098 |
field | -0.094 |
illa | -0.094 |
Token | who |
Token ID | 508 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ich | +0.030 |
opsy | +0.026 |
field | +0.025 |
ster | +0.024 |
sters | +0.022 |
Neg logit contributions | |
tant | -0.022 |
sc | -0.022 |
baths | -0.022 |
videos | -0.021 |
tests | -0.021 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
ich | +0.019 |
opsy | +0.017 |
field | +0.017 |
ster | +0.015 |
� | +0.014 |
Neg logit contributions | |
tant | -0.023 |
sc | -0.022 |
videos | -0.021 |
baths | -0.021 |
igators | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ich | +0.011 |
field | +0.009 |
opsy | +0.009 |
ster | +0.008 |
flower | +0.008 |
Neg logit contributions | |
sc | -0.007 |
tant | -0.006 |
taker | -0.006 |
aled | -0.006 |
igators | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
tant | +0.045 |
sc | +0.042 |
baths | +0.041 |
aled | +0.040 |
igators | +0.040 |
Neg logit contributions | |
ich | -0.041 |
field | -0.035 |
opsy | -0.035 |
ster | -0.033 |
ama | -0.032 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.006 |
field | +0.006 |
ster | +0.005 |
flower | +0.005 |
Neg logit contributions | |
tant | -0.003 |
sc | -0.003 |
baths | -0.003 |
tests | -0.003 |
videos | -0.002 |
Token | took |
Token ID | 1718 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
ich | +0.059 |
opsy | +0.053 |
field | +0.051 |
ster | +0.048 |
sters | +0.046 |
Neg logit contributions | |
sc | -0.030 |
baths | -0.029 |
tant | -0.028 |
bang | -0.027 |
videos | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
sc | +0.010 |
tant | +0.010 |
riend | +0.010 |
bench | +0.009 |
ult | +0.009 |
Neg logit contributions | |
ich | -0.008 |
opsy | -0.008 |
ster | -0.007 |
wife | -0.006 |
ese | -0.006 |
Token | monster |
Token ID | 9234 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
sc | +0.029 |
tant | +0.029 |
baths | +0.028 |
igators | +0.027 |
videos | +0.027 |
Neg logit contributions | |
ich | -0.040 |
ster | -0.034 |
opsy | -0.033 |
field | -0.032 |
flower | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
tant | +0.030 |
sc | +0.029 |
baths | +0.029 |
tests | +0.028 |
videos | +0.028 |
Neg logit contributions | |
ich | -0.050 |
opsy | -0.043 |
ster | -0.043 |
field | -0.043 |
flower | -0.040 |
Token | ch |
Token ID | 354 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
tant | +0.113 |
videos | +0.112 |
baths | +0.110 |
sc | +0.106 |
bang | +0.106 |
Neg logit contributions | |
ich | -0.129 |
opsy | -0.110 |
ster | -0.105 |
field | -0.102 |
flower | -0.098 |
Token | aser |
Token ID | 6005 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
tant | +0.048 |
tests | +0.046 |
sc | +0.046 |
videos | +0.045 |
baths | +0.044 |
Neg logit contributions | |
ich | -0.073 |
opsy | -0.064 |
field | -0.060 |
ster | -0.059 |
pper | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
tant | +0.027 |
baths | +0.026 |
tests | +0.026 |
videos | +0.026 |
sc | +0.025 |
Neg logit contributions | |
ich | -0.029 |
field | -0.025 |
ster | -0.025 |
opsy | -0.024 |
flower | -0.022 |
Token | bed |
Token ID | 3996 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ich | +0.007 |
opsy | +0.006 |
field | +0.006 |
ster | +0.006 |
pper | +0.005 |
Neg logit contributions | |
sc | -0.005 |
tant | -0.005 |
baths | -0.004 |
igators | -0.004 |
taker | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -3.64e-03 |
Pos logit contributions | |
igators | +0.042 |
sc | +0.042 |
tant | +0.041 |
baths | +0.041 |
tests | +0.040 |
Neg logit contributions | |
ich | -0.046 |
field | -0.039 |
ster | -0.038 |
opsy | -0.037 |
sters | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +4.38e-04 |
Pos logit contributions | |
sc | +0.026 |
tant | +0.025 |
baths | +0.025 |
videos | +0.024 |
tests | +0.023 |
Neg logit contributions | |
ich | -0.052 |
opsy | -0.048 |
field | -0.045 |
ster | -0.044 |
sters | -0.041 |
Token | Every |
Token ID | 3887 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ich | +0.001 |
field | +0.001 |
opsy | +0.001 |
� | +0.001 |
ster | +0.001 |
Neg logit contributions | |
tant | -0.001 |
sc | -0.001 |
baths | -0.000 |
tests | -0.000 |
taker | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
ich | +0.036 |
opsy | +0.034 |
field | +0.033 |
ster | +0.030 |
flower | +0.028 |
Neg logit contributions | |
tant | -0.028 |
videos | -0.026 |
sc | -0.026 |
tests | -0.026 |
baths | -0.026 |
Token | two |
Token ID | 734 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
tant | +0.030 |
sc | +0.029 |
baths | +0.027 |
videos | +0.027 |
tests | +0.027 |
Neg logit contributions | |
ich | -0.042 |
opsy | -0.038 |
field | -0.036 |
ster | -0.035 |
� | -0.033 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
tant | +0.008 |
sc | +0.008 |
baths | +0.008 |
videos | +0.007 |
tests | +0.007 |
Neg logit contributions | |
ich | -0.011 |
opsy | -0.010 |
field | -0.010 |
ster | -0.009 |
flower | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
sc | +0.061 |
tant | +0.060 |
baths | +0.058 |
tests | +0.056 |
videos | +0.056 |
Neg logit contributions | |
ich | -0.116 |
opsy | -0.105 |
field | -0.099 |
ster | -0.098 |
sters | -0.092 |
Token | year |
Token ID | 1941 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
tant | +0.063 |
baths | +0.061 |
sc | +0.059 |
tests | +0.056 |
videos | +0.056 |
Neg logit contributions | |
ich | -0.172 |
opsy | -0.158 |
field | -0.149 |
ster | -0.148 |
illa | -0.142 |
Token | - |
Token ID | 12 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
sc | +0.148 |
tant | +0.133 |
bang | +0.132 |
tests | +0.131 |
videos | +0.131 |
Neg logit contributions | |
ich | -0.186 |
opsy | -0.165 |
ster | -0.158 |
field | -0.146 |
sters | -0.146 |
Token | old |
Token ID | 727 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
tant | +0.082 |
sc | +0.078 |
baths | +0.078 |
bang | +0.075 |
videos | +0.074 |
Neg logit contributions | |
ich | -0.137 |
opsy | -0.124 |
field | -0.116 |
ster | -0.115 |
illa | -0.109 |
Token | children |
Token ID | 1751 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
ich | +0.014 |
opsy | +0.013 |
field | +0.012 |
ster | +0.011 |
flower | +0.011 |
Neg logit contributions | |
sc | -0.009 |
tant | -0.009 |
baths | -0.009 |
videos | -0.009 |
tests | -0.008 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
ich | +0.015 |
opsy | +0.014 |
field | +0.013 |
ster | +0.012 |
flower | +0.012 |
Neg logit contributions | |
tant | -0.012 |
sc | -0.012 |
baths | -0.012 |
videos | -0.011 |
tests | -0.011 |
Token | but |
Token ID | 475 |
Feature activation | +1.72e-04 |
Pos logit contributions | |
tant | +0.051 |
igators | +0.050 |
baths | +0.047 |
igator | +0.046 |
aids | +0.046 |
Neg logit contributions | |
ich | -0.039 |
ster | -0.034 |
field | -0.034 |
opsy | -0.032 |
ble | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
ich | +0.000 |
opsy | +0.000 |
field | +0.000 |
ster | +0.000 |
� | +0.000 |
Neg logit contributions | |
sc | -0.000 |
tant | -0.000 |
videos | -0.000 |
baths | -0.000 |
tests | -0.000 |
Token | words |
Token ID | 2456 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
tant | +0.006 |
sc | +0.006 |
baths | +0.006 |
videos | +0.006 |
tests | +0.006 |
Neg logit contributions | |
ich | -0.007 |
opsy | -0.006 |
field | -0.006 |
ster | -0.006 |
flower | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
baths | +0.018 |
tant | +0.018 |
sc | +0.018 |
videos | +0.017 |
igsaw | +0.017 |
Neg logit contributions | |
ich | -0.017 |
field | -0.015 |
opsy | -0.015 |
ster | -0.014 |
flower | -0.013 |
Token | too |
Token ID | 1165 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
sc | +0.017 |
tant | +0.016 |
baths | +0.015 |
head | +0.014 |
| | +0.014 |
Neg logit contributions | |
ich | -0.023 |
field | -0.020 |
opsy | -0.019 |
ster | -0.018 |
flower | -0.018 |
Token | complicated |
Token ID | 8253 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
ich | +0.013 |
opsy | +0.012 |
field | +0.011 |
ster | +0.011 |
� | +0.011 |
Neg logit contributions | |
sc | -0.006 |
baths | -0.005 |
tant | -0.005 |
aled | -0.005 |
igators | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
tant | +0.130 |
igators | +0.118 |
baths | +0.117 |
igator | +0.116 |
sc | +0.116 |
Neg logit contributions | |
ich | -0.095 |
ster | -0.080 |
field | -0.077 |
sters | -0.072 |
opsy | -0.069 |
Token | him |
Token ID | 683 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
sc | +0.036 |
tant | +0.035 |
baths | +0.030 |
igators | +0.029 |
tests | +0.029 |
Neg logit contributions | |
ich | -0.059 |
opsy | -0.054 |
field | -0.053 |
ster | -0.050 |
sters | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
tant | +0.030 |
sc | +0.030 |
baths | +0.028 |
videos | +0.028 |
igators | +0.027 |
Neg logit contributions | |
ich | -0.041 |
opsy | -0.035 |
field | -0.035 |
ster | -0.034 |
sters | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
tant | +0.006 |
sc | +0.006 |
baths | +0.006 |
tests | +0.005 |
bang | +0.005 |
Neg logit contributions | |
ich | -0.012 |
opsy | -0.011 |
field | -0.011 |
ster | -0.010 |
� | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
tant | +0.003 |
sc | +0.003 |
baths | +0.003 |
videos | +0.002 |
tests | +0.002 |
Neg logit contributions | |
ich | -0.004 |
opsy | -0.004 |
field | -0.003 |
ster | -0.003 |
sters | -0.003 |