Token | hard |
Token ID | 1327 |
Feature activation | -1.21e-04 |
Pos logit contributions | |
ha | +0.003 |
Little | +0.002 |
few | +0.002 |
www | +0.002 |
unt | +0.002 |
Neg logit contributions | |
ishes | -0.003 |
unes | -0.003 |
anks | -0.003 |
ware | -0.003 |
fault | -0.003 |
Token | work |
Token ID | 670 |
Feature activation | -3.23e-03 |
Pos logit contributions | |
ha | +0.000 |
Little | +0.000 |
www | +0.000 |
Time | +0.000 |
ww | +0.000 |
Neg logit contributions | |
ware | -0.000 |
anks | -0.000 |
ishes | -0.000 |
unes | -0.000 |
fault | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.005 |
www | +0.005 |
ww | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.007 |
ware | -0.007 |
anks | -0.007 |
unes | -0.007 |
fault | -0.007 |
Token | bravery |
Token ID | 37808 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
ware | +0.008 |
ishes | +0.008 |
unes | +0.008 |
anks | +0.008 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.007 |
www | -0.006 |
Little | -0.006 |
ww | -0.006 |
unt | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
ishes | +0.005 |
anks | +0.005 |
ware | +0.005 |
unes | +0.005 |
fault | +0.005 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.003 |
www | -0.003 |
ww | -0.003 |
Time | -0.003 |
Token | cle |
Token ID | 1190 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
ishes | +0.013 |
anks | +0.013 |
ware | +0.013 |
unes | +0.013 |
fault | +0.013 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.009 |
www | -0.009 |
ww | -0.009 |
unt | -0.009 |
Token | vern |
Token ID | 933 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
ishes | +0.124 |
ware | +0.120 |
unes | +0.120 |
anks | +0.118 |
fault | +0.115 |
Neg logit contributions | |
ha | -0.195 |
Little | -0.175 |
www | -0.171 |
few | -0.169 |
ww | -0.168 |
Token | ess |
Token ID | 408 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
ishes | +0.143 |
ware | +0.141 |
unes | +0.138 |
anks | +0.135 |
fault | +0.131 |
Neg logit contributions | |
ha | -0.112 |
www | -0.093 |
Little | -0.093 |
ww | -0.092 |
few | -0.092 |
Token | ! |
Token ID | 0 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ha | +0.068 |
Little | +0.059 |
www | +0.057 |
few | +0.056 |
ww | +0.056 |
Neg logit contributions | |
ishes | -0.082 |
ware | -0.082 |
anks | -0.082 |
unes | -0.081 |
fault | -0.079 |
Token | From |
Token ID | 3574 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
anks | +0.043 |
ishes | +0.043 |
unes | +0.043 |
ware | +0.043 |
fault | +0.042 |
Neg logit contributions | |
ha | -0.030 |
Little | -0.026 |
www | -0.025 |
ww | -0.024 |
few | -0.024 |
Token | now |
Token ID | 783 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ishes | +0.049 |
anks | +0.048 |
ware | +0.048 |
unes | +0.047 |
fault | +0.046 |
Neg logit contributions | |
ha | -0.040 |
Little | -0.034 |
Time | -0.034 |
www | -0.033 |
few | -0.033 |
Token | friends |
Token ID | 2460 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
ishes | +0.017 |
ware | +0.017 |
unes | +0.017 |
anks | +0.017 |
fault | +0.017 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.013 |
www | -0.012 |
few | -0.012 |
ww | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
ishes | +0.020 |
ware | +0.020 |
anks | +0.020 |
unes | +0.020 |
fault | +0.019 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.013 |
www | -0.013 |
few | -0.012 |
ww | -0.012 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ware | +0.026 |
ishes | +0.026 |
unes | +0.025 |
anks | +0.025 |
fault | +0.024 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.013 |
Time | -0.012 |
unt | -0.012 |
few | -0.011 |
Token | praised |
Token ID | 15342 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ha | +0.030 |
Little | +0.026 |
www | +0.025 |
ww | +0.024 |
few | +0.024 |
Neg logit contributions | |
ishes | -0.047 |
anks | -0.047 |
unes | -0.047 |
ware | -0.047 |
fault | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | +3.67e-03 |
Pos logit contributions | |
ishes | +0.032 |
ware | +0.032 |
unes | +0.032 |
anks | +0.032 |
fault | +0.031 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.016 |
www | -0.015 |
few | -0.015 |
Time | -0.015 |
Token | cle |
Token ID | 1190 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
ishes | +0.007 |
anks | +0.007 |
ware | +0.007 |
unes | +0.007 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.007 |
Little | -0.006 |
www | -0.006 |
Time | -0.006 |
ww | -0.006 |
Token | vern |
Token ID | 933 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
ishes | +0.143 |
unes | +0.137 |
ware | +0.135 |
anks | +0.133 |
fault | +0.129 |
Neg logit contributions | |
ha | -0.178 |
Little | -0.155 |
www | -0.154 |
few | -0.151 |
ww | -0.150 |
Token | ess |
Token ID | 408 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ishes | +0.151 |
ware | +0.149 |
unes | +0.146 |
anks | +0.144 |
fault | +0.139 |
Neg logit contributions | |
ha | -0.124 |
Little | -0.105 |
www | -0.104 |
few | -0.103 |
ww | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
ha | +0.074 |
Little | +0.065 |
www | +0.063 |
few | +0.062 |
ww | +0.062 |
Neg logit contributions | |
ishes | -0.075 |
ware | -0.074 |
anks | -0.074 |
unes | -0.074 |
fault | -0.072 |
Token | eventually |
Token ID | 4191 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ishes | +0.021 |
anks | +0.021 |
ware | +0.021 |
unes | +0.021 |
fault | +0.020 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.013 |
www | -0.012 |
ww | -0.012 |
Time | -0.012 |
Token | Jan |
Token ID | 2365 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
anks | +0.024 |
ishes | +0.024 |
unes | +0.024 |
fault | +0.023 |
ware | +0.023 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.017 |
unt | -0.015 |
Time | -0.015 |
www | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ishes | +0.028 |
ware | +0.028 |
anks | +0.028 |
unes | +0.027 |
fault | +0.027 |
Neg logit contributions | |
ha | -0.021 |
Little | -0.018 |
www | -0.017 |
few | -0.017 |
ww | -0.017 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ishes | +0.032 |
ware | +0.032 |
anks | +0.031 |
unes | +0.031 |
fault | +0.030 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.015 |
Time | -0.013 |
www | -0.013 |
few | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ishes | +0.026 |
ware | +0.026 |
anks | +0.026 |
unes | +0.025 |
fault | +0.025 |
Neg logit contributions | |
ha | -0.021 |
Little | -0.018 |
www | -0.018 |
Time | -0.018 |
ww | -0.018 |
Token | used |
Token ID | 973 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
ha | +0.022 |
Little | +0.020 |
unt | +0.019 |
www | +0.019 |
ww | +0.019 |
Neg logit contributions | |
fault | -0.028 |
ware | -0.027 |
anks | -0.027 |
unes | -0.027 |
ishes | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | -1.34e-04 |
Pos logit contributions | |
ishes | +0.041 |
anks | +0.040 |
ware | +0.040 |
unes | +0.040 |
fault | +0.039 |
Neg logit contributions | |
ha | -0.021 |
Little | -0.018 |
few | -0.017 |
www | -0.016 |
Time | -0.016 |
Token | cle |
Token ID | 1190 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
ha | +0.000 |
Little | +0.000 |
few | +0.000 |
www | +0.000 |
ww | +0.000 |
Neg logit contributions | |
ishes | -0.000 |
anks | -0.000 |
unes | -0.000 |
ware | -0.000 |
fault | -0.000 |
Token | vern |
Token ID | 933 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
ishes | +0.119 |
unes | +0.113 |
ware | +0.113 |
anks | +0.109 |
fault | +0.105 |
Neg logit contributions | |
ha | -0.192 |
www | -0.170 |
Little | -0.170 |
few | -0.169 |
ww | -0.165 |
Token | ess |
Token ID | 408 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
ishes | +0.142 |
ware | +0.140 |
unes | +0.137 |
anks | +0.133 |
els | +0.130 |
Neg logit contributions | |
ha | -0.110 |
www | -0.093 |
few | -0.093 |
ww | -0.092 |
Little | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | +6.81e-03 |
Pos logit contributions | |
ha | +0.067 |
Little | +0.058 |
few | +0.056 |
www | +0.055 |
ww | +0.054 |
Neg logit contributions | |
anks | -0.096 |
ware | -0.096 |
ishes | -0.096 |
unes | -0.095 |
fault | -0.093 |
Token | creat |
Token ID | 1827 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ishes | +0.015 |
ware | +0.015 |
anks | +0.015 |
unes | +0.015 |
fault | +0.015 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.009 |
www | -0.008 |
ww | -0.008 |
Time | -0.008 |
Token | iveness |
Token ID | 6517 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
anks | +0.028 |
unes | +0.027 |
ishes | +0.027 |
ware | +0.027 |
fault | +0.026 |
Neg logit contributions | |
ha | -0.030 |
Little | -0.026 |
www | -0.026 |
ww | -0.026 |
unt | -0.026 |
Token | got |
Token ID | 1392 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
ishes | +0.028 |
ware | +0.028 |
anks | +0.027 |
unes | +0.027 |
fault | +0.027 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.016 |
www | -0.015 |
ww | -0.015 |
Time | -0.015 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
ware | +0.008 |
unes | +0.008 |
ishes | +0.008 |
anks | +0.008 |
fault | +0.008 |
Neg logit contributions | |
ha | -0.005 |
few | -0.004 |
Little | -0.004 |
Time | -0.004 |
www | -0.004 |
Token | vere |
Token ID | 4119 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
ishes | +0.126 |
unes | +0.120 |
ware | +0.119 |
anks | +0.116 |
fault | +0.114 |
Neg logit contributions | |
ha | -0.183 |
Little | -0.165 |
www | -0.161 |
few | -0.159 |
ww | -0.157 |
Token | r |
Token ID | 81 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ishes | +0.017 |
ware | +0.017 |
anks | +0.017 |
unes | +0.017 |
fault | +0.017 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.018 |
www | -0.017 |
few | -0.017 |
ww | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
anks | +0.041 |
ishes | +0.041 |
ware | +0.041 |
unes | +0.041 |
fault | +0.041 |
Neg logit contributions | |
ha | -0.033 |
Little | -0.029 |
www | -0.028 |
Time | -0.027 |
ww | -0.027 |
Token | cle |
Token ID | 1190 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
ishes | +0.007 |
ware | +0.006 |
anks | +0.006 |
unes | +0.006 |
fault | +0.006 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.004 |
www | -0.003 |
ww | -0.003 |
Time | -0.003 |
Token | vere |
Token ID | 4119 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
ishes | +0.119 |
unes | +0.114 |
ware | +0.114 |
anks | +0.108 |
fault | +0.107 |
Neg logit contributions | |
ha | -0.194 |
Little | -0.176 |
www | -0.172 |
few | -0.170 |
ww | -0.168 |
Token | r |
Token ID | 81 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
ishes | +0.016 |
anks | +0.016 |
ware | +0.016 |
unes | +0.016 |
fault | +0.016 |
Neg logit contributions | |
ha | -0.021 |
Little | -0.019 |
www | -0.018 |
ww | -0.018 |
Time | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
anks | +0.042 |
ishes | +0.041 |
fault | +0.041 |
ware | +0.041 |
unes | +0.041 |
Neg logit contributions | |
ha | -0.036 |
Little | -0.032 |
www | -0.031 |
Time | -0.031 |
ww | -0.030 |
Token | Eventually |
Token ID | 16178 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
ishes | +0.013 |
ware | +0.013 |
unes | +0.013 |
anks | +0.013 |
fault | +0.012 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.007 |
few | -0.007 |
Time | -0.007 |
uren | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
ware | +0.029 |
anks | +0.029 |
unes | +0.028 |
kins | +0.028 |
ishes | +0.027 |
Neg logit contributions | |
ha | -0.028 |
While | -0.026 |
Alice | -0.026 |
Little | -0.026 |
unt | -0.026 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
ishes | +0.002 |
ware | +0.002 |
anks | +0.002 |
unes | +0.002 |
fault | +0.002 |
Neg logit contributions | |
ha | -0.002 |
www | -0.001 |
Little | -0.001 |
ww | -0.001 |
Time | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
unes | +0.041 |
anks | +0.041 |
ware | +0.041 |
ishes | +0.041 |
fault | +0.039 |
Neg logit contributions | |
ha | -0.024 |
Little | -0.020 |
www | -0.019 |
few | -0.019 |
ww | -0.019 |
Token | known |
Token ID | 1900 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
fault | +0.024 |
ishes | +0.024 |
anks | +0.023 |
unes | +0.023 |
ware | +0.023 |
Neg logit contributions | |
ha | -0.024 |
Little | -0.021 |
www | -0.021 |
ww | -0.021 |
uren | -0.020 |
Token | as |
Token ID | 355 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ishes | +0.014 |
ware | +0.014 |
anks | +0.014 |
unes | +0.014 |
fault | +0.014 |
Neg logit contributions | |
ha | -0.011 |
Little | -0.009 |
www | -0.009 |
few | -0.009 |
ww | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +5.14e-04 |
Pos logit contributions | |
ha | +0.017 |
Little | +0.014 |
www | +0.013 |
ww | +0.013 |
Time | +0.013 |
Neg logit contributions | |
ishes | -0.034 |
ware | -0.033 |
anks | -0.033 |
unes | -0.033 |
fault | -0.033 |
Token | cle |
Token ID | 1190 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
ishes | +0.001 |
anks | +0.001 |
ware | +0.001 |
unes | +0.001 |
fault | +0.001 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.001 |
ww | -0.001 |
unt | -0.001 |
Token | ve |
Token ID | 303 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
ishes | +0.155 |
ware | +0.151 |
unes | +0.150 |
anks | +0.149 |
fault | +0.146 |
Neg logit contributions | |
ha | -0.155 |
Little | -0.133 |
www | -0.132 |
few | -0.129 |
ww | -0.128 |
Token | rest |
Token ID | 2118 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
ha | +0.098 |
Little | +0.093 |
uren | +0.091 |
unt | +0.091 |
Time | +0.090 |
Neg logit contributions | |
ishes | -0.078 |
ware | -0.076 |
unes | -0.075 |
aces | -0.074 |
anks | -0.074 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ha | +0.053 |
Little | +0.047 |
www | +0.046 |
Time | +0.045 |
uren | +0.045 |
Neg logit contributions | |
ishes | -0.064 |
anks | -0.063 |
unes | -0.062 |
ware | -0.062 |
fault | -0.060 |
Token | in |
Token ID | 287 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
ishes | +0.042 |
ware | +0.042 |
anks | +0.041 |
unes | +0.041 |
fault | +0.040 |
Neg logit contributions | |
ha | -0.030 |
Little | -0.026 |
www | -0.025 |
ww | -0.024 |
Time | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +5.90e-04 |
Pos logit contributions | |
ishes | +0.081 |
anks | +0.081 |
ware | +0.081 |
unes | +0.080 |
fault | +0.079 |
Neg logit contributions | |
ha | -0.043 |
Little | -0.035 |
www | -0.034 |
ww | -0.033 |
unt | -0.032 |
Token | day |
Token ID | 1110 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
ware | +0.034 |
fault | +0.032 |
anks | +0.031 |
unes | +0.031 |
ishes | +0.031 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.015 |
T | -0.015 |
Alice | -0.014 |
www | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.15e-03 |
Pos logit contributions | |
ha | +0.024 |
ww | +0.021 |
www | +0.021 |
unt | +0.020 |
Little | +0.020 |
Neg logit contributions | |
anks | -0.029 |
ware | -0.029 |
unes | -0.029 |
ishes | -0.028 |
aces | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
ishes | +0.007 |
ware | +0.007 |
anks | +0.007 |
fault | +0.007 |
unes | +0.006 |
Neg logit contributions | |
ha | -0.005 |
Little | -0.004 |
unt | -0.004 |
ww | -0.004 |
www | -0.004 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
Time | +0.003 |
Neg logit contributions | |
ishes | -0.005 |
ware | -0.005 |
anks | -0.005 |
unes | -0.005 |
fault | -0.005 |
Token | got |
Token ID | 1392 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
ishes | +0.028 |
ware | +0.028 |
anks | +0.027 |
unes | +0.027 |
fault | +0.027 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.016 |
www | -0.015 |
ww | -0.015 |
Time | -0.015 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
ware | +0.008 |
unes | +0.008 |
ishes | +0.008 |
anks | +0.008 |
fault | +0.008 |
Neg logit contributions | |
ha | -0.005 |
few | -0.004 |
Little | -0.004 |
Time | -0.004 |
www | -0.004 |
Token | vere |
Token ID | 4119 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
ishes | +0.126 |
unes | +0.120 |
ware | +0.119 |
anks | +0.116 |
fault | +0.114 |
Neg logit contributions | |
ha | -0.183 |
Little | -0.165 |
www | -0.161 |
few | -0.159 |
ww | -0.157 |
Token | r |
Token ID | 81 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ishes | +0.017 |
ware | +0.017 |
anks | +0.017 |
unes | +0.017 |
fault | +0.017 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.018 |
www | -0.017 |
few | -0.017 |
ww | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
anks | +0.041 |
ishes | +0.041 |
ware | +0.041 |
unes | +0.041 |
fault | +0.041 |
Neg logit contributions | |
ha | -0.033 |
Little | -0.029 |
www | -0.028 |
Time | -0.027 |
ww | -0.027 |
Token | cle |
Token ID | 1190 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
ishes | +0.007 |
ware | +0.006 |
anks | +0.006 |
unes | +0.006 |
fault | +0.006 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.004 |
www | -0.003 |
ww | -0.003 |
Time | -0.003 |
Token | vere |
Token ID | 4119 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
ishes | +0.119 |
unes | +0.114 |
ware | +0.114 |
anks | +0.108 |
fault | +0.107 |
Neg logit contributions | |
ha | -0.194 |
Little | -0.176 |
www | -0.172 |
few | -0.170 |
ww | -0.168 |
Token | engine |
Token ID | 3113 |
Feature activation | -1.70e-04 |
Pos logit contributions | |
ha | +0.004 |
www | +0.004 |
ww | +0.004 |
uren | +0.004 |
Alice | +0.004 |
Neg logit contributions | |
fault | -0.003 |
ishes | -0.003 |
anks | -0.003 |
ware | -0.003 |
wounds | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ha | +0.000 |
Little | +0.000 |
www | +0.000 |
ww | +0.000 |
Time | +0.000 |
Neg logit contributions | |
ishes | -0.000 |
anks | -0.000 |
ware | -0.000 |
fault | -0.000 |
unes | -0.000 |
Token | known |
Token ID | 1900 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
fault | +0.028 |
ishes | +0.026 |
anks | +0.024 |
unes | +0.024 |
ric | +0.024 |
Neg logit contributions | |
ha | -0.029 |
www | -0.025 |
uren | -0.025 |
ww | -0.025 |
Little | -0.024 |
Token | as |
Token ID | 355 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
anks | +0.020 |
ishes | +0.020 |
unes | +0.020 |
fault | +0.020 |
ware | +0.020 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.016 |
www | -0.016 |
Time | -0.015 |
ww | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
ha | +0.020 |
Little | +0.016 |
www | +0.016 |
ww | +0.015 |
unt | +0.015 |
Neg logit contributions | |
ishes | -0.040 |
anks | -0.039 |
ware | -0.039 |
unes | -0.039 |
fault | -0.039 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
ha | +0.003 |
www | +0.003 |
ww | +0.003 |
uren | +0.003 |
Little | +0.003 |
Neg logit contributions | |
fault | -0.003 |
anks | -0.003 |
ishes | -0.003 |
unes | -0.003 |
ware | -0.003 |
Token | ve |
Token ID | 303 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
ishes | +0.131 |
ware | +0.129 |
anks | +0.128 |
unes | +0.128 |
fault | +0.124 |
Neg logit contributions | |
ha | -0.170 |
Little | -0.153 |
www | -0.148 |
ww | -0.146 |
few | -0.146 |
Token | rest |
Token ID | 2118 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ha | +0.096 |
uren | +0.094 |
Little | +0.094 |
www | +0.092 |
unt | +0.091 |
Neg logit contributions | |
ishes | -0.066 |
aces | -0.065 |
unes | -0.063 |
els | -0.063 |
anks | -0.062 |
Token | engine |
Token ID | 3113 |
Feature activation | +2.32e-04 |
Pos logit contributions | |
ha | +0.058 |
www | +0.053 |
Little | +0.053 |
uren | +0.052 |
Alice | +0.052 |
Neg logit contributions | |
ishes | -0.061 |
anks | -0.060 |
unes | -0.060 |
ware | -0.058 |
fault | -0.057 |
Token | in |
Token ID | 287 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
anks | +0.000 |
ishes | +0.000 |
ware | +0.000 |
unes | +0.000 |
fault | +0.000 |
Neg logit contributions | |
ha | -0.000 |
Little | -0.000 |
www | -0.000 |
ww | -0.000 |
Time | -0.000 |
Token | all |
Token ID | 477 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
fault | +0.070 |
ware | +0.069 |
anks | +0.069 |
ishes | +0.069 |
unes | +0.067 |
Neg logit contributions | |
ha | -0.045 |
www | -0.038 |
ww | -0.037 |
Little | -0.036 |
uren | -0.036 |
Token | John |
Token ID | 1757 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
ishes | +0.014 |
ware | +0.013 |
anks | +0.013 |
unes | +0.013 |
aces | +0.012 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.013 |
ww | -0.013 |
Time | -0.013 |
www | -0.013 |
Token | chose |
Token ID | 7690 |
Feature activation | -6.47e-03 |
Pos logit contributions | |
ha | +0.062 |
Little | +0.054 |
www | +0.052 |
ww | +0.052 |
Time | +0.052 |
Neg logit contributions | |
ishes | -0.093 |
ware | -0.089 |
anks | -0.089 |
unes | -0.089 |
fault | -0.088 |
Token | some |
Token ID | 617 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ha | +0.008 |
few | +0.006 |
Little | +0.006 |
www | +0.006 |
Time | +0.006 |
Neg logit contributions | |
anks | -0.017 |
ishes | -0.016 |
unes | -0.016 |
ware | -0.016 |
fault | -0.016 |
Token | carrots |
Token ID | 34397 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
anks | +0.022 |
ishes | +0.021 |
unes | +0.020 |
fault | +0.020 |
ware | +0.020 |
Neg logit contributions | |
ha | -0.017 |
few | -0.015 |
Little | -0.015 |
www | -0.014 |
ww | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.87e-03 |
Pos logit contributions | |
anks | +0.055 |
fault | +0.054 |
ishes | +0.052 |
unes | +0.052 |
wounds | +0.052 |
Neg logit contributions | |
ha | -0.017 |
few | -0.015 |
" | -0.014 |
ww | -0.012 |
long | -0.012 |
Token | cuc |
Token ID | 38421 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
ishes | +0.008 |
anks | +0.008 |
ware | +0.008 |
unes | +0.008 |
fault | +0.008 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
few | -0.005 |
ww | -0.005 |
Token | umbers |
Token ID | 17024 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ses | +0.120 |
fault | +0.117 |
wounds | +0.103 |
neys | +0.102 |
anks | +0.100 |
Neg logit contributions | |
ha | -0.188 |
few | -0.170 |
ww | -0.165 |
www | -0.162 |
T | -0.159 |
Token | to |
Token ID | 284 |
Feature activation | +1.33e-04 |
Pos logit contributions | |
anks | +0.048 |
fault | +0.047 |
ishes | +0.046 |
unes | +0.046 |
ses | +0.045 |
Neg logit contributions | |
ha | -0.024 |
few | -0.020 |
" | -0.018 |
Little | -0.017 |
www | -0.017 |
Token | take |
Token ID | 1011 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
anks | +0.000 |
unes | +0.000 |
ishes | +0.000 |
fault | +0.000 |
ware | +0.000 |
Neg logit contributions | |
ha | -0.000 |
Little | -0.000 |
few | -0.000 |
www | -0.000 |
ww | -0.000 |
Token | home |
Token ID | 1363 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
ha | +0.045 |
Little | +0.040 |
www | +0.038 |
Time | +0.038 |
ww | +0.038 |
Neg logit contributions | |
ishes | -0.058 |
ware | -0.057 |
unes | -0.057 |
anks | -0.057 |
fault | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ha | +0.023 |
few | +0.020 |
Little | +0.020 |
www | +0.018 |
T | +0.018 |
Neg logit contributions | |
anks | -0.034 |
unes | -0.033 |
ishes | -0.033 |
fault | -0.033 |
ware | -0.033 |
Token | praised |
Token ID | 15342 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ha | +0.023 |
unt | +0.019 |
Little | +0.019 |
www | +0.019 |
uren | +0.019 |
Neg logit contributions | |
ishes | -0.026 |
fault | -0.024 |
anks | -0.024 |
ware | -0.023 |
depending | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
ishes | +0.025 |
ware | +0.025 |
anks | +0.024 |
unes | +0.024 |
fault | +0.024 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.018 |
www | -0.017 |
few | -0.017 |
ww | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | -8.77e-04 |
Pos logit contributions | |
anks | +0.016 |
ishes | +0.016 |
ware | +0.016 |
fault | +0.016 |
unes | +0.016 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.014 |
www | -0.014 |
ww | -0.014 |
unt | -0.014 |
Token | obedience |
Token ID | 28777 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
ha | +0.002 |
www | +0.001 |
Little | +0.001 |
ww | +0.001 |
Alice | +0.001 |
Neg logit contributions | |
fault | -0.002 |
anks | -0.002 |
ishes | -0.002 |
unes | -0.002 |
ware | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
ha | +0.012 |
Little | +0.010 |
www | +0.010 |
ww | +0.010 |
Time | +0.010 |
Neg logit contributions | |
ishes | -0.016 |
anks | -0.016 |
ware | -0.016 |
unes | -0.016 |
fault | -0.016 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
ishes | +0.017 |
anks | +0.017 |
ware | +0.017 |
unes | +0.017 |
fault | +0.017 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.012 |
www | -0.012 |
ww | -0.011 |
Time | -0.011 |
Token | vern |
Token ID | 933 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
ishes | +0.109 |
ware | +0.107 |
unes | +0.105 |
anks | +0.100 |
fault | +0.097 |
Neg logit contributions | |
ha | -0.194 |
Little | -0.174 |
www | -0.173 |
few | -0.170 |
ww | -0.168 |
Token | ess |
Token ID | 408 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
ishes | +0.144 |
ware | +0.144 |
unes | +0.140 |
anks | +0.136 |
fault | +0.132 |
Neg logit contributions | |
ha | -0.115 |
www | -0.098 |
Little | -0.097 |
ww | -0.097 |
few | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ha | +0.064 |
Little | +0.056 |
www | +0.053 |
few | +0.053 |
ww | +0.052 |
Neg logit contributions | |
ishes | -0.083 |
ware | -0.083 |
anks | -0.082 |
unes | -0.082 |
fault | -0.080 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ware | +0.031 |
ishes | +0.030 |
anks | +0.030 |
unes | +0.030 |
fault | +0.029 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.015 |
www | -0.014 |
unt | -0.014 |
Time | -0.014 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ware | +0.027 |
anks | +0.027 |
unes | +0.027 |
ishes | +0.026 |
ests | +0.026 |
Neg logit contributions | |
ha | -0.023 |
www | -0.021 |
ww | -0.021 |
Little | -0.020 |
uren | -0.020 |
Token | animals |
Token ID | 4695 |
Feature activation | -5.66e-03 |
Pos logit contributions | |
ha | +0.000 |
www | +0.000 |
ww | +0.000 |
Little | +0.000 |
unt | +0.000 |
Neg logit contributions | |
ware | -0.000 |
ishes | -0.000 |
unes | -0.000 |
fault | -0.000 |
anks | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
ha | +0.009 |
Little | +0.008 |
www | +0.008 |
few | +0.008 |
ww | +0.008 |
Neg logit contributions | |
ishes | -0.012 |
anks | -0.012 |
ware | -0.012 |
unes | -0.012 |
fault | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
ha | +0.013 |
Little | +0.011 |
www | +0.011 |
ww | +0.010 |
Time | +0.010 |
Neg logit contributions | |
ware | -0.019 |
ishes | -0.019 |
anks | -0.019 |
unes | -0.019 |
fault | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
ware | +0.010 |
unes | +0.010 |
ishes | +0.009 |
anks | +0.009 |
depending | +0.009 |
Neg logit contributions | |
ha | -0.009 |
www | -0.008 |
ww | -0.008 |
Little | -0.008 |
Time | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ishes | +0.015 |
ware | +0.015 |
unes | +0.014 |
anks | +0.014 |
ests | +0.014 |
Neg logit contributions | |
ha | -0.011 |
www | -0.009 |
unt | -0.009 |
few | -0.009 |
Little | -0.009 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
ishes | +0.041 |
anks | +0.040 |
ware | +0.040 |
unes | +0.040 |
fault | +0.040 |
Neg logit contributions | |
ha | -0.033 |
Little | -0.028 |
www | -0.027 |
ww | -0.027 |
Time | -0.026 |
Token | ve |
Token ID | 303 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
ishes | +0.151 |
ware | +0.147 |
unes | +0.146 |
anks | +0.144 |
fault | +0.142 |
Neg logit contributions | |
ha | -0.151 |
Little | -0.131 |
www | -0.130 |
ww | -0.126 |
few | -0.126 |
Token | rest |
Token ID | 2118 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ha | +0.089 |
Little | +0.085 |
uren | +0.083 |
T | +0.083 |
Time | +0.083 |
Neg logit contributions | |
ware | -0.094 |
ishes | -0.094 |
anks | -0.093 |
unes | -0.093 |
aces | -0.092 |
Token | sheep |
Token ID | 15900 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ha | +0.045 |
Little | +0.040 |
Time | +0.038 |
T | +0.037 |
Alice | +0.037 |
Neg logit contributions | |
ishes | -0.068 |
anks | -0.068 |
ware | -0.068 |
unes | -0.067 |
fault | -0.066 |
Token | ever |
Token ID | 1683 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
ha | +0.019 |
Little | +0.016 |
www | +0.015 |
Time | +0.015 |
ww | +0.015 |
Neg logit contributions | |
ishes | -0.028 |
anks | -0.028 |
ware | -0.027 |
unes | -0.027 |
fault | -0.027 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ishes | +0.014 |
anks | +0.014 |
unes | +0.014 |
fault | +0.014 |
ware | +0.013 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.009 |
unt | -0.009 |
Alice | -0.009 |
uren | -0.008 |
Token | fountain |
Token ID | 29420 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
ha | +0.010 |
Little | +0.009 |
www | +0.009 |
ww | +0.009 |
T | +0.009 |
Neg logit contributions | |
ishes | -0.007 |
ware | -0.007 |
unes | -0.007 |
anks | -0.007 |
fault | -0.007 |
Token | burst |
Token ID | 11173 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
ware | +0.009 |
ishes | +0.009 |
unes | +0.009 |
anks | +0.009 |
fault | +0.008 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
ww | -0.005 |
unt | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
unes | +0.007 |
ishes | +0.007 |
ware | +0.007 |
anks | +0.007 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.006 |
www | -0.006 |
ww | -0.005 |
unt | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
ha | +0.009 |
www | +0.007 |
Little | +0.007 |
ww | +0.007 |
unt | +0.007 |
Neg logit contributions | |
ishes | -0.011 |
ware | -0.011 |
unes | -0.011 |
anks | -0.010 |
fault | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -3.75e-03 |
Pos logit contributions | |
ishes | +0.065 |
ware | +0.065 |
anks | +0.065 |
unes | +0.064 |
fault | +0.063 |
Neg logit contributions | |
ha | -0.036 |
Little | -0.031 |
www | -0.029 |
few | -0.029 |
ww | -0.029 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
ha | +0.006 |
Little | +0.005 |
few | +0.005 |
www | +0.005 |
ww | +0.005 |
Neg logit contributions | |
anks | -0.008 |
ishes | -0.008 |
ware | -0.008 |
unes | -0.008 |
fault | -0.008 |
Token | arest |
Token ID | 12423 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
ishes | +0.171 |
ware | +0.165 |
unes | +0.165 |
anks | +0.165 |
fault | +0.160 |
Neg logit contributions | |
ha | -0.132 |
www | -0.111 |
Little | -0.107 |
ww | -0.107 |
few | -0.106 |
Token | water |
Token ID | 1660 |
Feature activation | -5.75e-03 |
Pos logit contributions | |
ha | +0.003 |
Little | +0.003 |
few | +0.003 |
www | +0.003 |
Time | +0.003 |
Neg logit contributions | |
anks | -0.004 |
ishes | -0.004 |
ware | -0.004 |
unes | -0.004 |
fault | -0.004 |
Token | they |
Token ID | 484 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
www | +0.007 |
few | +0.007 |
ww | +0.007 |
Neg logit contributions | |
anks | -0.013 |
ishes | -0.013 |
unes | -0.013 |
ware | -0.013 |
fault | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -6.59e-03 |
Pos logit contributions | |
anks | +0.027 |
ware | +0.027 |
unes | +0.027 |
fault | +0.027 |
ishes | +0.027 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.014 |
www | -0.013 |
few | -0.013 |
Time | -0.013 |
Token | ever |
Token ID | 1683 |
Feature activation | +7.40e-03 |
Pos logit contributions | |
ha | +0.010 |
Little | +0.009 |
www | +0.009 |
ww | +0.008 |
few | +0.008 |
Neg logit contributions | |
ishes | -0.015 |
ware | -0.014 |
anks | -0.014 |
unes | -0.014 |
fault | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
ware | +0.012 |
ishes | +0.011 |
anks | +0.011 |
unes | +0.011 |
fault | +0.011 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
ww | -0.005 |
Time | -0.004 |
Token | moment |
Token ID | 2589 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
ha | +0.007 |
www | +0.006 |
ww | +0.006 |
Kelly | +0.006 |
Alice | +0.005 |
Neg logit contributions | |
ware | -0.013 |
kins | -0.012 |
mouths | -0.012 |
ishes | -0.012 |
bugs | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
ware | +0.006 |
unes | +0.006 |
anks | +0.006 |
kins | +0.006 |
els | +0.006 |
Neg logit contributions | |
ha | -0.006 |
www | -0.006 |
ww | -0.006 |
T | -0.005 |
Charlie | -0.005 |
Token | independence |
Token ID | 10404 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
ware | +0.020 |
ishes | +0.020 |
unes | +0.019 |
els | +0.019 |
anks | +0.019 |
Neg logit contributions | |
ha | -0.012 |
ww | -0.010 |
www | -0.010 |
Little | -0.009 |
unt | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e-04 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.001 |
www | +0.001 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
ware | -0.002 |
ishes | -0.002 |
unes | -0.002 |
anks | -0.002 |
fault | -0.002 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
ha | +0.000 |
Little | +0.000 |
Time | +0.000 |
ww | +0.000 |
www | +0.000 |
Neg logit contributions | |
ishes | -0.000 |
anks | -0.000 |
ware | -0.000 |
unes | -0.000 |
fault | -0.000 |
Token | vern |
Token ID | 933 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
ishes | +0.127 |
ware | +0.120 |
unes | +0.120 |
anks | +0.115 |
fault | +0.115 |
Neg logit contributions | |
ha | -0.180 |
Little | -0.157 |
www | -0.155 |
few | -0.153 |
unt | -0.150 |
Token | ess |
Token ID | 408 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
ishes | +0.135 |
ware | +0.134 |
unes | +0.130 |
anks | +0.127 |
fault | +0.124 |
Neg logit contributions | |
ha | -0.104 |
www | -0.088 |
few | -0.086 |
Little | -0.086 |
ww | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
ha | +0.075 |
Little | +0.065 |
www | +0.062 |
ww | +0.061 |
few | +0.061 |
Neg logit contributions | |
ishes | -0.106 |
anks | -0.105 |
ware | -0.105 |
unes | -0.105 |
fault | -0.103 |
Token | she |
Token ID | 673 |
Feature activation | +9.60e-05 |
Pos logit contributions | |
ha | +0.008 |
www | +0.007 |
ww | +0.007 |
Little | +0.007 |
Time | +0.007 |
Neg logit contributions | |
ishes | -0.012 |
ware | -0.012 |
anks | -0.012 |
unes | -0.012 |
fault | -0.012 |
Token | used |
Token ID | 973 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ishes | +0.000 |
ware | +0.000 |
anks | +0.000 |
unes | +0.000 |
fault | +0.000 |
Neg logit contributions | |
ha | -0.000 |
Little | -0.000 |
www | -0.000 |
ww | -0.000 |
few | -0.000 |
Token | continued |
Token ID | 3767 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.006 |
www | +0.005 |
few | +0.005 |
T | +0.005 |
Neg logit contributions | |
fault | -0.023 |
ishes | -0.022 |
ware | -0.022 |
unes | -0.022 |
anks | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ishes | +0.034 |
ware | +0.034 |
anks | +0.034 |
unes | +0.034 |
fault | +0.033 |
Neg logit contributions | |
ha | -0.028 |
Little | -0.025 |
www | -0.024 |
ww | -0.023 |
Time | -0.023 |
Token | scatter |
Token ID | 41058 |
Feature activation | +5.65e-03 |
Pos logit contributions | |
fault | +0.024 |
ware | +0.024 |
ishes | +0.024 |
anks | +0.024 |
unes | +0.023 |
Neg logit contributions | |
ha | -0.020 |
www | -0.017 |
Little | -0.017 |
unt | -0.016 |
ww | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +6.64e-03 |
Pos logit contributions | |
anks | +0.014 |
ware | +0.014 |
unes | +0.014 |
ishes | +0.014 |
fault | +0.014 |
Neg logit contributions | |
ha | -0.007 |
few | -0.006 |
Little | -0.006 |
Time | -0.005 |
www | -0.005 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
anks | +0.013 |
unes | +0.012 |
ishes | +0.012 |
ware | +0.012 |
fault | +0.012 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.011 |
few | -0.011 |
ww | -0.010 |
www | -0.010 |
Token | cr |
Token ID | 6098 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
anks | +0.030 |
ware | +0.030 |
unes | +0.030 |
ishes | +0.029 |
fault | +0.029 |
Neg logit contributions | |
ha | -0.018 |
few | -0.016 |
long | -0.015 |
ww | -0.014 |
Little | -0.014 |
Token | umbs |
Token ID | 18146 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ware | +0.115 |
fault | +0.112 |
anks | +0.110 |
ishes | +0.108 |
unes | +0.105 |
Neg logit contributions | |
ha | -0.178 |
Little | -0.159 |
few | -0.159 |
ww | -0.158 |
www | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ishes | +0.061 |
ware | +0.061 |
anks | +0.060 |
unes | +0.060 |
fault | +0.059 |
Neg logit contributions | |
ha | -0.043 |
Little | -0.037 |
www | -0.036 |
few | -0.035 |
ww | -0.035 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
unes | +0.032 |
ishes | +0.032 |
anks | +0.032 |
ware | +0.032 |
fault | +0.031 |
Neg logit contributions | |
ha | -0.027 |
Little | -0.024 |
www | -0.023 |
ww | -0.023 |
few | -0.022 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
anks | +0.037 |
ishes | +0.037 |
ware | +0.037 |
unes | +0.036 |
fault | +0.036 |
Neg logit contributions | |
ha | -0.028 |
Little | -0.024 |
www | -0.024 |
ww | -0.023 |
few | -0.023 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.003 |
www | +0.003 |
ww | +0.003 |
Time | +0.003 |
Neg logit contributions | |
ishes | -0.004 |
ware | -0.004 |
anks | -0.004 |
unes | -0.004 |
fault | -0.004 |
Token | two |
Token ID | 734 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ware | +0.044 |
ishes | +0.044 |
unes | +0.043 |
anks | +0.043 |
fault | +0.043 |
Neg logit contributions | |
ha | -0.036 |
Little | -0.031 |
www | -0.030 |
ww | -0.030 |
T | -0.030 |
Token | friends |
Token ID | 2460 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
ha | +0.035 |
Little | +0.031 |
www | +0.029 |
few | +0.029 |
ww | +0.029 |
Neg logit contributions | |
ishes | -0.039 |
ware | -0.039 |
anks | -0.039 |
unes | -0.038 |
fault | -0.037 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ishes | +0.015 |
ware | +0.014 |
anks | +0.014 |
unes | +0.014 |
fault | +0.014 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.013 |
www | -0.012 |
ww | -0.012 |
Time | -0.012 |
Token | at |
Token ID | 379 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
anks | +0.034 |
ishes | +0.034 |
ware | +0.034 |
unes | +0.033 |
fault | +0.033 |
Neg logit contributions | |
ha | -0.028 |
Little | -0.024 |
www | -0.024 |
ww | -0.023 |
Time | -0.023 |
Token | their |
Token ID | 511 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
ha | +0.006 |
Little | +0.006 |
few | +0.005 |
www | +0.005 |
Time | +0.005 |
Neg logit contributions | |
anks | -0.008 |
ware | -0.008 |
unes | -0.008 |
ishes | -0.008 |
fault | -0.008 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
ha | +0.014 |
Little | +0.012 |
www | +0.012 |
ww | +0.012 |
Time | +0.012 |
Neg logit contributions | |
ishes | -0.016 |
anks | -0.015 |
ware | -0.015 |
unes | -0.015 |
fault | -0.015 |
Token | vern |
Token ID | 933 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
ishes | +0.113 |
ware | +0.110 |
unes | +0.109 |
anks | +0.106 |
fault | +0.100 |
Neg logit contributions | |
ha | -0.184 |
Little | -0.163 |
www | -0.162 |
few | -0.159 |
ww | -0.158 |
Token | ess |
Token ID | 408 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
ishes | +0.142 |
ware | +0.141 |
unes | +0.138 |
anks | +0.135 |
fault | +0.130 |
Neg logit contributions | |
ha | -0.111 |
www | -0.093 |
few | -0.092 |
Little | -0.092 |
ww | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
ha | +0.058 |
Little | +0.049 |
www | +0.046 |
few | +0.046 |
ww | +0.045 |
Neg logit contributions | |
ishes | -0.098 |
ware | -0.098 |
anks | -0.097 |
unes | -0.097 |
fault | -0.095 |
Token | went |
Token ID | 1816 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ishes | +0.010 |
anks | +0.010 |
ware | +0.009 |
fault | +0.009 |
unes | +0.009 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.008 |
Time | -0.007 |
www | -0.007 |
ww | -0.007 |
Token | off |
Token ID | 572 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
anks | +0.032 |
unes | +0.030 |
ishes | +0.030 |
fault | +0.029 |
ware | +0.029 |
Neg logit contributions | |
ha | -0.036 |
Little | -0.035 |
ww | -0.032 |
www | -0.032 |
T | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
ha | +0.024 |
Little | +0.021 |
www | +0.020 |
ww | +0.020 |
unt | +0.020 |
Neg logit contributions | |
ware | -0.033 |
ishes | -0.033 |
anks | -0.033 |
unes | -0.033 |
fault | -0.033 |
Token | down |
Token ID | 866 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
ishes | +0.017 |
anks | +0.017 |
ware | +0.017 |
fault | +0.017 |
unes | +0.017 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.016 |
ww | -0.016 |
www | -0.016 |
T | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
ha | +0.060 |
Little | +0.052 |
www | +0.051 |
ww | +0.050 |
unt | +0.049 |
Neg logit contributions | |
ware | -0.080 |
anks | -0.080 |
ishes | -0.079 |
unes | -0.079 |
fault | -0.079 |
Token | street |
Token ID | 4675 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
ishes | +0.003 |
ware | +0.003 |
anks | +0.003 |
unes | +0.003 |
fault | +0.003 |
Neg logit contributions | |
ha | -0.002 |
Little | -0.002 |
www | -0.002 |
ww | -0.002 |
Time | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ha | +0.049 |
Little | +0.043 |
www | +0.042 |
ww | +0.041 |
Time | +0.040 |
Neg logit contributions | |
ware | -0.057 |
ishes | -0.057 |
anks | -0.057 |
unes | -0.056 |
fault | -0.056 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
unes | +0.034 |
anks | +0.033 |
ware | +0.033 |
fault | +0.032 |
ishes | +0.032 |
Neg logit contributions | |
ha | -0.031 |
www | -0.027 |
ww | -0.027 |
Little | -0.026 |
few | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
ishes | +0.158 |
ware | +0.151 |
fault | +0.145 |
unes | +0.144 |
depending | +0.140 |
Neg logit contributions | |
ha | -0.109 |
www | -0.098 |
Time | -0.098 |
Little | -0.097 |
ww | -0.095 |
Token | went |
Token ID | 1816 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ha | +0.007 |
Little | +0.006 |
www | +0.006 |
ww | +0.006 |
few | +0.006 |
Neg logit contributions | |
ishes | -0.012 |
ware | -0.012 |
anks | -0.012 |
unes | -0.012 |
fault | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
unes | +0.023 |
anks | +0.023 |
aces | +0.022 |
ware | +0.021 |
els | +0.021 |
Neg logit contributions | |
ha | -0.021 |
T | -0.020 |
ww | -0.020 |
Little | -0.020 |
www | -0.019 |
Token | people |
Token ID | 661 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
ww | +0.005 |
unt | +0.005 |
Little | +0.005 |
Neg logit contributions | |
ishes | -0.009 |
unes | -0.009 |
ware | -0.009 |
anks | -0.009 |
aces | -0.009 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.16e-03 |
Pos logit contributions | |
ha | +0.021 |
Little | +0.019 |
www | +0.019 |
ww | +0.018 |
Time | +0.018 |
Neg logit contributions | |
ishes | -0.028 |
ware | -0.027 |
anks | -0.027 |
unes | -0.027 |
fault | -0.026 |
Token | So |
Token ID | 1406 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
ware | +0.035 |
ishes | +0.034 |
unes | +0.034 |
anks | +0.033 |
fault | +0.033 |
Neg logit contributions | |
ha | -0.024 |
Little | -0.021 |
unt | -0.020 |
www | -0.020 |
few | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +9.23e-04 |
Pos logit contributions | |
ishes | +0.058 |
anks | +0.055 |
ware | +0.054 |
unes | +0.052 |
kins | +0.052 |
Neg logit contributions | |
ha | -0.045 |
Time | -0.038 |
www | -0.037 |
Little | -0.037 |
Alice | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ishes | +0.002 |
anks | +0.002 |
ware | +0.002 |
unes | +0.002 |
rier | +0.002 |
Neg logit contributions | |
ha | -0.002 |
www | -0.001 |
ww | -0.001 |
Time | -0.001 |
Little | -0.001 |
Token | used |
Token ID | 973 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ishes | +0.022 |
ware | +0.022 |
anks | +0.022 |
unes | +0.021 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.013 |
www | -0.013 |
ww | -0.012 |
Time | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | -8.42e-04 |
Pos logit contributions | |
ishes | +0.035 |
anks | +0.035 |
ware | +0.035 |
unes | +0.034 |
fault | +0.034 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.016 |
few | -0.016 |
www | -0.015 |
Time | -0.015 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
few | +0.001 |
www | +0.001 |
ww | +0.001 |
Neg logit contributions | |
ishes | -0.002 |
anks | -0.002 |
unes | -0.002 |
ware | -0.002 |
fault | -0.002 |
Token | vern |
Token ID | 933 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
ishes | +0.107 |
unes | +0.102 |
ware | +0.102 |
anks | +0.095 |
fault | +0.091 |
Neg logit contributions | |
ha | -0.190 |
www | -0.170 |
few | -0.167 |
Little | -0.166 |
ww | -0.164 |
Token | ess |
Token ID | 408 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
ishes | +0.140 |
ware | +0.139 |
unes | +0.135 |
anks | +0.129 |
els | +0.128 |
Neg logit contributions | |
ha | -0.106 |
www | -0.089 |
few | -0.088 |
ww | -0.088 |
unt | -0.087 |
Token | to |
Token ID | 284 |
Feature activation | +5.54e-03 |
Pos logit contributions | |
ha | +0.064 |
Little | +0.054 |
few | +0.054 |
www | +0.050 |
ww | +0.050 |
Neg logit contributions | |
ware | -0.099 |
anks | -0.099 |
unes | -0.098 |
ishes | -0.097 |
fault | -0.095 |
Token | find |
Token ID | 1064 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
anks | +0.010 |
ishes | +0.010 |
ware | +0.010 |
unes | +0.010 |
fault | +0.010 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.009 |
ww | -0.009 |
www | -0.009 |
Time | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -3.58e-05 |
Pos logit contributions | |
ishes | +0.037 |
ware | +0.037 |
anks | +0.037 |
unes | +0.036 |
fault | +0.036 |
Neg logit contributions | |
ha | -0.023 |
Little | -0.020 |
www | -0.019 |
ww | -0.018 |
Time | -0.018 |
Token | lin |
Token ID | 2815 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
ishes | +0.016 |
ware | +0.015 |
anks | +0.015 |
unes | +0.015 |
fault | +0.014 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.015 |
www | -0.015 |
Time | -0.015 |
few | -0.015 |
Token | g |
Token ID | 308 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
ha | +0.015 |
Little | +0.013 |
www | +0.013 |
ww | +0.012 |
few | +0.012 |
Neg logit contributions | |
ishes | -0.018 |
ware | -0.018 |
anks | -0.018 |
unes | -0.018 |
fault | -0.017 |
Token | to |
Token ID | 1462 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
ishes | +0.011 |
ware | +0.011 |
fault | +0.010 |
anks | +0.010 |
unes | +0.010 |
Neg logit contributions | |
ha | -0.017 |
www | -0.015 |
ww | -0.015 |
Little | -0.015 |
few | -0.014 |
Token | be |
Token ID | 307 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ha | +0.081 |
Little | +0.075 |
Time | +0.073 |
unt | +0.072 |
www | +0.071 |
Neg logit contributions | |
anks | -0.073 |
ishes | -0.071 |
ware | -0.071 |
unes | -0.070 |
aces | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
ha | +0.028 |
unt | +0.025 |
Little | +0.025 |
www | +0.025 |
ww | +0.024 |
Neg logit contributions | |
ishes | -0.031 |
aces | -0.031 |
anks | -0.030 |
kins | -0.029 |
unes | -0.028 |
Token | cle |
Token ID | 1190 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
ha | +0.003 |
Little | +0.003 |
few | +0.003 |
www | +0.003 |
ww | +0.003 |
Neg logit contributions | |
ishes | -0.003 |
anks | -0.003 |
unes | -0.003 |
ware | -0.003 |
fault | -0.003 |
Token | ve |
Token ID | 303 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
ishes | +0.159 |
unes | +0.155 |
ware | +0.155 |
anks | +0.154 |
fault | +0.150 |
Neg logit contributions | |
ha | -0.131 |
Little | -0.112 |
www | -0.111 |
ww | -0.108 |
few | -0.107 |
Token | rest |
Token ID | 2118 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ha | +0.097 |
Little | +0.090 |
Time | +0.086 |
ww | +0.085 |
www | +0.085 |
Neg logit contributions | |
ware | -0.091 |
ishes | -0.091 |
anks | -0.090 |
unes | -0.090 |
fault | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
ha | +0.058 |
Little | +0.052 |
Time | +0.049 |
www | +0.049 |
ww | +0.048 |
Neg logit contributions | |
ware | -0.071 |
ishes | -0.071 |
anks | -0.071 |
unes | -0.070 |
fault | -0.069 |
Token | But |
Token ID | 887 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
ishes | +0.014 |
ware | +0.014 |
anks | +0.014 |
unes | +0.014 |
fault | +0.014 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.008 |
few | -0.007 |
Time | -0.007 |
www | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
ishes | +0.010 |
ware | +0.010 |
anks | +0.010 |
unes | +0.010 |
fault | +0.009 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
ww | -0.005 |
Time | -0.005 |
Token | each |
Token ID | 1123 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.008 |
ware | -0.008 |
anks | -0.008 |
unes | -0.008 |
fault | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
ha | +0.017 |
uren | +0.015 |
www | +0.015 |
ww | +0.015 |
unt | +0.015 |
Neg logit contributions | |
ware | -0.020 |
ishes | -0.019 |
els | -0.018 |
anks | -0.018 |
fault | -0.018 |
Token | every |
Token ID | 790 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ishes | +0.007 |
anks | +0.007 |
ware | +0.007 |
unes | +0.007 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
ww | -0.005 |
Time | -0.004 |
Token | country |
Token ID | 1499 |
Feature activation | -7.90e-03 |
Pos logit contributions | |
ware | +0.039 |
fault | +0.037 |
ishes | +0.036 |
anks | +0.035 |
unes | +0.035 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.016 |
T | -0.016 |
uren | -0.016 |
www | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
ha | +0.012 |
Little | +0.009 |
few | +0.009 |
www | +0.009 |
Time | +0.009 |
Neg logit contributions | |
unes | -0.018 |
ishes | -0.018 |
anks | -0.018 |
ware | -0.018 |
fault | -0.017 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
ishes | +0.018 |
ware | +0.018 |
anks | +0.017 |
unes | +0.017 |
fault | +0.017 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.011 |
Time | -0.010 |
few | -0.010 |
unt | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
ishes | +0.181 |
ware | +0.178 |
unes | +0.173 |
fault | +0.173 |
anks | +0.172 |
Neg logit contributions | |
ha | -0.095 |
Little | -0.081 |
www | -0.079 |
Time | -0.077 |
ww | -0.077 |
Token | visited |
Token ID | 8672 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ishes | +0.015 |
anks | +0.015 |
ware | +0.015 |
unes | +0.015 |
fault | +0.015 |
Neg logit contributions | |
ha | -0.009 |
Little | -0.008 |
www | -0.007 |
ww | -0.007 |
Time | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
ishes | +0.035 |
ware | +0.035 |
anks | +0.035 |
unes | +0.034 |
fault | +0.034 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.016 |
www | -0.015 |
ww | -0.015 |
Time | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.003 |
www | +0.003 |
ww | +0.003 |
Time | +0.003 |
Neg logit contributions | |
ishes | -0.007 |
ware | -0.006 |
anks | -0.006 |
unes | -0.006 |
fault | -0.006 |
Token | left |
Token ID | 1364 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
ishes | +0.015 |
anks | +0.015 |
unes | +0.015 |
ware | +0.015 |
fault | +0.015 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.008 |
www | -0.008 |
few | -0.008 |
Time | -0.008 |
Token | having |
Token ID | 1719 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
anks | +0.011 |
ishes | +0.010 |
ware | +0.010 |
fault | +0.010 |
unes | +0.010 |
Neg logit contributions | |
ha | -0.009 |
Little | -0.008 |
www | -0.007 |
ww | -0.007 |
Time | -0.007 |
Token | lots |
Token ID | 6041 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
Little | +0.005 |
ww | +0.005 |
unt | +0.005 |
Neg logit contributions | |
fault | -0.008 |
aces | -0.008 |
anks | -0.008 |
ishes | -0.008 |
unes | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ha | +0.040 |
Little | +0.035 |
www | +0.035 |
ww | +0.034 |
uren | +0.033 |
Neg logit contributions | |
anks | -0.045 |
unes | -0.045 |
ishes | -0.045 |
ware | -0.045 |
fault | -0.044 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ishes | +0.033 |
anks | +0.033 |
ware | +0.033 |
unes | +0.033 |
fault | +0.033 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.017 |
www | -0.016 |
ww | -0.016 |
Time | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ishes | +0.021 |
ware | +0.021 |
anks | +0.021 |
unes | +0.021 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.017 |
www | -0.017 |
ww | -0.016 |
Time | -0.016 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
anks | +0.024 |
unes | +0.024 |
ishes | +0.023 |
ware | +0.023 |
fault | +0.023 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.017 |
www | -0.016 |
ww | -0.016 |
few | -0.015 |
Token | she |
Token ID | 673 |
Feature activation | -9.67e-04 |
Pos logit contributions | |
ishes | +0.166 |
ware | +0.164 |
fault | +0.157 |
unes | +0.156 |
anks | +0.154 |
Neg logit contributions | |
ha | -0.106 |
www | -0.089 |
Little | -0.088 |
unt | -0.087 |
ww | -0.087 |
Token | went |
Token ID | 1816 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
www | +0.001 |
ww | +0.001 |
unt | +0.001 |
Neg logit contributions | |
ware | -0.002 |
ishes | -0.002 |
anks | -0.002 |
unes | -0.002 |
fault | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
unes | +0.030 |
anks | +0.030 |
ware | +0.029 |
ishes | +0.028 |
aces | +0.028 |
Neg logit contributions | |
ha | -0.024 |
T | -0.021 |
Little | -0.021 |
ww | -0.021 |
www | -0.021 |
Token | she |
Token ID | 673 |
Feature activation | -5.32e-04 |
Pos logit contributions | |
ha | +0.005 |
www | +0.004 |
ww | +0.004 |
Little | +0.004 |
unt | +0.004 |
Neg logit contributions | |
ishes | -0.009 |
ware | -0.009 |
anks | -0.009 |
fault | -0.009 |
unes | -0.008 |
Token | showed |
Token ID | 3751 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
www | +0.001 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
ishes | -0.001 |
ware | -0.001 |
anks | -0.001 |
unes | -0.001 |
fault | -0.001 |
Token | woman |
Token ID | 2415 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
ha | +0.003 |
Little | +0.002 |
www | +0.002 |
ww | +0.002 |
Time | +0.002 |
Neg logit contributions | |
ishes | -0.004 |
ware | -0.004 |
anks | -0.004 |
unes | -0.004 |
fault | -0.003 |
Token | became |
Token ID | 2627 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ha | +0.040 |
Little | +0.034 |
few | +0.032 |
www | +0.032 |
ww | +0.032 |
Neg logit contributions | |
ware | -0.053 |
anks | -0.053 |
unes | -0.053 |
ishes | -0.053 |
fault | -0.051 |
Token | insepar |
Token ID | 50140 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
ware | +0.041 |
ishes | +0.041 |
anks | +0.041 |
unes | +0.041 |
fault | +0.040 |
Neg logit contributions | |
ha | -0.032 |
Little | -0.028 |
www | -0.026 |
few | -0.026 |
Time | -0.026 |
Token | able |
Token ID | 540 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ishes | +0.004 |
ware | +0.004 |
anks | +0.004 |
unes | +0.004 |
fault | +0.004 |
Neg logit contributions | |
ha | -0.003 |
Little | -0.003 |
www | -0.003 |
ww | -0.003 |
few | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ha | +0.017 |
few | +0.015 |
Little | +0.014 |
www | +0.013 |
T | +0.013 |
Neg logit contributions | |
ware | -0.028 |
unes | -0.028 |
anks | -0.027 |
ishes | -0.027 |
fault | -0.026 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
ware | +0.028 |
ishes | +0.028 |
anks | +0.027 |
unes | +0.027 |
rier | +0.026 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.018 |
unt | -0.017 |
Time | -0.016 |
few | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
ishes | +0.163 |
ware | +0.159 |
unes | +0.156 |
anks | +0.153 |
fault | +0.152 |
Neg logit contributions | |
ha | -0.115 |
Little | -0.101 |
www | -0.098 |
Time | -0.096 |
ww | -0.095 |
Token | woman |
Token ID | 2415 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
ww | +0.005 |
Alice | +0.005 |
uren | +0.005 |
Neg logit contributions | |
ishes | -0.006 |
ware | -0.006 |
unes | -0.006 |
anks | -0.006 |
rier | -0.005 |
Token | went |
Token ID | 1816 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ha | +0.036 |
Little | +0.030 |
www | +0.028 |
few | +0.028 |
unt | +0.028 |
Neg logit contributions | |
anks | -0.061 |
unes | -0.061 |
ishes | -0.060 |
ware | -0.060 |
fault | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
ishes | +0.033 |
anks | +0.033 |
unes | +0.033 |
ware | +0.032 |
fault | +0.031 |
Neg logit contributions | |
ha | -0.023 |
Little | -0.020 |
www | -0.019 |
T | -0.019 |
ww | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -2.63e-03 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.001 |
www | +0.001 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
ishes | -0.003 |
ware | -0.003 |
anks | -0.003 |
unes | -0.003 |
fault | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
ha | +0.024 |
few | +0.021 |
Time | +0.021 |
Little | +0.021 |
Charlie | +0.020 |
Neg logit contributions | |
anks | -0.022 |
unes | -0.022 |
ware | -0.022 |
rier | -0.021 |
ishes | -0.021 |
Token | € |
Token ID | 26391 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ha | +0.009 |
few | +0.008 |
Little | +0.008 |
ww | +0.007 |
Kelly | +0.007 |
Neg logit contributions | |
anks | -0.009 |
unes | -0.008 |
ware | -0.008 |
aces | -0.008 |
fault | -0.008 |
Token | � |
Token ID | 129 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ha | +0.053 |
few | +0.049 |
Time | +0.046 |
Little | +0.044 |
www | +0.043 |
Neg logit contributions | |
anks | -0.055 |
unes | -0.054 |
ishes | -0.053 |
fault | -0.052 |
aces | -0.052 |
Token | � |
Token ID | 241 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
ha | +0.038 |
Little | +0.033 |
few | +0.033 |
ww | +0.031 |
Time | +0.031 |
Neg logit contributions | |
anks | -0.037 |
unes | -0.036 |
fault | -0.035 |
aces | -0.033 |
ware | -0.033 |
Token | A |
Token ID | 32 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
fault | +0.002 |
ware | +0.002 |
unes | +0.002 |
depending | +0.002 |
anks | +0.002 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
unt | -0.001 |
ww | -0.001 |
uren | -0.001 |
Token | ww |
Token ID | 1383 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
ware | +0.005 |
fault | +0.005 |
unes | +0.004 |
rier | +0.004 |
anks | +0.004 |
Neg logit contributions | |
Kelly | -0.003 |
Charlie | -0.003 |
Kelly | -0.002 |
Sarah | -0.002 |
T | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
Time | +0.122 |
While | +0.122 |
ha | +0.121 |
Charlie | +0.119 |
Sarah | +0.117 |
Neg logit contributions | |
ishes | -0.190 |
unes | -0.189 |
anks | -0.187 |
ware | -0.185 |
aces | -0.180 |
Token | okay |
Token ID | 8788 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ha | +0.029 |
Little | +0.025 |
Charlie | +0.024 |
T | +0.024 |
While | +0.024 |
Neg logit contributions | |
unes | -0.033 |
ware | -0.033 |
fault | -0.033 |
ishes | -0.032 |
depending | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
ha | +0.034 |
Little | +0.030 |
uren | +0.030 |
Time | +0.029 |
Charlie | +0.029 |
Neg logit contributions | |
fault | -0.027 |
ishes | -0.027 |
unes | -0.027 |
anks | -0.027 |
ware | -0.026 |
Token | â |
Token ID | 22940 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.004 |
www | +0.003 |
ww | +0.003 |
few | +0.003 |
Neg logit contributions | |
ishes | -0.004 |
anks | -0.004 |
ware | -0.004 |
unes | -0.004 |
fault | -0.004 |
Token | € |
Token ID | 26391 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
ha | +0.033 |
few | +0.031 |
T | +0.030 |
Little | +0.028 |
While | +0.028 |
Neg logit contributions | |
anks | -0.032 |
unes | -0.031 |
ishes | -0.029 |
aces | -0.029 |
ware | -0.029 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
www | +0.002 |
ww | +0.002 |
few | +0.002 |
Neg logit contributions | |
anks | -0.004 |
ishes | -0.004 |
unes | -0.004 |
ware | -0.004 |
fault | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +5.87e-04 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
unt | +0.001 |
www | +0.001 |
few | +0.001 |
Neg logit contributions | |
ishes | -0.004 |
anks | -0.004 |
ware | -0.004 |
unes | -0.004 |
fault | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
ishes | +0.001 |
ware | +0.001 |
anks | +0.001 |
unes | +0.001 |
fault | +0.001 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.001 |
ww | -0.001 |
few | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
ha | +0.001 |
www | +0.001 |
few | +0.001 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
ware | -0.003 |
ests | -0.003 |
ishes | -0.003 |
els | -0.003 |
ases | -0.003 |
Token | re |
Token ID | 302 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
ware | +0.022 |
ishes | +0.022 |
unes | +0.021 |
anks | +0.021 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.013 |
www | -0.012 |
ww | -0.012 |
Time | -0.012 |
Token | ind |
Token ID | 521 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
ha | +0.057 |
Little | +0.047 |
www | +0.047 |
unt | +0.046 |
ww | +0.046 |
Neg logit contributions | |
unes | -0.086 |
anks | -0.084 |
ishes | -0.082 |
fault | -0.082 |
ware | -0.080 |
Token | eer |
Token ID | 28153 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
ha | +0.211 |
Little | +0.186 |
unt | +0.184 |
www | +0.184 |
few | +0.182 |
Neg logit contributions | |
anks | -0.122 |
unes | -0.118 |
fault | -0.115 |
ishes | -0.115 |
ware | -0.110 |
Token | nods |
Token ID | 34833 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ha | +0.036 |
Little | +0.031 |
www | +0.029 |
few | +0.029 |
uren | +0.029 |
Neg logit contributions | |
anks | -0.050 |
unes | -0.049 |
ishes | -0.049 |
fault | -0.048 |
ware | -0.048 |
Token | again |
Token ID | 757 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
ha | +0.022 |
Little | +0.019 |
few | +0.018 |
T | +0.018 |
Time | +0.018 |
Neg logit contributions | |
ishes | -0.042 |
unes | -0.041 |
anks | -0.041 |
fault | -0.040 |
ware | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
ishes | +0.015 |
anks | +0.015 |
ware | +0.015 |
unes | +0.015 |
fault | +0.015 |
Neg logit contributions | |
ha | -0.011 |
Little | -0.010 |
www | -0.009 |
few | -0.009 |
ww | -0.009 |
Token | win |
Token ID | 1592 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
www | +0.007 |
few | +0.007 |
Time | +0.007 |
Neg logit contributions | |
unes | -0.011 |
anks | -0.011 |
ishes | -0.010 |
ware | -0.010 |
fault | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
ishes | +0.046 |
anks | +0.046 |
ware | +0.046 |
unes | +0.046 |
fault | +0.045 |
Neg logit contributions | |
ha | -0.030 |
Little | -0.026 |
www | -0.025 |
ww | -0.025 |
few | -0.024 |
Token | there |
Token ID | 612 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
ha | +0.003 |
Little | +0.003 |
few | +0.002 |
www | +0.002 |
ww | +0.002 |
Neg logit contributions | |
ishes | -0.004 |
anks | -0.004 |
ware | -0.004 |
unes | -0.004 |
fault | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.30e-05 |
Pos logit contributions | |
ha | +0.003 |
Little | +0.003 |
few | +0.002 |
Time | +0.002 |
unt | +0.002 |
Neg logit contributions | |
anks | -0.008 |
ishes | -0.008 |
unes | -0.007 |
ware | -0.007 |
aces | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
ishes | +0.000 |
unes | +0.000 |
ware | +0.000 |
anks | +0.000 |
fault | +0.000 |
Neg logit contributions | |
ha | -0.000 |
Little | -0.000 |
www | -0.000 |
unt | -0.000 |
ww | -0.000 |
Token | re |
Token ID | 302 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
ha | +0.020 |
Time | +0.016 |
www | +0.016 |
Alice | +0.015 |
Kelly | +0.015 |
Neg logit contributions | |
ware | -0.034 |
ishes | -0.033 |
kins | -0.032 |
rier | -0.032 |
melon | -0.032 |
Token | ind |
Token ID | 521 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
ha | +0.063 |
Little | +0.055 |
www | +0.053 |
Time | +0.052 |
ww | +0.052 |
Neg logit contributions | |
ishes | -0.079 |
ware | -0.078 |
anks | -0.078 |
unes | -0.077 |
fault | -0.076 |
Token | eer |
Token ID | 28153 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
ha | +0.232 |
Little | +0.212 |
www | +0.207 |
ww | +0.206 |
few | +0.205 |
Neg logit contributions | |
ishes | -0.097 |
anks | -0.097 |
ware | -0.095 |
unes | -0.095 |
fault | -0.091 |
Token | named |
Token ID | 3706 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
ha | +0.041 |
Little | +0.036 |
www | +0.034 |
Time | +0.034 |
ww | +0.034 |
Neg logit contributions | |
ishes | -0.051 |
ware | -0.051 |
anks | -0.051 |
unes | -0.050 |
fault | -0.049 |
Token | S |
Token ID | 311 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ha | +0.015 |
Time | +0.013 |
Little | +0.013 |
www | +0.013 |
ww | +0.012 |
Neg logit contributions | |
ishes | -0.013 |
unes | -0.013 |
ware | -0.013 |
anks | -0.012 |
fault | -0.012 |
Token | illy |
Token ID | 6548 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
ishes | +0.025 |
anks | +0.025 |
ware | +0.025 |
unes | +0.024 |
fault | +0.024 |
Neg logit contributions | |
ha | -0.023 |
Little | -0.020 |
unt | -0.019 |
www | -0.019 |
T | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-03 |
Pos logit contributions | |
ha | +0.042 |
Little | +0.037 |
www | +0.035 |
few | +0.035 |
ww | +0.035 |
Neg logit contributions | |
ishes | -0.054 |
anks | -0.053 |
unes | -0.053 |
ware | -0.053 |
fault | -0.052 |
Token | â |
Token ID | 22940 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ishes | +0.027 |
ware | +0.027 |
anks | +0.027 |
unes | +0.026 |
fault | +0.026 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.018 |
www | -0.017 |
few | -0.016 |
Time | -0.016 |
Token | € |
Token ID | 26391 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ha | +0.033 |
few | +0.029 |
Little | +0.029 |
Time | +0.027 |
ww | +0.027 |
Neg logit contributions | |
anks | -0.034 |
unes | -0.033 |
ishes | -0.033 |
ware | -0.033 |
fault | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -3.68e-03 |
Pos logit contributions | |
ha | +0.044 |
few | +0.040 |
Time | +0.038 |
www | +0.037 |
ww | +0.037 |
Neg logit contributions | |
anks | -0.051 |
unes | -0.050 |
fault | -0.049 |
ishes | -0.048 |
aces | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
ha | +0.006 |
ww | +0.005 |
www | +0.005 |
few | +0.005 |
uren | +0.005 |
Neg logit contributions | |
unes | -0.007 |
anks | -0.007 |
ware | -0.007 |
fault | -0.007 |
ests | -0.007 |
Token | C |
Token ID | 34 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ha | +0.005 |
Kelly | +0.005 |
ww | +0.005 |
Margaret | +0.004 |
www | +0.004 |
Neg logit contributions | |
ests | -0.010 |
ware | -0.010 |
depending | -0.010 |
unes | -0.010 |
auc | -0.010 |
Token | ind |
Token ID | 521 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
ha | +0.043 |
Little | +0.038 |
few | +0.038 |
www | +0.037 |
Time | +0.037 |
Neg logit contributions | |
ishes | -0.042 |
ware | -0.042 |
anks | -0.042 |
unes | -0.042 |
fault | -0.040 |
Token | y |
Token ID | 88 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ha | +0.155 |
Little | +0.139 |
www | +0.134 |
Time | +0.133 |
few | +0.132 |
Neg logit contributions | |
ishes | -0.173 |
ware | -0.171 |
unes | -0.169 |
anks | -0.168 |
fault | -0.164 |
Token | said |
Token ID | 531 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ha | +0.048 |
Time | +0.044 |
Little | +0.043 |
ww | +0.043 |
www | +0.042 |
Neg logit contributions | |
ware | -0.059 |
ishes | -0.058 |
anks | -0.057 |
unes | -0.056 |
aces | -0.056 |
Token | yes |
Token ID | 3763 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
ha | +0.028 |
Little | +0.025 |
Time | +0.024 |
www | +0.024 |
ww | +0.023 |
Neg logit contributions | |
ware | -0.045 |
unes | -0.044 |
anks | -0.044 |
ishes | -0.043 |
fault | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
anks | +0.033 |
unes | +0.032 |
fault | +0.032 |
ware | +0.031 |
ishes | +0.031 |
Neg logit contributions | |
ha | -0.025 |
Little | -0.022 |
Time | -0.022 |
ww | -0.021 |
www | -0.021 |
Token | so |
Token ID | 523 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ha | +0.023 |
Little | +0.020 |
ww | +0.020 |
www | +0.019 |
Time | +0.019 |
Neg logit contributions | |
unes | -0.023 |
ware | -0.023 |
anks | -0.022 |
depending | -0.022 |
ishes | -0.022 |
Token | there |
Token ID | 612 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
ha | +0.016 |
www | +0.015 |
Little | +0.014 |
uren | +0.014 |
unt | +0.014 |
Neg logit contributions | |
ishes | -0.020 |
ware | -0.020 |
aces | -0.019 |
fault | -0.019 |
kins | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +9.41e-04 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.008 |
anks | -0.008 |
ware | -0.008 |
unes | -0.008 |
fault | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
unes | +0.002 |
ware | +0.002 |
fault | +0.002 |
ishes | +0.002 |
anks | +0.002 |
Neg logit contributions | |
ha | -0.001 |
www | -0.001 |
Little | -0.001 |
unt | -0.001 |
uren | -0.001 |
Token | poor |
Token ID | 3595 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
ha | +0.021 |
Alice | +0.017 |
Time | +0.017 |
www | +0.017 |
Kelly | +0.016 |
Neg logit contributions | |
ware | -0.034 |
ishes | -0.033 |
rier | -0.032 |
kins | -0.032 |
melon | -0.031 |
Token | re |
Token ID | 302 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
ha | +0.029 |
Little | +0.026 |
Time | +0.025 |
Alice | +0.024 |
Charlie | +0.023 |
Neg logit contributions | |
ware | -0.048 |
ishes | -0.046 |
unes | -0.045 |
fault | -0.044 |
anks | -0.044 |
Token | ind |
Token ID | 521 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
ha | +0.063 |
Little | +0.055 |
Time | +0.053 |
www | +0.053 |
ww | +0.052 |
Neg logit contributions | |
ishes | -0.072 |
ware | -0.070 |
anks | -0.069 |
unes | -0.069 |
fault | -0.067 |
Token | eer |
Token ID | 28153 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ha | +0.234 |
Little | +0.215 |
www | +0.210 |
ww | +0.208 |
few | +0.208 |
Neg logit contributions | |
ishes | -0.094 |
ware | -0.092 |
anks | -0.092 |
unes | -0.091 |
fault | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
ha | +0.041 |
Little | +0.035 |
www | +0.034 |
Time | +0.034 |
ww | +0.033 |
Neg logit contributions | |
ishes | -0.050 |
ware | -0.050 |
anks | -0.050 |
unes | -0.049 |
fault | -0.048 |
Token | He |
Token ID | 679 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
www | +0.002 |
ww | +0.002 |
Time | +0.002 |
Neg logit contributions | |
unes | -0.002 |
ware | -0.002 |
anks | -0.002 |
ishes | -0.002 |
fault | -0.002 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ware | +0.010 |
ishes | +0.010 |
anks | +0.010 |
unes | +0.010 |
fault | +0.009 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.007 |
www | -0.007 |
Time | -0.007 |
ww | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
ha | +0.017 |
Little | +0.015 |
www | +0.014 |
ww | +0.014 |
Time | +0.013 |
Neg logit contributions | |
anks | -0.029 |
ware | -0.029 |
unes | -0.029 |
ishes | -0.029 |
fault | -0.028 |
Token | I |
Token ID | 314 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ha | +0.024 |
Little | +0.020 |
unt | +0.019 |
www | +0.019 |
ww | +0.019 |
Neg logit contributions | |
ishes | -0.046 |
anks | -0.046 |
ware | -0.045 |
unes | -0.045 |
fault | -0.044 |
Token | play |
Token ID | 711 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
ha | +0.043 |
Little | +0.036 |
few | +0.034 |
www | +0.034 |
ww | +0.033 |
Neg logit contributions | |
ishes | -0.074 |
ware | -0.074 |
unes | -0.073 |
anks | -0.073 |
fault | -0.072 |
Token | with |
Token ID | 351 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ha | +0.026 |
Little | +0.022 |
few | +0.021 |
www | +0.021 |
ww | +0.020 |
Neg logit contributions | |
ishes | -0.040 |
unes | -0.040 |
anks | -0.039 |
fault | -0.039 |
ware | -0.039 |
Token | your |
Token ID | 534 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
ishes | +0.029 |
ware | +0.029 |
unes | +0.029 |
anks | +0.029 |
fault | +0.028 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.015 |
www | -0.014 |
Time | -0.014 |
ww | -0.014 |
Token | re |
Token ID | 302 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
ha | +0.036 |
few | +0.033 |
little | +0.032 |
long | +0.031 |
ww | +0.030 |
Neg logit contributions | |
anks | -0.052 |
unes | -0.052 |
ishes | -0.051 |
ware | -0.050 |
fault | -0.049 |
Token | ind |
Token ID | 521 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
ha | +0.052 |
ww | +0.044 |
few | +0.043 |
unt | +0.043 |
www | +0.043 |
Neg logit contributions | |
unes | -0.081 |
anks | -0.079 |
ware | -0.078 |
fault | -0.077 |
depending | -0.075 |
Token | eer |
Token ID | 28153 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ha | +0.202 |
ww | +0.178 |
few | +0.177 |
unt | +0.177 |
www | +0.175 |
Neg logit contributions | |
anks | -0.122 |
unes | -0.117 |
fault | -0.114 |
ware | -0.113 |
ishes | -0.112 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
ha | +0.032 |
Little | +0.028 |
www | +0.026 |
few | +0.026 |
ww | +0.026 |
Neg logit contributions | |
ware | -0.040 |
unes | -0.040 |
ishes | -0.040 |
anks | -0.040 |
fault | -0.039 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.003 |
www | +0.003 |
ww | +0.003 |
Time | +0.003 |
Neg logit contributions | |
ishes | -0.006 |
ware | -0.006 |
anks | -0.006 |
unes | -0.006 |
fault | -0.006 |
Token | asks |
Token ID | 7893 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
unes | +0.057 |
anks | +0.056 |
ishes | +0.056 |
fault | +0.055 |
ware | +0.055 |
Neg logit contributions | |
ha | -0.024 |
Little | -0.020 |
unt | -0.019 |
few | -0.018 |
uren | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
ha | +0.028 |
Little | +0.024 |
few | +0.023 |
T | +0.022 |
Kelly | +0.022 |
Neg logit contributions | |
ishes | -0.048 |
fault | -0.047 |
anks | -0.047 |
unes | -0.047 |
ware | -0.047 |
Token | merry |
Token ID | 44570 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ishes | +0.024 |
anks | +0.023 |
ware | +0.023 |
unes | +0.023 |
fault | +0.023 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.016 |
www | -0.015 |
few | -0.015 |
ww | -0.015 |
Token | way |
Token ID | 835 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
ha | +0.025 |
Little | +0.023 |
Time | +0.022 |
T | +0.021 |
www | +0.021 |
Neg logit contributions | |
ishes | -0.033 |
anks | -0.033 |
ware | -0.033 |
fault | -0.032 |
aces | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
www | +0.002 |
Time | +0.002 |
ww | +0.002 |
Neg logit contributions | |
fault | -0.002 |
anks | -0.002 |
unes | -0.002 |
ishes | -0.002 |
ware | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
unes | +0.029 |
anks | +0.029 |
ishes | +0.029 |
ware | +0.029 |
fault | +0.028 |
Neg logit contributions | |
ha | -0.027 |
Little | -0.023 |
www | -0.023 |
ww | -0.022 |
few | -0.022 |
Token | C |
Token ID | 34 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
anks | +0.045 |
ishes | +0.045 |
ware | +0.045 |
unes | +0.045 |
fault | +0.043 |
Neg logit contributions | |
ha | -0.031 |
Little | -0.027 |
www | -0.027 |
ww | -0.026 |
few | -0.026 |
Token | ind |
Token ID | 521 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
ha | +0.041 |
Little | +0.036 |
www | +0.035 |
few | +0.034 |
ww | +0.034 |
Neg logit contributions | |
ishes | -0.048 |
ware | -0.047 |
anks | -0.047 |
unes | -0.047 |
fault | -0.045 |
Token | y |
Token ID | 88 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
ha | +0.181 |
Little | +0.165 |
www | +0.160 |
Time | +0.158 |
ww | +0.157 |
Neg logit contributions | |
ishes | -0.144 |
ware | -0.141 |
anks | -0.139 |
unes | -0.139 |
fault | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
ha | +0.053 |
Time | +0.047 |
www | +0.046 |
Little | +0.045 |
ww | +0.045 |
Neg logit contributions | |
ishes | -0.063 |
ware | -0.062 |
anks | -0.061 |
unes | -0.060 |
fault | -0.059 |
Token | her |
Token ID | 607 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.005 |
few | +0.004 |
Time | +0.004 |
www | +0.004 |
Neg logit contributions | |
ishes | -0.006 |
unes | -0.006 |
melon | -0.006 |
anks | -0.005 |
ocular | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.79e-06 |
Pos logit contributions | |
ha | +0.017 |
Little | +0.015 |
www | +0.015 |
Time | +0.014 |
ww | +0.014 |
Neg logit contributions | |
ishes | -0.021 |
ware | -0.021 |
anks | -0.021 |
unes | -0.020 |
fault | -0.020 |
Token | my |
Token ID | 1820 |
Feature activation | -4.02e-03 |
Token | . |
Token ID | 13 |
Feature activation | -7.06e-04 |
Pos logit contributions | |
ha | +0.023 |
Little | +0.020 |
www | +0.019 |
few | +0.019 |
ww | +0.019 |
Neg logit contributions | |
ishes | -0.034 |
anks | -0.034 |
unes | -0.034 |
ware | -0.034 |
fault | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -6.60e-03 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
ww | +0.001 |
www | +0.001 |
Time | +0.001 |
Neg logit contributions | |
unes | -0.001 |
ware | -0.001 |
anks | -0.001 |
ishes | -0.001 |
fault | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -7.58e-03 |
Pos logit contributions | |
ha | +0.011 |
ww | +0.011 |
www | +0.010 |
uren | +0.010 |
few | +0.010 |
Neg logit contributions | |
ware | -0.011 |
ests | -0.011 |
unes | -0.011 |
fault | -0.011 |
anks | -0.011 |
Token | " |
Token ID | 1 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ha | +0.011 |
night | +0.010 |
thunder | +0.010 |
ww | +0.010 |
evening | +0.009 |
Neg logit contributions | |
ests | -0.012 |
auc | -0.012 |
bugs | -0.011 |
ectar | -0.011 |
self | -0.011 |
Token | E |
Token ID | 36 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ha | +0.016 |
www | +0.013 |
few | +0.013 |
unt | +0.013 |
ww | +0.012 |
Neg logit contributions | |
ware | -0.026 |
ishes | -0.025 |
unes | -0.024 |
anks | -0.023 |
ests | -0.023 |
Token | ww |
Token ID | 1383 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
ha | +0.044 |
Little | +0.039 |
Time | +0.037 |
few | +0.037 |
unt | +0.037 |
Neg logit contributions | |
ishes | -0.064 |
ware | -0.063 |
unes | -0.062 |
anks | -0.062 |
fault | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
Time | +0.128 |
ha | +0.125 |
Alice | +0.125 |
Little | +0.123 |
Sarah | +0.121 |
Neg logit contributions | |
ishes | -0.194 |
unes | -0.187 |
anks | -0.186 |
ware | -0.180 |
aces | -0.171 |
Token | this |
Token ID | 428 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ha | +0.021 |
Little | +0.018 |
www | +0.017 |
Time | +0.017 |
uren | +0.017 |
Neg logit contributions | |
ware | -0.029 |
unes | -0.028 |
ishes | -0.028 |
fault | -0.027 |
anks | -0.027 |
Token | fish |
Token ID | 5916 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
ishes | +0.043 |
anks | +0.043 |
unes | +0.043 |
ware | +0.043 |
fault | +0.041 |
Neg logit contributions | |
ha | -0.048 |
Little | -0.043 |
www | -0.042 |
ww | -0.041 |
few | -0.041 |
Token | is |
Token ID | 318 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
unes | +0.018 |
anks | +0.018 |
ware | +0.018 |
ishes | +0.018 |
fault | +0.018 |
Neg logit contributions | |
ha | -0.016 |
www | -0.014 |
ww | -0.014 |
Little | -0.013 |
few | -0.013 |
Token | sm |
Token ID | 895 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
ishes | +0.007 |
ware | +0.007 |
anks | +0.007 |
unes | +0.007 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.005 |
Little | -0.004 |
www | -0.004 |
few | -0.004 |
ww | -0.004 |
Token | € |
Token ID | 26391 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
ha | +0.048 |
few | +0.043 |
Little | +0.041 |
www | +0.040 |
T | +0.040 |
Neg logit contributions | |
anks | -0.050 |
unes | -0.049 |
ishes | -0.048 |
aces | -0.047 |
ware | -0.046 |
Token | ™ |
Token ID | 8151 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
ha | +0.056 |
few | +0.051 |
Time | +0.050 |
Little | +0.049 |
www | +0.047 |
Neg logit contributions | |
unes | -0.068 |
anks | -0.068 |
aces | -0.065 |
fault | -0.063 |
ric | -0.063 |
Token | s |
Token ID | 82 |
Feature activation | -3.86e-03 |
Pos logit contributions | |
ha | +0.055 |
Little | +0.048 |
www | +0.047 |
ww | +0.046 |
few | +0.046 |
Neg logit contributions | |
ishes | -0.052 |
ware | -0.052 |
anks | -0.051 |
unes | -0.051 |
fault | -0.049 |
Token | okay |
Token ID | 8788 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
ha | +0.007 |
Little | +0.006 |
www | +0.006 |
uren | +0.006 |
ww | +0.006 |
Neg logit contributions | |
unes | -0.008 |
ishes | -0.008 |
fault | -0.007 |
anks | -0.007 |
ware | -0.007 |
Token | sweet |
Token ID | 6029 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ha | +0.032 |
Little | +0.027 |
Time | +0.026 |
www | +0.026 |
uren | +0.026 |
Neg logit contributions | |
fault | -0.037 |
ishes | -0.036 |
unes | -0.036 |
anks | -0.036 |
ware | -0.035 |
Token | heart |
Token ID | 11499 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
ha | +0.036 |
Little | +0.032 |
Alice | +0.030 |
Time | +0.030 |
Charlie | +0.030 |
Neg logit contributions | |
ishes | -0.044 |
ware | -0.044 |
unes | -0.044 |
anks | -0.043 |
fault | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
ha | +0.133 |
Little | +0.116 |
www | +0.110 |
Time | +0.109 |
ww | +0.108 |
Neg logit contributions | |
ishes | -0.186 |
anks | -0.185 |
ware | -0.185 |
unes | -0.184 |
fault | -0.181 |
Token | How |
Token ID | 1374 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
few | +0.004 |
Neg logit contributions | |
unes | -0.005 |
ishes | -0.005 |
anks | -0.005 |
ware | -0.005 |
fault | -0.005 |
Token | about |
Token ID | 546 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ishes | +0.031 |
ware | +0.030 |
anks | +0.030 |
unes | +0.030 |
fault | +0.029 |
Neg logit contributions | |
ha | -0.029 |
Little | -0.026 |
www | -0.025 |
ww | -0.024 |
few | -0.024 |
Token | I |
Token ID | 314 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ha | +0.061 |
Little | +0.051 |
www | +0.049 |
Time | +0.049 |
ww | +0.048 |
Neg logit contributions | |
ishes | -0.089 |
ware | -0.087 |
unes | -0.086 |
anks | -0.086 |
fault | -0.084 |
Token | give |
Token ID | 1577 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ha | +0.033 |
Little | +0.029 |
www | +0.028 |
ww | +0.028 |
Time | +0.027 |
Neg logit contributions | |
anks | -0.039 |
ware | -0.039 |
ishes | -0.039 |
fault | -0.039 |
unes | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
ha | +0.013 |
Little | +0.011 |
www | +0.011 |
ww | +0.011 |
uren | +0.011 |
Neg logit contributions | |
ware | -0.014 |
ishes | -0.014 |
unes | -0.014 |
fault | -0.014 |
anks | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
few | +0.004 |
Neg logit contributions | |
ishes | -0.007 |
anks | -0.007 |
unes | -0.007 |
ware | -0.007 |
fault | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.94e-03 |
Pos logit contributions | |
ha | +0.011 |
ww | +0.011 |
www | +0.010 |
uren | +0.010 |
few | +0.010 |
Neg logit contributions | |
els | -0.010 |
ware | -0.010 |
unes | -0.010 |
ests | -0.010 |
anks | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ha | +0.011 |
woke | +0.009 |
night | +0.009 |
zing | +0.009 |
few | +0.009 |
Neg logit contributions | |
els | -0.014 |
ases | -0.014 |
bugs | -0.013 |
neys | -0.013 |
olds | -0.013 |
Token | re |
Token ID | 302 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ware | +0.025 |
ishes | +0.024 |
unes | +0.024 |
fault | +0.024 |
anks | +0.024 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.011 |
www | -0.011 |
ww | -0.011 |
Time | -0.011 |
Token | ind |
Token ID | 521 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
ha | +0.058 |
Little | +0.050 |
www | +0.048 |
ww | +0.047 |
few | +0.047 |
Neg logit contributions | |
anks | -0.083 |
unes | -0.083 |
ishes | -0.082 |
ware | -0.082 |
fault | -0.081 |
Token | eer |
Token ID | 28153 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
ha | +0.222 |
Little | +0.203 |
www | +0.198 |
few | +0.196 |
ww | +0.196 |
Neg logit contributions | |
anks | -0.099 |
ishes | -0.097 |
unes | -0.097 |
ware | -0.096 |
fault | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
ha | +0.034 |
Little | +0.030 |
www | +0.029 |
ww | +0.028 |
Time | +0.028 |
Neg logit contributions | |
ishes | -0.050 |
ware | -0.050 |
anks | -0.049 |
unes | -0.049 |
fault | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -9.09e-03 |
Pos logit contributions | |
ha | +0.011 |
Little | +0.010 |
www | +0.009 |
ww | +0.009 |
Time | +0.009 |
Neg logit contributions | |
ware | -0.018 |
ishes | -0.018 |
unes | -0.018 |
anks | -0.018 |
fault | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
ha | +0.014 |
Little | +0.012 |
www | +0.011 |
ww | +0.011 |
Time | +0.011 |
Neg logit contributions | |
ware | -0.021 |
ishes | -0.020 |
unes | -0.020 |
anks | -0.020 |
fault | -0.020 |
Token | became |
Token ID | 2627 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
ha | +0.029 |
Little | +0.025 |
www | +0.024 |
few | +0.024 |
Time | +0.024 |
Neg logit contributions | |
ishes | -0.042 |
ware | -0.041 |
anks | -0.041 |
unes | -0.041 |
fault | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
ha | +0.006 |
few | +0.005 |
Little | +0.005 |
T | +0.005 |
unt | +0.005 |
Neg logit contributions | |
ishes | -0.011 |
ware | -0.011 |
unes | -0.011 |
anks | -0.010 |
fault | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | -8.07e-03 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
Time | +0.007 |
unt | +0.007 |
few | +0.007 |
Neg logit contributions | |
ishes | -0.017 |
ware | -0.017 |
anks | -0.016 |
unes | -0.016 |
fault | -0.016 |
Token | hugs |
Token ID | 40657 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ha | +0.015 |
Little | +0.013 |
Time | +0.012 |
www | +0.012 |
few | +0.012 |
Neg logit contributions | |
unes | -0.015 |
anks | -0.015 |
ishes | -0.015 |
ware | -0.014 |
fault | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
ha | +0.016 |
Little | +0.014 |
www | +0.013 |
Time | +0.013 |
few | +0.013 |
Neg logit contributions | |
ishes | -0.024 |
anks | -0.024 |
ware | -0.024 |
unes | -0.024 |
fault | -0.024 |
Token | re |
Token ID | 302 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ha | +0.013 |
Little | +0.012 |
www | +0.011 |
ww | +0.011 |
Time | +0.011 |
Neg logit contributions | |
ware | -0.015 |
ishes | -0.015 |
unes | -0.014 |
anks | -0.014 |
fault | -0.014 |
Token | ind |
Token ID | 521 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
ha | +0.044 |
unt | +0.037 |
Little | +0.036 |
www | +0.035 |
T | +0.035 |
Neg logit contributions | |
unes | -0.080 |
anks | -0.079 |
fault | -0.077 |
ware | -0.076 |
ishes | -0.076 |
Token | eer |
Token ID | 28153 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ha | +0.205 |
Little | +0.182 |
unt | +0.181 |
few | +0.180 |
www | +0.180 |
Neg logit contributions | |
anks | -0.112 |
unes | -0.107 |
fault | -0.106 |
ishes | -0.105 |
ware | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -6.51e-03 |
Pos logit contributions | |
ha | +0.029 |
Little | +0.025 |
few | +0.024 |
www | +0.023 |
ww | +0.023 |
Neg logit contributions | |
ishes | -0.044 |
ware | -0.044 |
anks | -0.044 |
unes | -0.044 |
fault | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
Time | +0.007 |
unt | +0.007 |
www | +0.007 |
Neg logit contributions | |
ishes | -0.016 |
ware | -0.016 |
anks | -0.016 |
unes | -0.016 |
fault | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -7.29e-03 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
www | +0.006 |
Time | +0.006 |
unt | +0.006 |
Neg logit contributions | |
ishes | -0.015 |
ware | -0.015 |
anks | -0.015 |
unes | -0.015 |
fault | -0.014 |
Token | " |
Token ID | 1 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ha | +0.009 |
www | +0.008 |
few | +0.007 |
zing | +0.007 |
ww | +0.007 |
Neg logit contributions | |
els | -0.015 |
ishes | -0.015 |
ases | -0.015 |
ware | -0.015 |
kins | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ishes | +0.023 |
ware | +0.023 |
anks | +0.023 |
unes | +0.023 |
fault | +0.022 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.016 |
www | -0.015 |
Time | -0.015 |
ww | -0.015 |
Token | picks |
Token ID | 11103 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
ha | +0.019 |
Little | +0.016 |
www | +0.015 |
few | +0.015 |
Time | +0.015 |
Neg logit contributions | |
anks | -0.024 |
unes | -0.024 |
ishes | -0.024 |
ware | -0.023 |
fault | -0.023 |
Token | up |
Token ID | 510 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ishes | +0.004 |
ware | +0.004 |
anks | +0.004 |
unes | +0.004 |
fault | +0.004 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.004 |
www | -0.004 |
Time | -0.003 |
ww | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
ha | +0.033 |
Little | +0.028 |
www | +0.027 |
Time | +0.026 |
ww | +0.026 |
Neg logit contributions | |
ishes | -0.061 |
ware | -0.060 |
unes | -0.060 |
anks | -0.059 |
fault | -0.058 |
Token | re |
Token ID | 302 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ha | +0.009 |
Little | +0.008 |
few | +0.008 |
www | +0.007 |
ww | +0.007 |
Neg logit contributions | |
anks | -0.010 |
ishes | -0.010 |
unes | -0.010 |
ware | -0.010 |
fault | -0.009 |
Token | ind |
Token ID | 521 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
ha | +0.050 |
Little | +0.042 |
www | +0.041 |
few | +0.041 |
ww | +0.041 |
Neg logit contributions | |
unes | -0.078 |
anks | -0.078 |
fault | -0.075 |
ware | -0.075 |
ishes | -0.075 |
Token | eer |
Token ID | 28153 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
ha | +0.204 |
Little | +0.184 |
few | +0.181 |
www | +0.180 |
ww | +0.179 |
Neg logit contributions | |
anks | -0.112 |
unes | -0.107 |
fault | -0.105 |
ishes | -0.105 |
ware | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
ha | +0.026 |
Little | +0.023 |
www | +0.021 |
few | +0.021 |
ww | +0.021 |
Neg logit contributions | |
ishes | -0.042 |
anks | -0.042 |
ware | -0.042 |
unes | -0.042 |
fault | -0.041 |
Token | She |
Token ID | 1375 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
few | +0.004 |
Neg logit contributions | |
ishes | -0.006 |
ware | -0.006 |
anks | -0.006 |
unes | -0.006 |
fault | -0.006 |
Token | looks |
Token ID | 3073 |
Feature activation | +5.86e-03 |
Pos logit contributions | |
ha | +0.020 |
Little | +0.018 |
few | +0.017 |
uren | +0.017 |
unt | +0.016 |
Neg logit contributions | |
unes | -0.022 |
anks | -0.022 |
ishes | -0.021 |
fault | -0.020 |
rier | -0.020 |
Token | at |
Token ID | 379 |
Feature activation | -9.25e-03 |
Pos logit contributions | |
ware | +0.013 |
anks | +0.013 |
ishes | +0.013 |
unes | +0.013 |
fault | +0.013 |
Neg logit contributions | |
ha | -0.009 |
Little | -0.008 |
few | -0.007 |
www | -0.007 |
ww | -0.007 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.44e-03 |
Pos logit contributions | |
ishes | +0.008 |
ware | +0.008 |
anks | +0.008 |
unes | +0.008 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
Time | -0.005 |
few | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
few | +0.004 |
www | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.009 |
anks | -0.008 |
unes | -0.008 |
ware | -0.008 |
fault | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ha | +0.014 |
Little | +0.012 |
www | +0.011 |
ww | +0.011 |
Time | +0.011 |
Neg logit contributions | |
ishes | -0.024 |
ware | -0.024 |
anks | -0.024 |
unes | -0.024 |
fault | -0.024 |
Token | " |
Token ID | 1 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ha | +0.013 |
www | +0.010 |
unt | +0.010 |
Kelly | +0.010 |
ww | +0.010 |
Neg logit contributions | |
ware | -0.027 |
kins | -0.027 |
ishes | -0.027 |
ests | -0.027 |
wounds | -0.026 |
Token | A |
Token ID | 32 |
Feature activation | -3.66e-04 |
Pos logit contributions | |
ha | +0.021 |
Little | +0.017 |
www | +0.017 |
unt | +0.017 |
few | +0.016 |
Neg logit contributions | |
ware | -0.035 |
ishes | -0.034 |
unes | -0.034 |
anks | -0.034 |
fault | -0.033 |
Token | ww |
Token ID | 1383 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
Little | +0.001 |
Sarah | +0.001 |
John | +0.001 |
ha | +0.001 |
Kelly | +0.001 |
Neg logit contributions | |
ware | -0.001 |
rier | -0.001 |
ishes | -0.001 |
fault | -0.001 |
anks | -0.001 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
Sarah | +0.127 |
Little | +0.126 |
Alice | +0.124 |
Time | +0.124 |
T | +0.124 |
Neg logit contributions | |
ishes | -0.175 |
anks | -0.172 |
unes | -0.168 |
ware | -0.166 |
aces | -0.155 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
www | +0.007 |
ww | +0.007 |
Time | +0.007 |
Neg logit contributions | |
ware | -0.013 |
ishes | -0.013 |
anks | -0.013 |
unes | -0.012 |
fault | -0.012 |
Token | says |
Token ID | 1139 |
Feature activation | -6.27e-03 |
Pos logit contributions | |
ishes | +0.020 |
unes | +0.020 |
ware | +0.020 |
anks | +0.019 |
rier | +0.019 |
Neg logit contributions | |
ha | -0.024 |
Little | -0.021 |
unt | -0.020 |
www | -0.020 |
uren | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ha | +0.009 |
Little | +0.007 |
few | +0.007 |
T | +0.007 |
long | +0.007 |
Neg logit contributions | |
ishes | -0.015 |
ware | -0.015 |
unes | -0.014 |
anks | -0.014 |
fault | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ha | +0.015 |
Little | +0.013 |
www | +0.012 |
ww | +0.012 |
Time | +0.012 |
Neg logit contributions | |
ishes | -0.023 |
ware | -0.023 |
anks | -0.023 |
unes | -0.023 |
fault | -0.023 |
Token | But |
Token ID | 1537 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ha | +0.016 |
Little | +0.014 |
www | +0.013 |
Time | +0.013 |
ww | +0.012 |
Neg logit contributions | |
ishes | -0.031 |
anks | -0.031 |
unes | -0.031 |
ware | -0.030 |
fault | -0.030 |
Token | I |
Token ID | 314 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ha | +0.015 |
Little | +0.013 |
www | +0.012 |
ww | +0.012 |
few | +0.012 |
Neg logit contributions | |
anks | -0.026 |
ishes | -0.025 |
unes | -0.025 |
ware | -0.025 |
fault | -0.025 |
Token | like |
Token ID | 588 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
ha | +0.045 |
Little | +0.040 |
www | +0.039 |
ww | +0.038 |
unt | +0.038 |
Neg logit contributions | |
ishes | -0.042 |
fault | -0.042 |
anks | -0.042 |
ware | -0.041 |
unes | -0.041 |
Token | your |
Token ID | 534 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
anks | +0.014 |
ishes | +0.014 |
unes | +0.014 |
ware | +0.014 |
fault | +0.014 |
Neg logit contributions | |
ha | -0.007 |
Little | -0.006 |
few | -0.006 |
www | -0.005 |
ww | -0.005 |
Token | re |
Token ID | 302 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ha | +0.029 |
few | +0.027 |
little | +0.025 |
unt | +0.025 |
long | +0.025 |
Neg logit contributions | |
unes | -0.054 |
anks | -0.053 |
ishes | -0.053 |
ware | -0.052 |
aces | -0.051 |
Token | ind |
Token ID | 521 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
ha | +0.041 |
unt | +0.034 |
Little | +0.034 |
www | +0.033 |
ww | +0.033 |
Neg logit contributions | |
unes | -0.078 |
anks | -0.076 |
ware | -0.076 |
fault | -0.074 |
ishes | -0.074 |
Token | eer |
Token ID | 28153 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ha | +0.197 |
unt | +0.176 |
ww | +0.174 |
few | +0.173 |
www | +0.173 |
Neg logit contributions | |
anks | -0.110 |
ware | -0.108 |
unes | -0.107 |
ishes | -0.106 |
fault | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
ha | +0.028 |
few | +0.023 |
Little | +0.023 |
ww | +0.023 |
www | +0.023 |
Neg logit contributions | |
ware | -0.045 |
unes | -0.045 |
anks | -0.044 |
ishes | -0.044 |
fault | -0.043 |
Token | It |
Token ID | 632 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ha | +0.011 |
Little | +0.010 |
unt | +0.010 |
www | +0.009 |
ww | +0.009 |
Neg logit contributions | |
ishes | -0.017 |
ware | -0.016 |
anks | -0.016 |
fault | -0.016 |
unes | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
anks | +0.028 |
unes | +0.027 |
uggets | +0.026 |
ishes | +0.026 |
ware | +0.026 |
Neg logit contributions | |
ha | -0.017 |
ww | -0.014 |
few | -0.013 |
www | -0.013 |
unt | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
ishes | +0.004 |
ware | +0.004 |
anks | +0.004 |
unes | +0.004 |
fault | +0.004 |
Neg logit contributions | |
ha | -0.003 |
Little | -0.002 |
www | -0.002 |
few | -0.002 |
ww | -0.002 |
Token | at |
Token ID | 379 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
unt | +0.004 |
Neg logit contributions | |
ishes | -0.005 |
fault | -0.005 |
anks | -0.005 |
unes | -0.005 |
ware | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
ha | +0.006 |
Little | +0.005 |
few | +0.005 |
www | +0.005 |
unt | +0.005 |
Neg logit contributions | |
anks | -0.014 |
ware | -0.013 |
unes | -0.013 |
ishes | -0.013 |
fault | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
ishes | +0.003 |
anks | +0.003 |
unes | +0.003 |
ware | +0.003 |
fault | +0.003 |
Neg logit contributions | |
ha | -0.002 |
Little | -0.002 |
few | -0.002 |
www | -0.002 |
ww | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
ha | +0.030 |
Little | +0.026 |
www | +0.024 |
ww | +0.024 |
Time | +0.024 |
Neg logit contributions | |
ishes | -0.051 |
ware | -0.050 |
anks | -0.050 |
unes | -0.050 |
fault | -0.049 |
Token | ew |
Token ID | 413 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ha | +0.010 |
unt | +0.008 |
www | +0.008 |
Little | +0.008 |
uren | +0.008 |
Neg logit contributions | |
ishes | -0.011 |
unes | -0.011 |
ware | -0.011 |
anks | -0.011 |
aces | -0.010 |
Token | ww |
Token ID | 1383 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
ha | +0.033 |
Time | +0.030 |
Alice | +0.030 |
Little | +0.029 |
unt | +0.028 |
Neg logit contributions | |
ishes | -0.043 |
unes | -0.041 |
anks | -0.040 |
ware | -0.040 |
els | -0.039 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.00e-03 |
Pos logit contributions | |
Sarah | +0.143 |
Time | +0.142 |
Alice | +0.141 |
ha | +0.138 |
John | +0.136 |
Neg logit contributions | |
ishes | -0.171 |
unes | -0.162 |
anks | -0.162 |
ware | -0.152 |
sters | -0.148 |
Token | |
Token ID | 220 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
ishes | +0.002 |
ware | +0.002 |
anks | +0.002 |
unes | +0.002 |
fault | +0.002 |
Neg logit contributions | |
ha | -0.002 |
Little | -0.001 |
few | -0.001 |
www | -0.001 |
unt | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.004 |
unt | +0.003 |
Alice | +0.003 |
T | +0.003 |
Neg logit contributions | |
ishes | -0.012 |
ware | -0.012 |
unes | -0.012 |
anks | -0.011 |
fault | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ha | +0.023 |
ww | +0.021 |
www | +0.021 |
Time | +0.019 |
Little | +0.019 |
Neg logit contributions | |
ware | -0.024 |
anks | -0.023 |
ests | -0.023 |
unes | -0.023 |
ishes | -0.022 |
Token | One |
Token ID | 3198 |
Feature activation | +7.74e-03 |
Pos logit contributions | |
ha | +0.017 |
ww | +0.015 |
www | +0.015 |
uren | +0.013 |
zing | +0.013 |
Neg logit contributions | |
neys | -0.026 |
ware | -0.026 |
ests | -0.026 |
ocular | -0.025 |
preferences | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ha | +0.024 |
Little | +0.020 |
www | +0.019 |
ww | +0.018 |
few | +0.018 |
Neg logit contributions | |
ishes | -0.045 |
ware | -0.044 |
anks | -0.044 |
unes | -0.044 |
fault | -0.043 |
Token | sle |
Token ID | 3133 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
ha | +0.015 |
Little | +0.012 |
www | +0.012 |
ww | +0.011 |
Time | +0.011 |
Neg logit contributions | |
ishes | -0.027 |
ware | -0.027 |
anks | -0.026 |
unes | -0.026 |
fault | -0.026 |
Token | igh |
Token ID | 394 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ha | +0.053 |
Little | +0.047 |
www | +0.046 |
ww | +0.045 |
few | +0.045 |
Neg logit contributions | |
ware | -0.040 |
anks | -0.039 |
unes | -0.039 |
ishes | -0.039 |
fault | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -6.79e-03 |
Pos logit contributions | |
ha | +0.026 |
Little | +0.023 |
www | +0.022 |
Time | +0.022 |
ww | +0.022 |
Neg logit contributions | |
ware | -0.030 |
ishes | -0.030 |
anks | -0.030 |
unes | -0.030 |
aces | -0.028 |
Token | re |
Token ID | 302 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
ha | +0.011 |
Little | +0.010 |
www | +0.009 |
Time | +0.009 |
ww | +0.009 |
Neg logit contributions | |
ware | -0.015 |
ishes | -0.015 |
anks | -0.014 |
unes | -0.014 |
aces | -0.014 |
Token | ind |
Token ID | 521 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
ha | +0.047 |
Little | +0.041 |
www | +0.039 |
ww | +0.038 |
few | +0.038 |
Neg logit contributions | |
anks | -0.067 |
ware | -0.067 |
unes | -0.067 |
ishes | -0.066 |
fault | -0.065 |
Token | eer |
Token ID | 28153 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
ha | +0.216 |
Little | +0.195 |
www | +0.192 |
few | +0.190 |
ww | +0.190 |
Neg logit contributions | |
anks | -0.094 |
ware | -0.094 |
ishes | -0.094 |
unes | -0.093 |
fault | -0.090 |
Token | who |
Token ID | 508 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
ha | +0.032 |
Little | +0.029 |
www | +0.028 |
Time | +0.027 |
ww | +0.027 |
Neg logit contributions | |
ishes | -0.039 |
anks | -0.039 |
ware | -0.039 |
unes | -0.038 |
fault | -0.037 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ha | +0.051 |
Little | +0.046 |
www | +0.044 |
ww | +0.043 |
few | +0.043 |
Neg logit contributions | |
ishes | -0.052 |
ware | -0.052 |
anks | -0.052 |
unes | -0.052 |
fault | -0.050 |
Token | in |
Token ID | 287 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ishes | +0.027 |
ware | +0.026 |
anks | +0.026 |
unes | +0.026 |
fault | +0.026 |
Neg logit contributions | |
ha | -0.022 |
Little | -0.019 |
www | -0.018 |
ww | -0.018 |
Time | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
ware | +0.051 |
ishes | +0.050 |
fault | +0.049 |
anks | +0.049 |
unes | +0.049 |
Neg logit contributions | |
ha | -0.030 |
www | -0.026 |
ww | -0.026 |
Little | -0.025 |
uren | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ware | +0.008 |
ishes | +0.008 |
unes | +0.008 |
anks | +0.008 |
fault | +0.008 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.003 |
www | -0.003 |
ww | -0.003 |
Time | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ha | +0.018 |
www | +0.015 |
Little | +0.015 |
Alice | +0.015 |
uren | +0.015 |
Neg logit contributions | |
ware | -0.021 |
fault | -0.019 |
ishes | -0.019 |
endant | -0.019 |
rier | -0.019 |
Token | group |
Token ID | 1448 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ha | +0.020 |
T | +0.018 |
Little | +0.018 |
While | +0.017 |
Time | +0.017 |
Neg logit contributions | |
ware | -0.019 |
ishes | -0.018 |
unes | -0.018 |
fault | -0.018 |
melon | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | +9.71e-04 |
Pos logit contributions | |
ha | +0.022 |
Little | +0.019 |
www | +0.019 |
ww | +0.018 |
T | +0.018 |
Neg logit contributions | |
ware | -0.024 |
unes | -0.023 |
anks | -0.023 |
ishes | -0.023 |
aces | -0.022 |
Token | re |
Token ID | 302 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ishes | +0.002 |
ware | +0.002 |
unes | +0.002 |
anks | +0.002 |
fault | +0.002 |
Neg logit contributions | |
ha | -0.002 |
Little | -0.002 |
www | -0.002 |
ww | -0.002 |
uren | -0.001 |
Token | ind |
Token ID | 521 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
ha | +0.060 |
Little | +0.053 |
www | +0.051 |
Time | +0.051 |
ww | +0.050 |
Neg logit contributions | |
ishes | -0.069 |
ware | -0.067 |
anks | -0.067 |
unes | -0.066 |
fault | -0.065 |
Token | eer |
Token ID | 28153 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
ha | +0.219 |
Little | +0.200 |
www | +0.196 |
ww | +0.194 |
few | +0.193 |
Neg logit contributions | |
ishes | -0.092 |
anks | -0.092 |
ware | -0.092 |
unes | -0.090 |
fault | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
ha | +0.036 |
Little | +0.032 |
www | +0.031 |
ww | +0.031 |
unt | +0.031 |
Neg logit contributions | |
ishes | -0.044 |
anks | -0.043 |
ware | -0.043 |
unes | -0.043 |
fault | -0.041 |
Token | It |
Token ID | 632 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.005 |
www | +0.004 |
ww | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.006 |
ware | -0.006 |
unes | -0.006 |
anks | -0.006 |
fault | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
ware | +0.024 |
ishes | +0.023 |
unes | +0.022 |
anks | +0.022 |
fault | +0.022 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.016 |
www | -0.016 |
ww | -0.016 |
Time | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ishes | +0.005 |
ware | +0.005 |
anks | +0.005 |
unes | +0.005 |
fault | +0.005 |
Neg logit contributions | |
ha | -0.003 |
Little | -0.002 |
www | -0.002 |
ww | -0.002 |
Time | -0.002 |
Token | eer |
Token ID | 28153 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
ha | +0.226 |
Little | +0.207 |
www | +0.202 |
few | +0.200 |
ww | +0.200 |
Neg logit contributions | |
anks | -0.103 |
ishes | -0.103 |
unes | -0.102 |
ware | -0.102 |
fault | -0.098 |
Token | away |
Token ID | 1497 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ha | +0.028 |
Little | +0.025 |
www | +0.024 |
ww | +0.023 |
Time | +0.023 |
Neg logit contributions | |
ishes | -0.038 |
ware | -0.037 |
anks | -0.037 |
unes | -0.037 |
fault | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ha | +0.037 |
Little | +0.032 |
www | +0.031 |
ww | +0.030 |
Time | +0.030 |
Neg logit contributions | |
ishes | -0.045 |
ware | -0.045 |
anks | -0.045 |
unes | -0.044 |
fault | -0.044 |
Token | The |
Token ID | 383 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
unes | +0.022 |
ishes | +0.022 |
anks | +0.022 |
ware | +0.022 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.017 |
www | -0.016 |
ww | -0.016 |
few | -0.016 |
Token | re |
Token ID | 302 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
ware | +0.035 |
ishes | +0.035 |
unes | +0.034 |
anks | +0.033 |
fault | +0.033 |
Neg logit contributions | |
ha | -0.027 |
Little | -0.023 |
www | -0.022 |
ww | -0.022 |
Time | -0.022 |
Token | ind |
Token ID | 521 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
ha | +0.042 |
Little | +0.036 |
www | +0.035 |
few | +0.034 |
unt | +0.034 |
Neg logit contributions | |
unes | -0.066 |
anks | -0.066 |
ware | -0.065 |
ishes | -0.064 |
fault | -0.064 |
Token | eer |
Token ID | 28153 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ha | +0.213 |
Little | +0.194 |
www | +0.189 |
few | +0.188 |
ww | +0.188 |
Neg logit contributions | |
anks | -0.098 |
unes | -0.096 |
ishes | -0.096 |
ware | -0.095 |
fault | -0.092 |
Token | said |
Token ID | 531 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
ha | +0.025 |
Little | +0.021 |
www | +0.020 |
few | +0.020 |
ww | +0.020 |
Neg logit contributions | |
anks | -0.039 |
unes | -0.039 |
ishes | -0.039 |
ware | -0.039 |
fault | -0.038 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
www | +0.006 |
Time | +0.006 |
ww | +0.006 |
Neg logit contributions | |
ware | -0.012 |
unes | -0.012 |
ishes | -0.012 |
anks | -0.012 |
fault | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
ha | +0.016 |
Little | +0.014 |
www | +0.013 |
Time | +0.013 |
ww | +0.013 |
Neg logit contributions | |
ishes | -0.022 |
anks | -0.022 |
ware | -0.022 |
unes | -0.021 |
fault | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
ishes | +0.004 |
anks | +0.004 |
ware | +0.004 |
unes | +0.004 |
fault | +0.003 |
Neg logit contributions | |
ha | -0.003 |
Little | -0.002 |
www | -0.002 |
ww | -0.002 |
Time | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
ha | +0.019 |
Little | +0.016 |
www | +0.016 |
ww | +0.016 |
unt | +0.015 |
Neg logit contributions | |
ishes | -0.027 |
ware | -0.027 |
unes | -0.026 |
fault | -0.026 |
anks | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +9.79e-04 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
www | +0.002 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
ishes | -0.003 |
ware | -0.003 |
anks | -0.003 |
unes | -0.003 |
fault | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ishes | +0.002 |
ware | +0.002 |
unes | +0.002 |
fault | +0.002 |
anks | +0.002 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.001 |
unt | -0.001 |
ww | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.96e-03 |
Pos logit contributions | |
ha | +0.019 |
Time | +0.015 |
www | +0.015 |
Alice | +0.015 |
Little | +0.014 |
Neg logit contributions | |
ware | -0.032 |
ishes | -0.031 |
rier | -0.030 |
kins | -0.030 |
melon | -0.029 |
Token | re |
Token ID | 302 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ware | +0.006 |
ishes | +0.006 |
melon | +0.006 |
unes | +0.005 |
ectar | +0.005 |
Neg logit contributions | |
ha | -0.005 |
Little | -0.004 |
Alice | -0.004 |
Time | -0.004 |
www | -0.004 |
Token | ind |
Token ID | 521 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
ha | +0.057 |
Little | +0.050 |
Time | +0.048 |
www | +0.048 |
ww | +0.047 |
Neg logit contributions | |
ishes | -0.067 |
ware | -0.066 |
anks | -0.066 |
unes | -0.065 |
fault | -0.064 |
Token | eer |
Token ID | 28153 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ha | +0.226 |
Little | +0.209 |
www | +0.203 |
Time | +0.202 |
ww | +0.201 |
Neg logit contributions | |
ishes | -0.086 |
ware | -0.085 |
anks | -0.084 |
unes | -0.083 |
fault | -0.079 |
Token | named |
Token ID | 3706 |
Feature activation | -5.87e-03 |
Pos logit contributions | |
ha | +0.037 |
Little | +0.033 |
www | +0.032 |
Time | +0.031 |
ww | +0.031 |
Neg logit contributions | |
ishes | -0.043 |
ware | -0.043 |
anks | -0.043 |
unes | -0.042 |
fault | -0.041 |
Token | Rudolph |
Token ID | 48684 |
Feature activation | +5.41e-04 |
Pos logit contributions | |
ha | +0.011 |
Time | +0.011 |
Little | +0.010 |
www | +0.010 |
Sarah | +0.010 |
Neg logit contributions | |
unes | -0.010 |
ishes | -0.010 |
ware | -0.010 |
anks | -0.009 |
ocular | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
ishes | +0.001 |
anks | +0.001 |
ware | +0.001 |
unes | +0.001 |
fault | +0.001 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.001 |
Time | -0.001 |
ww | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
ha | +0.003 |
Little | +0.002 |
www | +0.002 |
Sarah | +0.002 |
Time | +0.002 |
Neg logit contributions | |
ware | -0.002 |
ishes | -0.002 |
anks | -0.002 |
unes | -0.002 |
ests | -0.002 |
Token | began |
Token ID | 2540 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
ishes | +0.034 |
ware | +0.033 |
anks | +0.033 |
unes | +0.033 |
fault | +0.032 |
Neg logit contributions | |
ha | -0.024 |
Little | -0.021 |
www | -0.020 |
few | -0.020 |
ww | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
ha | +0.036 |
Little | +0.031 |
few | +0.030 |
www | +0.030 |
Time | +0.029 |
Neg logit contributions | |
ishes | -0.052 |
ware | -0.051 |
anks | -0.051 |
unes | -0.051 |
fault | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
unes | +0.019 |
ware | +0.019 |
anks | +0.019 |
ishes | +0.019 |
fault | +0.018 |
Neg logit contributions | |
ha | -0.016 |
Little | -0.013 |
www | -0.013 |
ww | -0.013 |
Time | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-04 |
Pos logit contributions | |
ware | +0.005 |
anks | +0.005 |
unes | +0.005 |
ests | +0.005 |
fault | +0.004 |
Neg logit contributions | |
ha | -0.004 |
ww | -0.004 |
www | -0.004 |
uren | -0.003 |
Little | -0.003 |
Token | C |
Token ID | 34 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ha | +0.000 |
ww | +0.000 |
www | +0.000 |
Kelly | +0.000 |
unt | +0.000 |
Neg logit contributions | |
ests | -0.000 |
ware | -0.000 |
neys | -0.000 |
ases | -0.000 |
auc | -0.000 |
Token | ind |
Token ID | 521 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
ha | +0.038 |
Little | +0.034 |
www | +0.033 |
few | +0.033 |
ww | +0.032 |
Neg logit contributions | |
ishes | -0.036 |
ware | -0.035 |
anks | -0.035 |
unes | -0.035 |
fault | -0.034 |
Token | y |
Token ID | 88 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ha | +0.146 |
Little | +0.131 |
www | +0.126 |
Time | +0.124 |
ww | +0.124 |
Neg logit contributions | |
ishes | -0.165 |
ware | -0.163 |
anks | -0.161 |
unes | -0.161 |
fault | -0.157 |
Token | tried |
Token ID | 3088 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
ha | +0.041 |
Little | +0.036 |
Time | +0.036 |
ww | +0.035 |
www | +0.035 |
Neg logit contributions | |
ware | -0.050 |
ishes | -0.050 |
anks | -0.049 |
unes | -0.047 |
fault | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
ha | +0.013 |
Little | +0.011 |
www | +0.011 |
ww | +0.011 |
unt | +0.010 |
Neg logit contributions | |
fault | -0.014 |
anks | -0.014 |
ware | -0.014 |
ishes | -0.014 |
unes | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ha | +0.009 |
ww | +0.008 |
www | +0.008 |
Little | +0.008 |
unt | +0.008 |
Neg logit contributions | |
anks | -0.010 |
ware | -0.010 |
ishes | -0.010 |
fault | -0.010 |
unes | -0.010 |
Token | Peter |
Token ID | 5613 |
Feature activation | -4.98e-03 |
Pos logit contributions | |
anks | +0.026 |
ishes | +0.026 |
fault | +0.026 |
ware | +0.026 |
unes | +0.026 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.015 |
www | -0.014 |
ww | -0.014 |
Time | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
ha | +0.025 |
Little | +0.022 |
few | +0.022 |
www | +0.021 |
Time | +0.021 |
Neg logit contributions | |
anks | -0.029 |
ware | -0.029 |
ishes | -0.029 |
unes | -0.029 |
fault | -0.029 |
Token | someone |
Token ID | 2130 |
Feature activation | +4.76e-03 |
Pos logit contributions | |
ishes | +0.018 |
ware | +0.018 |
anks | +0.018 |
unes | +0.018 |
fault | +0.018 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.012 |
www | -0.012 |
ww | -0.012 |
unt | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
anks | +0.012 |
ware | +0.012 |
unes | +0.012 |
ishes | +0.011 |
rier | +0.011 |
Neg logit contributions | |
ha | -0.006 |
few | -0.005 |
Little | -0.005 |
www | -0.005 |
unt | -0.005 |
Token | add |
Token ID | 751 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
ishes | +0.015 |
ware | +0.015 |
unes | +0.015 |
anks | +0.014 |
fault | +0.014 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.009 |
few | -0.008 |
www | -0.008 |
Time | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ware | +0.090 |
anks | +0.090 |
ishes | +0.087 |
unes | +0.087 |
ses | +0.085 |
Neg logit contributions | |
ha | -0.045 |
few | -0.040 |
long | -0.036 |
time | -0.035 |
Little | -0.033 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
ishes | +0.030 |
ware | +0.030 |
anks | +0.029 |
unes | +0.029 |
fault | +0.029 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.015 |
few | -0.014 |
Time | -0.014 |
unt | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
ishes | +0.152 |
ware | +0.148 |
unes | +0.143 |
anks | +0.141 |
fault | +0.141 |
Neg logit contributions | |
ha | -0.116 |
www | -0.102 |
Little | -0.100 |
ww | -0.100 |
unt | -0.098 |
Token | looked |
Token ID | 3114 |
Feature activation | +4.99e-04 |
Pos logit contributions | |
ishes | +0.020 |
anks | +0.020 |
unes | +0.020 |
ware | +0.020 |
fault | +0.020 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.010 |
www | -0.009 |
ww | -0.009 |
few | -0.009 |
Token | there |
Token ID | 612 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
ishes | +0.001 |
ware | +0.001 |
anks | +0.001 |
unes | +0.001 |
fault | +0.001 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.000 |
ww | -0.000 |
few | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
anks | +0.020 |
ishes | +0.019 |
unes | +0.019 |
ware | +0.019 |
fault | +0.019 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.010 |
few | -0.010 |
Time | -0.010 |
Kelly | -0.009 |
Token | no |
Token ID | 645 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
anks | +0.010 |
ishes | +0.010 |
unes | +0.010 |
ware | +0.010 |
fault | +0.010 |
Neg logit contributions | |
ha | -0.007 |
few | -0.006 |
Little | -0.006 |
Time | -0.006 |
www | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
ishes | +0.010 |
ware | +0.010 |
anks | +0.009 |
unes | +0.009 |
fault | +0.009 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
ww | -0.005 |
Time | -0.005 |
Token | overwhelmed |
Token ID | 20974 |
Feature activation | +5.50e-04 |
Pos logit contributions | |
fault | +0.012 |
anks | +0.012 |
ishes | +0.012 |
unes | +0.012 |
ware | +0.011 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.013 |
ww | -0.012 |
www | -0.012 |
T | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ishes | +0.001 |
ware | +0.001 |
anks | +0.001 |
unes | +0.001 |
fault | +0.001 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.001 |
ww | -0.001 |
Time | -0.001 |
Token | joy |
Token ID | 8716 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
ishes | +0.048 |
anks | +0.048 |
ware | +0.048 |
unes | +0.047 |
fault | +0.046 |
Neg logit contributions | |
ha | -0.030 |
Little | -0.025 |
www | -0.024 |
few | -0.024 |
Time | -0.023 |
Token | ! |
Token ID | 0 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
ha | +0.014 |
Little | +0.012 |
www | +0.012 |
ww | +0.011 |
Time | +0.011 |
Neg logit contributions | |
ishes | -0.015 |
ware | -0.015 |
anks | -0.015 |
unes | -0.015 |
fault | -0.015 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
unes | +0.017 |
anks | +0.017 |
ishes | +0.017 |
ware | +0.016 |
fault | +0.016 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.012 |
www | -0.012 |
ww | -0.012 |
Time | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
ishes | +0.147 |
ware | +0.143 |
unes | +0.136 |
els | +0.134 |
aces | +0.133 |
Neg logit contributions | |
ha | -0.102 |
ww | -0.091 |
www | -0.091 |
Time | -0.090 |
Little | -0.089 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
ww | +0.004 |
www | +0.004 |
unt | +0.004 |
Neg logit contributions | |
ware | -0.007 |
ishes | -0.007 |
unes | -0.007 |
anks | -0.007 |
els | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -8.36e-03 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.010 |
ware | -0.010 |
unes | -0.010 |
anks | -0.010 |
fault | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | -3.28e-03 |
Pos logit contributions | |
ha | +0.012 |
www | +0.010 |
ww | +0.009 |
Little | +0.009 |
unt | +0.009 |
Neg logit contributions | |
ishes | -0.020 |
ware | -0.020 |
unes | -0.020 |
anks | -0.019 |
fault | -0.019 |
Token | could |
Token ID | 714 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.008 |
ware | -0.008 |
anks | -0.008 |
unes | -0.008 |
fault | -0.008 |
Token | ribbon |
Token ID | 29092 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
few | +0.004 |
ww | +0.004 |
Neg logit contributions | |
ishes | -0.006 |
anks | -0.006 |
ware | -0.006 |
unes | -0.006 |
fault | -0.006 |
Token | trailing |
Token ID | 25462 |
Feature activation | -9.39e-03 |
Pos logit contributions | |
ha | +0.025 |
Little | +0.022 |
www | +0.021 |
Time | +0.020 |
ww | +0.020 |
Neg logit contributions | |
ware | -0.036 |
ishes | -0.036 |
anks | -0.036 |
unes | -0.036 |
fault | -0.035 |
Token | behind |
Token ID | 2157 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
ha | +0.018 |
Little | +0.016 |
www | +0.015 |
ww | +0.015 |
Time | +0.015 |
Neg logit contributions | |
ware | -0.018 |
ishes | -0.018 |
anks | -0.018 |
unes | -0.017 |
fault | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -8.44e-04 |
Pos logit contributions | |
ha | +0.009 |
www | +0.008 |
ww | +0.008 |
Little | +0.008 |
unt | +0.007 |
Neg logit contributions | |
ware | -0.013 |
unes | -0.013 |
anks | -0.012 |
ishes | -0.012 |
aces | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
few | +0.001 |
www | +0.001 |
uren | +0.001 |
Neg logit contributions | |
ishes | -0.002 |
ware | -0.002 |
unes | -0.002 |
anks | -0.002 |
fault | -0.002 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
anks | +0.012 |
unes | +0.012 |
fault | +0.011 |
ware | +0.011 |
aces | +0.011 |
Neg logit contributions | |
ha | -0.012 |
ww | -0.011 |
www | -0.010 |
Little | -0.010 |
Time | -0.009 |
Token | she |
Token ID | 673 |
Feature activation | -1.28e-03 |
Pos logit contributions | |
ishes | +0.131 |
ware | +0.126 |
fault | +0.126 |
els | +0.125 |
depending | +0.124 |
Neg logit contributions | |
ha | -0.103 |
ww | -0.098 |
www | -0.097 |
T | -0.092 |
While | -0.092 |
Token | went |
Token ID | 1816 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ha | +0.002 |
ww | +0.002 |
unt | +0.002 |
www | +0.002 |
Little | +0.002 |
Neg logit contributions | |
ware | -0.003 |
ishes | -0.003 |
aces | -0.002 |
unes | -0.002 |
els | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
unes | +0.026 |
ware | +0.025 |
anks | +0.025 |
aces | +0.024 |
els | +0.024 |
Neg logit contributions | |
ha | -0.021 |
ww | -0.020 |
www | -0.020 |
Little | -0.019 |
T | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
ha | +0.010 |
www | +0.009 |
ww | +0.009 |
unt | +0.008 |
Little | +0.008 |
Neg logit contributions | |
ishes | -0.015 |
unes | -0.015 |
anks | -0.015 |
ware | -0.015 |
fault | -0.015 |
Token | ribbon |
Token ID | 29092 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ha | +0.007 |
Little | +0.006 |
www | +0.006 |
ww | +0.006 |
unt | +0.006 |
Neg logit contributions | |
ware | -0.008 |
ishes | -0.007 |
fault | -0.007 |
aces | -0.007 |
unes | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
ha | +0.039 |
Little | +0.033 |
www | +0.032 |
ww | +0.031 |
Time | +0.031 |
Neg logit contributions | |
ishes | -0.057 |
ware | -0.056 |
anks | -0.056 |
unes | -0.056 |
fault | -0.055 |
Token | took |
Token ID | 1718 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
ishes | +0.006 |
anks | +0.006 |
ware | +0.006 |
aces | +0.005 |
fault | +0.005 |
Neg logit contributions | |
ha | -0.005 |
Time | -0.004 |
Little | -0.004 |
unt | -0.004 |
ww | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
anks | +0.003 |
aces | +0.003 |
ware | +0.003 |
els | +0.003 |
fault | +0.003 |
Neg logit contributions | |
unt | -0.002 |
ww | -0.002 |
Little | -0.002 |
www | -0.002 |
Time | -0.002 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
anks | +0.009 |
unes | +0.009 |
fault | +0.009 |
ishes | +0.009 |
ware | +0.009 |
Neg logit contributions | |
ha | -0.009 |
Little | -0.008 |
www | -0.008 |
Time | -0.007 |
ww | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +7.76e-03 |
Pos logit contributions | |
anks | +0.042 |
ware | +0.042 |
unes | +0.041 |
rier | +0.040 |
fault | +0.040 |
Neg logit contributions | |
ha | -0.041 |
ww | -0.036 |
Time | -0.035 |
www | -0.035 |
Little | -0.035 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
anks | +0.016 |
unes | +0.016 |
ishes | +0.016 |
ware | +0.015 |
fault | +0.015 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.012 |
www | -0.011 |
ww | -0.011 |
Time | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
ishes | +0.150 |
ware | +0.145 |
unes | +0.138 |
fault | +0.137 |
els | +0.134 |
Neg logit contributions | |
ha | -0.103 |
Time | -0.091 |
ww | -0.091 |
www | -0.090 |
While | -0.090 |
Token | little |
Token ID | 1310 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
Time | +0.005 |
ww | +0.005 |
T | +0.005 |
Neg logit contributions | |
ware | -0.010 |
ishes | -0.009 |
rier | -0.009 |
unes | -0.009 |
kins | -0.009 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ha | +0.017 |
Little | +0.014 |
www | +0.014 |
ww | +0.013 |
Time | +0.013 |
Neg logit contributions | |
ishes | -0.028 |
ware | -0.028 |
unes | -0.027 |
anks | -0.027 |
fault | -0.026 |
Token | went |
Token ID | 1816 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ha | +0.018 |
Little | +0.016 |
www | +0.015 |
ww | +0.015 |
Time | +0.015 |
Neg logit contributions | |
ishes | -0.028 |
ware | -0.028 |
anks | -0.027 |
unes | -0.027 |
fault | -0.027 |
Token | she |
Token ID | 673 |
Feature activation | -3.45e-04 |
Pos logit contributions | |
anks | +0.028 |
unes | +0.027 |
ware | +0.027 |
ishes | +0.026 |
aces | +0.026 |
Neg logit contributions | |
ha | -0.020 |
Little | -0.018 |
ww | -0.018 |
T | -0.018 |
www | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
ishes | +0.031 |
anks | +0.030 |
ware | +0.030 |
unes | +0.030 |
fault | +0.030 |
Neg logit contributions | |
ha | -0.021 |
Little | -0.019 |
www | -0.019 |
ww | -0.018 |
Time | -0.018 |
Token | became |
Token ID | 2627 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ha | +0.008 |
www | +0.007 |
Little | +0.007 |
ww | +0.007 |
unt | +0.007 |
Neg logit contributions | |
ishes | -0.011 |
ware | -0.010 |
unes | -0.010 |
anks | -0.010 |
fault | -0.010 |
Token | best |
Token ID | 1266 |
Feature activation | +6.62e-04 |
Pos logit contributions | |
ishes | +0.028 |
anks | +0.028 |
ware | +0.028 |
unes | +0.028 |
fault | +0.027 |
Neg logit contributions | |
ha | -0.023 |
Little | -0.020 |
www | -0.019 |
ww | -0.019 |
Time | -0.018 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.95e-03 |
Pos logit contributions | |
ishes | +0.001 |
anks | +0.001 |
unes | +0.001 |
fault | +0.001 |
ware | +0.001 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.001 |
ww | -0.001 |
Time | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
ha | +0.005 |
Little | +0.004 |
www | +0.004 |
ww | +0.004 |
Time | +0.004 |
Neg logit contributions | |
ishes | -0.006 |
anks | -0.006 |
ware | -0.006 |
unes | -0.006 |
fault | -0.006 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
ware | +0.010 |
ishes | +0.010 |
unes | +0.010 |
anks | +0.010 |
fault | +0.009 |
Neg logit contributions | |
ha | -0.009 |
Little | -0.008 |
few | -0.008 |
unt | -0.008 |
Time | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
ishes | +0.142 |
ware | +0.135 |
anks | +0.132 |
unes | +0.130 |
fault | +0.126 |
Neg logit contributions | |
ha | -0.117 |
Little | -0.105 |
www | -0.104 |
Time | -0.101 |
Alice | -0.101 |
Token | driver |
Token ID | 4639 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
ha | +0.009 |
www | +0.008 |
ww | +0.008 |
Little | +0.008 |
T | +0.008 |
Neg logit contributions | |
ishes | -0.011 |
ware | -0.010 |
anks | -0.010 |
unes | -0.010 |
fault | -0.010 |
Token | went |
Token ID | 1816 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
www | +0.001 |
few | +0.001 |
unt | +0.001 |
Neg logit contributions | |
anks | -0.003 |
unes | -0.003 |
fault | -0.003 |
ware | -0.003 |
ishes | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
anks | +0.027 |
ishes | +0.026 |
unes | +0.026 |
ware | +0.026 |
fault | +0.024 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.017 |
www | -0.016 |
ww | -0.016 |
T | -0.016 |
Token | Sack |
Token ID | 49175 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ha | +0.006 |
Little | +0.005 |
www | +0.005 |
ww | +0.005 |
unt | +0.005 |
Neg logit contributions | |
ishes | -0.009 |
ware | -0.009 |
anks | -0.009 |
unes | -0.009 |
fault | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ware | +0.000 |
anks | +0.000 |
unes | +0.000 |
ishes | +0.000 |
aces | +0.000 |
Neg logit contributions | |
ha | -0.000 |
Little | -0.000 |
few | -0.000 |
Time | -0.000 |
www | -0.000 |
Token | Hur |
Token ID | 10077 |
Feature activation | -6.20e-03 |
Pos logit contributions | |
ishes | +0.053 |
anks | +0.052 |
ware | +0.052 |
unes | +0.052 |
fault | +0.051 |
Neg logit contributions | |
ha | -0.040 |
Little | -0.035 |
www | -0.033 |
ww | -0.033 |
few | -0.033 |
Token | ry |
Token ID | 563 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
ha | +0.013 |
Little | +0.011 |
www | +0.011 |
ww | +0.011 |
Time | +0.011 |
Neg logit contributions | |
ishes | -0.011 |
anks | -0.011 |
unes | -0.011 |
ware | -0.011 |
fault | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ishes | +0.051 |
ware | +0.051 |
anks | +0.051 |
unes | +0.051 |
fault | +0.049 |
Neg logit contributions | |
ha | -0.045 |
Little | -0.040 |
www | -0.038 |
ww | -0.038 |
Time | -0.037 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.70e-03 |
Pos logit contributions | |
ha | +0.022 |
Little | +0.019 |
www | +0.019 |
ww | +0.018 |
Time | +0.018 |
Neg logit contributions | |
ishes | -0.030 |
ware | -0.029 |
anks | -0.029 |
unes | -0.029 |
fault | -0.029 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ishes | +0.010 |
anks | +0.010 |
unes | +0.010 |
ware | +0.010 |
fault | +0.010 |
Neg logit contributions | |
ha | -0.007 |
Little | -0.006 |
www | -0.006 |
ww | -0.006 |
Time | -0.006 |
Token | shouted |
Token ID | 17293 |
Feature activation | -3.78e-04 |
Pos logit contributions | |
ishes | +0.032 |
anks | +0.032 |
ware | +0.031 |
unes | +0.031 |
fault | +0.031 |
Neg logit contributions | |
ha | -0.024 |
Little | -0.020 |
www | -0.020 |
ww | -0.020 |
Time | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
www | +0.001 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
anks | -0.001 |
ware | -0.001 |
unes | -0.001 |
fault | -0.001 |
ishes | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ishes | +0.035 |
ware | +0.035 |
anks | +0.034 |
unes | +0.034 |
fault | +0.034 |
Neg logit contributions | |
ha | -0.022 |
Little | -0.019 |
www | -0.018 |
ww | -0.018 |
Time | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
ware | +0.030 |
ishes | +0.029 |
anks | +0.029 |
unes | +0.028 |
fault | +0.028 |
Neg logit contributions | |
ha | -0.021 |
Little | -0.020 |
ww | -0.019 |
www | -0.019 |
Time | -0.018 |
Token | almost |
Token ID | 2048 |
Feature activation | +2.93e-03 |
Pos logit contributions | |
fault | +0.011 |
anks | +0.011 |
unes | +0.011 |
ishes | +0.011 |
ware | +0.011 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.011 |
ww | -0.011 |
www | -0.011 |
unt | -0.010 |
Token | find |
Token ID | 1064 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ware | +0.022 |
anks | +0.022 |
unes | +0.022 |
ishes | +0.021 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.015 |
few | -0.014 |
www | -0.014 |
rush | -0.014 |
Token | some |
Token ID | 617 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
anks | +0.040 |
ware | +0.040 |
unes | +0.039 |
ishes | +0.039 |
fault | +0.038 |
Neg logit contributions | |
ha | -0.022 |
Little | -0.018 |
few | -0.017 |
www | -0.017 |
ww | -0.017 |
Token | cheap |
Token ID | 7026 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
anks | +0.035 |
unes | +0.034 |
ware | +0.034 |
ishes | +0.034 |
fault | +0.033 |
Neg logit contributions | |
ha | -0.020 |
few | -0.017 |
Little | -0.017 |
ww | -0.016 |
Time | -0.016 |
Token | steam |
Token ID | 13324 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
anks | +0.012 |
unes | +0.011 |
ware | +0.011 |
ishes | +0.011 |
fault | +0.011 |
Neg logit contributions | |
ha | -0.009 |
few | -0.008 |
Little | -0.007 |
ww | -0.007 |
www | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +8.08e-03 |
Pos logit contributions | |
ha | +0.018 |
Little | +0.014 |
www | +0.014 |
few | +0.014 |
ww | +0.014 |
Neg logit contributions | |
ishes | -0.026 |
ware | -0.026 |
anks | -0.026 |
unes | -0.025 |
fault | -0.025 |
Token | His |
Token ID | 2399 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ishes | +0.017 |
ware | +0.017 |
anks | +0.016 |
unes | +0.016 |
fault | +0.016 |
Neg logit contributions | |
ha | -0.013 |
Little | -0.012 |
few | -0.011 |
unt | -0.011 |
uren | -0.011 |
Token | friends |
Token ID | 2460 |
Feature activation | +5.73e-03 |
Pos logit contributions | |
ware | +0.040 |
unes | +0.040 |
ishes | +0.040 |
anks | +0.040 |
fault | +0.038 |
Neg logit contributions | |
ha | -0.037 |
Little | -0.033 |
few | -0.032 |
www | -0.032 |
ww | -0.031 |
Token | got |
Token ID | 1392 |
Feature activation | +1.83e-03 |
Pos logit contributions | |
ishes | +0.011 |
ware | +0.011 |
anks | +0.011 |
unes | +0.011 |
fault | +0.010 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.009 |
www | -0.009 |
ww | -0.009 |
Time | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ware | +0.005 |
anks | +0.005 |
unes | +0.005 |
ishes | +0.005 |
ests | +0.005 |
Neg logit contributions | |
ha | -0.002 |
few | -0.002 |
Time | -0.002 |
Little | -0.002 |
long | -0.002 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
ware | +0.039 |
unes | +0.039 |
anks | +0.039 |
ishes | +0.037 |
ests | +0.037 |
Neg logit contributions | |
ha | -0.014 |
few | -0.013 |
Little | -0.012 |
ww | -0.012 |
www | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
ishes | +0.007 |
ware | +0.006 |
anks | +0.006 |
unes | +0.006 |
fault | +0.006 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.003 |
www | -0.003 |
few | -0.003 |
Time | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
ishes | +0.013 |
ware | +0.013 |
anks | +0.013 |
unes | +0.013 |
fault | +0.012 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.007 |
www | -0.006 |
ww | -0.006 |
Time | -0.006 |
Token | herself |
Token ID | 5223 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
ware | +0.059 |
anks | +0.059 |
els | +0.058 |
fault | +0.058 |
ishes | +0.058 |
Neg logit contributions | |
ha | -0.051 |
ww | -0.043 |
www | -0.042 |
unt | -0.042 |
Little | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
ishes | +0.019 |
ware | +0.019 |
anks | +0.019 |
unes | +0.019 |
fault | +0.018 |
Neg logit contributions | |
ha | -0.014 |
Little | -0.012 |
www | -0.011 |
ww | -0.011 |
Time | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
ha | +0.005 |
ww | +0.004 |
www | +0.004 |
Little | +0.004 |
unt | +0.004 |
Neg logit contributions | |
ware | -0.006 |
fault | -0.006 |
ishes | -0.006 |
anks | -0.006 |
unes | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
ishes | +0.011 |
ware | +0.011 |
anks | +0.011 |
unes | +0.011 |
fault | +0.011 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.007 |
ww | -0.007 |
www | -0.007 |
unt | -0.007 |
Token | showed |
Token ID | 3751 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
ware | +0.010 |
ishes | +0.010 |
anks | +0.010 |
fault | +0.009 |
unes | +0.009 |
Neg logit contributions | |
ha | -0.008 |
www | -0.007 |
ww | -0.007 |
Little | -0.007 |
unt | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ishes | +0.115 |
anks | +0.115 |
ware | +0.113 |
unes | +0.113 |
fault | +0.112 |
Neg logit contributions | |
ha | -0.068 |
Little | -0.058 |
www | -0.056 |
ww | -0.056 |
Time | -0.055 |
Token | her |
Token ID | 607 |
Feature activation | +1.54e-03 |
Pos logit contributions | |
ware | +0.067 |
fault | +0.067 |
anks | +0.066 |
ishes | +0.065 |
els | +0.064 |
Neg logit contributions | |
ha | -0.052 |
www | -0.044 |
ww | -0.043 |
Little | -0.042 |
unt | -0.041 |
Token | painting |
Token ID | 12036 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
unes | +0.003 |
ishes | +0.003 |
ware | +0.003 |
anks | +0.003 |
fault | +0.003 |
Neg logit contributions | |
ha | -0.002 |
Little | -0.002 |
few | -0.002 |
www | -0.002 |
ww | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ishes | +0.029 |
unes | +0.028 |
ware | +0.028 |
anks | +0.028 |
fault | +0.028 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.017 |
few | -0.016 |
www | -0.016 |
unt | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
anks | +0.022 |
ishes | +0.022 |
unes | +0.022 |
ware | +0.022 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.018 |
Little | -0.015 |
www | -0.015 |
ww | -0.015 |
Time | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | -7.43e-04 |
Pos logit contributions | |
ishes | +0.012 |
anks | +0.012 |
ware | +0.012 |
unes | +0.012 |
fault | +0.012 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.008 |
www | -0.008 |
ww | -0.008 |
Time | -0.008 |
Token | smiled |
Token ID | 13541 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
www | +0.001 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
ishes | -0.002 |
ware | -0.002 |
anks | -0.002 |
fault | -0.001 |
unes | -0.001 |
Token | right |
Token ID | 826 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
ishes | +0.016 |
anks | +0.016 |
ware | +0.016 |
unes | +0.016 |
fault | +0.016 |
Neg logit contributions | |
ha | -0.013 |
Little | -0.011 |
www | -0.011 |
ww | -0.011 |
Time | -0.011 |
Token | back |
Token ID | 736 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ishes | +0.005 |
ware | +0.005 |
anks | +0.005 |
unes | +0.005 |
fault | +0.005 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.004 |
www | -0.004 |
ww | -0.004 |
Time | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
anks | +0.047 |
ishes | +0.046 |
fault | +0.045 |
unes | +0.045 |
ware | +0.045 |
Neg logit contributions | |
ha | -0.047 |
Little | -0.041 |
www | -0.040 |
ww | -0.040 |
Time | -0.039 |
Token | From |
Token ID | 3574 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ishes | +0.032 |
anks | +0.032 |
unes | +0.032 |
ware | +0.032 |
fault | +0.031 |
Neg logit contributions | |
ha | -0.023 |
Little | -0.019 |
www | -0.019 |
ww | -0.019 |
few | -0.018 |
Token | then |
Token ID | 788 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
ishes | +0.044 |
ocular | +0.042 |
els | +0.042 |
ware | +0.041 |
anks | +0.041 |
Neg logit contributions | |
ha | -0.046 |
Time | -0.039 |
few | -0.038 |
www | -0.038 |
T | -0.038 |
Token | on |
Token ID | 319 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
anks | +0.015 |
aces | +0.014 |
unes | +0.014 |
els | +0.014 |
ishes | +0.014 |
Neg logit contributions | |
ha | -0.017 |
Little | -0.015 |
uren | -0.015 |
Charlie | -0.015 |
Sarah | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +8.78e-04 |
Pos logit contributions | |
ha | +0.017 |
Time | +0.014 |
Little | +0.014 |
www | +0.014 |
T | +0.014 |
Neg logit contributions | |
ware | -0.025 |
ishes | -0.025 |
unes | -0.024 |
fault | -0.024 |
anks | -0.024 |
Token | Hannah |
Token ID | 26013 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ishes | +0.002 |
ware | +0.002 |
unes | +0.002 |
anks | +0.002 |
fault | +0.002 |
Neg logit contributions | |
ha | -0.001 |
www | -0.001 |
ww | -0.001 |
Little | -0.001 |
Time | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
ha | +0.023 |
www | +0.021 |
ww | +0.021 |
Time | +0.020 |
Little | +0.020 |
Neg logit contributions | |
ishes | -0.026 |
anks | -0.025 |
ware | -0.025 |
fault | -0.024 |
aces | -0.024 |
Token | go |
Token ID | 467 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
anks | +0.007 |
ware | +0.007 |
ishes | +0.007 |
unes | +0.007 |
fault | +0.006 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.004 |
www | -0.003 |
ww | -0.003 |
Time | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
ishes | +0.026 |
anks | +0.025 |
ware | +0.025 |
unes | +0.025 |
fault | +0.024 |
Neg logit contributions | |
ha | -0.019 |
Little | -0.017 |
www | -0.016 |
ww | -0.016 |
Time | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
anks | +0.010 |
fault | +0.010 |
ware | +0.009 |
unes | +0.009 |
aces | +0.009 |
Neg logit contributions | |
ha | -0.009 |
Little | -0.008 |
www | -0.008 |
unt | -0.008 |
ww | -0.008 |
Token | ride |
Token ID | 6594 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
ha | +0.007 |
Little | +0.007 |
Time | +0.007 |
www | +0.006 |
Sarah | +0.006 |
Neg logit contributions | |
ware | -0.013 |
fault | -0.013 |
ishes | -0.013 |
unes | -0.012 |
ocular | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -9.05e-03 |
Pos logit contributions | |
ha | +0.014 |
Little | +0.012 |
Time | +0.012 |
www | +0.012 |
ww | +0.012 |
Neg logit contributions | |
anks | -0.016 |
ishes | -0.016 |
ware | -0.016 |
unes | -0.015 |
fault | -0.015 |
Token | so |
Token ID | 523 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
ha | +0.016 |
Little | +0.014 |
www | +0.013 |
few | +0.013 |
Time | +0.013 |
Neg logit contributions | |
ishes | -0.019 |
anks | -0.018 |
ware | -0.018 |
unes | -0.018 |
fault | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
ware | +0.063 |
ishes | +0.059 |
mouths | +0.058 |
anks | +0.058 |
ocular | +0.056 |
Neg logit contributions | |
ha | -0.087 |
Time | -0.082 |
Little | -0.081 |
Alice | -0.081 |
www | -0.080 |
Token | went |
Token ID | 1816 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ware | +0.016 |
ishes | +0.016 |
anks | +0.015 |
unes | +0.015 |
aces | +0.015 |
Neg logit contributions | |
ha | -0.011 |
Little | -0.011 |
Time | -0.010 |
www | -0.010 |
Alice | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
anks | +0.024 |
ware | +0.023 |
unes | +0.022 |
ishes | +0.022 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.026 |
Little | -0.025 |
ww | -0.024 |
www | -0.023 |
Time | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
ware | +0.006 |
anks | +0.006 |
fault | +0.006 |
ishes | +0.006 |
unes | +0.006 |
Neg logit contributions | |
ha | -0.005 |
ww | -0.004 |
www | -0.004 |
Little | -0.004 |
Time | -0.004 |
Token | st |
Token ID | 336 |
Feature activation | -3.86e-03 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
www | +0.007 |
ww | +0.007 |
Time | +0.007 |
Neg logit contributions | |
ware | -0.009 |
anks | -0.008 |
ishes | -0.008 |
ocular | -0.008 |
unes | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
ishes | +0.006 |
unes | +0.006 |
anks | +0.006 |
ware | +0.006 |
ocular | +0.006 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
Time | -0.005 |
While | -0.005 |
After | -0.005 |
Token | our |
Token ID | 674 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
www | +0.002 |
Time | +0.002 |
ww | +0.001 |
Neg logit contributions | |
anks | -0.002 |
ishes | -0.002 |
unes | -0.002 |
ware | -0.002 |
fault | -0.002 |
Token | show |
Token ID | 905 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ha | +0.034 |
Little | +0.030 |
www | +0.029 |
ww | +0.028 |
Time | +0.028 |
Neg logit contributions | |
ishes | -0.036 |
ware | -0.036 |
anks | -0.035 |
unes | -0.035 |
fault | -0.035 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
anks | +0.065 |
ware | +0.063 |
ishes | +0.063 |
unes | +0.063 |
fault | +0.062 |
Neg logit contributions | |
ha | -0.048 |
Little | -0.044 |
Time | -0.041 |
www | -0.040 |
T | -0.040 |
Token | They |
Token ID | 1119 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ha | +0.003 |
uren | +0.002 |
few | +0.002 |
unt | +0.002 |
Little | +0.002 |
Neg logit contributions | |
ishes | -0.005 |
unes | -0.004 |
ware | -0.004 |
fault | -0.004 |
anks | -0.004 |
Token | start |
Token ID | 923 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ha | +0.019 |
Little | +0.016 |
www | +0.015 |
ww | +0.015 |
Time | +0.015 |
Neg logit contributions | |
ishes | -0.027 |
ware | -0.027 |
anks | -0.027 |
unes | -0.026 |
fault | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -4.24e-04 |
Pos logit contributions | |
ha | +0.026 |
Little | +0.023 |
www | +0.022 |
ww | +0.022 |
unt | +0.021 |
Neg logit contributions | |
ware | -0.028 |
anks | -0.027 |
ishes | -0.027 |
unes | -0.027 |
fault | -0.027 |
Token | act |
Token ID | 719 |
Feature activation | -3.80e-04 |
Pos logit contributions | |
ha | +0.001 |
www | +0.001 |
ww | +0.001 |
Little | +0.001 |
unt | +0.001 |
Neg logit contributions | |
ware | -0.001 |
ishes | -0.001 |
anks | -0.001 |
fault | -0.001 |
els | -0.001 |
Token | like |
Token ID | 588 |
Feature activation | +8.71e-03 |
Pos logit contributions | |
ha | +0.001 |
Little | +0.001 |
www | +0.001 |
ww | +0.000 |
few | +0.000 |
Neg logit contributions | |
ishes | -0.001 |
ware | -0.001 |
anks | -0.001 |
unes | -0.001 |
fault | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
ishes | +0.020 |
anks | +0.020 |
ware | +0.020 |
unes | +0.020 |
fault | +0.019 |
Neg logit contributions | |
ha | -0.013 |
Little | -0.011 |
few | -0.010 |
www | -0.010 |
Time | -0.010 |
Token | pirate |
Token ID | 25868 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ha | +0.013 |
Little | +0.012 |
www | +0.011 |
Time | +0.011 |
Alice | +0.011 |
Neg logit contributions | |
ware | -0.013 |
fault | -0.012 |
anks | -0.012 |
ishes | -0.012 |
rier | -0.012 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ha | +0.023 |
www | +0.021 |
Little | +0.020 |
ww | +0.020 |
unt | +0.018 |
Neg logit contributions | |
ware | -0.026 |
ishes | -0.023 |
unes | -0.023 |
kins | -0.022 |
melon | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | +9.22e-03 |
Pos logit contributions | |
ishes | +0.026 |
ware | +0.024 |
fault | +0.023 |
anks | +0.022 |
aces | +0.022 |
Neg logit contributions | |
ha | -0.023 |
uren | -0.020 |
unt | -0.020 |
Alice | -0.020 |
www | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
ishes | +0.022 |
ware | +0.022 |
unes | +0.022 |
anks | +0.022 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.011 |
few | -0.010 |
www | -0.010 |
unt | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | -3.55e-04 |
Pos logit contributions | |
ishes | +0.002 |
unes | +0.002 |
ware | +0.002 |
anks | +0.002 |
fault | +0.002 |
Neg logit contributions | |
ha | -0.002 |
uren | -0.002 |
www | -0.002 |
Alice | -0.002 |
Little | -0.002 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ha | +0.001 |
Alice | +0.001 |
Little | +0.001 |
uren | +0.001 |
www | +0.001 |
Neg logit contributions | |
ishes | -0.001 |
ware | -0.001 |
anks | -0.001 |
unes | -0.001 |
fault | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
ha | +0.027 |
www | +0.023 |
Little | +0.023 |
ww | +0.023 |
uren | +0.022 |
Neg logit contributions | |
ishes | -0.040 |
ware | -0.039 |
unes | -0.039 |
anks | -0.038 |
fault | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
ha | +0.011 |
Little | +0.010 |
www | +0.010 |
ww | +0.010 |
Time | +0.010 |
Neg logit contributions | |
ware | -0.013 |
ishes | -0.013 |
anks | -0.012 |
unes | -0.012 |
fault | -0.012 |
Token | write |
Token ID | 3551 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
anks | +0.003 |
ware | +0.003 |
ishes | +0.003 |
unes | +0.003 |
fault | +0.003 |
Neg logit contributions | |
ha | -0.003 |
Little | -0.003 |
www | -0.003 |
ww | -0.003 |
Time | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
ware | +0.018 |
anks | +0.018 |
ishes | +0.018 |
unes | +0.018 |
aces | +0.017 |
Neg logit contributions | |
ha | -0.012 |
www | -0.011 |
Little | -0.011 |
ww | -0.011 |
Time | -0.011 |
Token | name |
Token ID | 1438 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
few | +0.007 |
www | +0.007 |
unt | +0.006 |
Neg logit contributions | |
unes | -0.015 |
ishes | -0.015 |
ware | -0.015 |
anks | -0.015 |
fault | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ha | +0.026 |
Little | +0.023 |
www | +0.023 |
ww | +0.022 |
Time | +0.022 |
Neg logit contributions | |
ware | -0.033 |
anks | -0.032 |
unes | -0.032 |
ishes | -0.031 |
aces | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -8.72e-04 |
Pos logit contributions | |
ware | +0.054 |
ishes | +0.054 |
anks | +0.054 |
unes | +0.054 |
fault | +0.053 |
Neg logit contributions | |
ha | -0.031 |
Little | -0.026 |
few | -0.025 |
www | -0.024 |
unt | -0.024 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.05e-03 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.001 |
www | +0.001 |
ww | +0.001 |
Time | +0.001 |
Neg logit contributions | |
ishes | -0.002 |
ware | -0.002 |
unes | -0.002 |
anks | -0.002 |
fault | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
Little | +0.004 |
ha | +0.004 |
ww | +0.004 |
www | +0.004 |
unt | +0.004 |
Neg logit contributions | |
unes | -0.003 |
anks | -0.003 |
fault | -0.003 |
ocular | -0.003 |
ishes | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
ware | +0.009 |
fault | +0.009 |
anks | +0.009 |
ishes | +0.009 |
unes | +0.008 |
Neg logit contributions | |
ha | -0.006 |
ww | -0.006 |
www | -0.005 |
Little | -0.005 |
unt | -0.005 |
Token | grass |
Token ID | 8701 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ha | +0.009 |
Little | +0.008 |
www | +0.007 |
ww | +0.007 |
Time | +0.007 |
Neg logit contributions | |
ishes | -0.011 |
ware | -0.011 |
anks | -0.011 |
unes | -0.011 |
fault | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e-04 |
Pos logit contributions | |
ha | +0.019 |
Little | +0.016 |
few | +0.016 |
unt | +0.015 |
Time | +0.015 |
Neg logit contributions | |
ishes | -0.032 |
anks | -0.031 |
unes | -0.031 |
ware | -0.031 |
fault | -0.030 |
Token | They |
Token ID | 1119 |
Feature activation | -8.98e-03 |
Pos logit contributions | |
unes | +0.000 |
anks | +0.000 |
ware | +0.000 |
ishes | +0.000 |
fault | +0.000 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.000 |
www | -0.000 |
ww | -0.000 |
Time | -0.000 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
ha | +0.013 |
Little | +0.012 |
ww | +0.012 |
www | +0.012 |
Time | +0.011 |
Neg logit contributions | |
ishes | -0.021 |
ware | -0.020 |
unes | -0.019 |
anks | -0.019 |
fault | -0.019 |
Token | another |
Token ID | 1194 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
anks | +0.022 |
ishes | +0.022 |
ware | +0.022 |
unes | +0.022 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.008 |
few | -0.008 |
Time | -0.008 |
www | -0.007 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
ware | +0.024 |
fault | +0.024 |
ishes | +0.024 |
unes | +0.023 |
anks | +0.023 |
Neg logit contributions | |
ha | -0.025 |
Little | -0.022 |
uren | -0.022 |
Time | -0.022 |
T | -0.022 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.38e-04 |
Pos logit contributions | |
ishes | +0.006 |
ware | +0.006 |
anks | +0.006 |
unes | +0.006 |
fault | +0.006 |
Neg logit contributions | |
ha | -0.005 |
Little | -0.004 |
www | -0.004 |
ww | -0.004 |
unt | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
ha | +0.025 |
www | +0.023 |
Alice | +0.023 |
unt | +0.023 |
uren | +0.022 |
Neg logit contributions | |
ishes | -0.032 |
unes | -0.031 |
anks | -0.030 |
ware | -0.030 |
mouths | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
ha | +0.005 |
www | +0.004 |
Little | +0.004 |
unt | +0.004 |
ww | +0.004 |
Neg logit contributions | |
ishes | -0.009 |
anks | -0.009 |
ware | -0.009 |
unes | -0.009 |
fault | -0.009 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +9.83e-03 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
Alice | +0.005 |
Little | +0.005 |
ww | +0.005 |
Neg logit contributions | |
ishes | -0.007 |
ware | -0.007 |
anks | -0.007 |
unes | -0.006 |
fault | -0.006 |
Token | went |
Token ID | 1816 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ishes | +0.022 |
ware | +0.022 |
anks | +0.022 |
unes | +0.021 |
fault | +0.021 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.013 |
www | -0.012 |
ww | -0.012 |
Time | -0.012 |
Token | back |
Token ID | 736 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
anks | +0.027 |
unes | +0.026 |
ishes | +0.025 |
ware | +0.025 |
fault | +0.024 |
Neg logit contributions | |
ha | -0.032 |
Little | -0.030 |
www | -0.028 |
ww | -0.028 |
T | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +4.89e-03 |
Pos logit contributions | |
ishes | +0.041 |
anks | +0.040 |
ware | +0.040 |
unes | +0.040 |
fault | +0.039 |
Neg logit contributions | |
ha | -0.035 |
Little | -0.031 |
www | -0.030 |
ww | -0.029 |
Time | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
anks | +0.010 |
ware | +0.010 |
fault | +0.010 |
ishes | +0.010 |
unes | +0.010 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.007 |
www | -0.007 |
ww | -0.007 |
unt | -0.007 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
Little | +0.005 |
uren | +0.005 |
ww | +0.005 |
Neg logit contributions | |
ware | -0.006 |
ishes | -0.006 |
anks | -0.005 |
fault | -0.005 |
melon | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
ishes | +0.004 |
unes | +0.004 |
ware | +0.004 |
anks | +0.004 |
fault | +0.003 |
Neg logit contributions | |
ha | -0.002 |
Little | -0.002 |
few | -0.002 |
www | -0.002 |
Time | -0.002 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.54e-03 |
Pos logit contributions | |
ishes | +0.009 |
anks | +0.008 |
ware | +0.008 |
unes | +0.008 |
fault | +0.008 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.006 |
ww | -0.005 |
www | -0.005 |
unt | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
ishes | +0.005 |
anks | +0.005 |
ware | +0.005 |
unes | +0.005 |
fault | +0.005 |
Neg logit contributions | |
ha | -0.005 |
Little | -0.004 |
www | -0.004 |
ww | -0.004 |
Time | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
ww | +0.005 |
unt | +0.005 |
Little | +0.005 |
Neg logit contributions | |
ware | -0.008 |
unes | -0.008 |
ishes | -0.008 |
anks | -0.008 |
fault | -0.008 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.003 |
www | +0.003 |
ww | +0.003 |
T | +0.003 |
Neg logit contributions | |
ware | -0.005 |
fault | -0.005 |
ishes | -0.005 |
unes | -0.005 |
anks | -0.005 |
Token | became |
Token ID | 2627 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ha | +0.015 |
ww | +0.015 |
www | +0.015 |
Time | +0.014 |
unt | +0.014 |
Neg logit contributions | |
ishes | -0.021 |
ware | -0.020 |
aces | -0.019 |
anks | -0.019 |
els | -0.019 |
Token | still |
Token ID | 991 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ware | +0.031 |
ishes | +0.031 |
anks | +0.031 |
unes | +0.031 |
fault | +0.030 |
Neg logit contributions | |
ha | -0.025 |
Little | -0.022 |
few | -0.022 |
www | -0.021 |
Time | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +5.33e-03 |
Pos logit contributions | |
ishes | +0.033 |
anks | +0.033 |
ware | +0.033 |
fault | +0.033 |
unes | +0.032 |
Neg logit contributions | |
ha | -0.028 |
Little | -0.024 |
www | -0.023 |
ww | -0.023 |
unt | -0.022 |
Token | Instead |
Token ID | 5455 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
ishes | +0.012 |
ware | +0.012 |
anks | +0.012 |
unes | +0.012 |
fault | +0.012 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.007 |
www | -0.007 |
few | -0.007 |
Time | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ha | +0.034 |
Little | +0.031 |
www | +0.030 |
ww | +0.030 |
Time | +0.030 |
Neg logit contributions | |
unes | -0.041 |
ware | -0.041 |
ishes | -0.040 |
anks | -0.040 |
fault | -0.040 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
fault | +0.028 |
ware | +0.028 |
anks | +0.028 |
ishes | +0.028 |
unes | +0.028 |
Neg logit contributions | |
ha | -0.023 |
Little | -0.020 |
www | -0.020 |
ww | -0.019 |
unt | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
ha | +0.026 |
www | +0.023 |
ww | +0.023 |
Little | +0.023 |
Time | +0.022 |
Neg logit contributions | |
ware | -0.036 |
unes | -0.035 |
ishes | -0.035 |
anks | -0.035 |
fault | -0.033 |
Token | she |
Token ID | 673 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
ww | +0.005 |
Little | +0.005 |
unt | +0.005 |
Neg logit contributions | |
ware | -0.012 |
ishes | -0.011 |
unes | -0.011 |
anks | -0.011 |
fault | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ishes | +0.012 |
ware | +0.012 |
anks | +0.012 |
unes | +0.012 |
fault | +0.012 |
Neg logit contributions | |
ha | -0.008 |
Little | -0.008 |
www | -0.007 |
ww | -0.007 |
Time | -0.007 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ha | +0.044 |
Little | +0.039 |
www | +0.037 |
Alice | +0.036 |
ww | +0.036 |
Neg logit contributions | |
ware | -0.054 |
anks | -0.053 |
unes | -0.052 |
ishes | -0.051 |
fault | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-03 |
Pos logit contributions | |
ha | +0.037 |
www | +0.033 |
Little | +0.033 |
ww | +0.032 |
uren | +0.032 |
Neg logit contributions | |
ware | -0.031 |
anks | -0.031 |
unes | -0.031 |
ishes | -0.030 |
fault | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
ishes | +0.008 |
anks | +0.007 |
ware | +0.007 |
unes | +0.007 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.004 |
Little | -0.004 |
Time | -0.004 |
T | -0.004 |
few | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
ha | +0.006 |
www | +0.005 |
ww | +0.005 |
Little | +0.005 |
few | +0.005 |
Neg logit contributions | |
ware | -0.009 |
anks | -0.009 |
ishes | -0.009 |
unes | -0.009 |
fault | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
ha | +0.007 |
Margaret | +0.007 |
uren | +0.007 |
Kelly | +0.006 |
www | +0.006 |
Neg logit contributions | |
kins | -0.012 |
auc | -0.012 |
ests | -0.012 |
ases | -0.012 |
els | -0.011 |
Token | Stop |
Token ID | 19485 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
ha | +0.012 |
www | +0.010 |
unt | +0.010 |
few | +0.010 |
uren | +0.010 |
Neg logit contributions | |
ware | -0.020 |
ishes | -0.019 |
unes | -0.019 |
ests | -0.018 |
fault | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
ha | +0.084 |
Time | +0.077 |
Little | +0.076 |
Alice | +0.074 |
unt | +0.073 |
Neg logit contributions | |
fault | -0.109 |
ishes | -0.106 |
anks | -0.103 |
unes | -0.103 |
ware | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
anks | +0.003 |
unes | +0.003 |
ishes | +0.003 |
fault | +0.003 |
ware | +0.003 |
Neg logit contributions | |
ha | -0.002 |
uren | -0.002 |
Time | -0.002 |
T | -0.002 |
Little | -0.002 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.13e-03 |
Pos logit contributions | |
ha | +0.016 |
Little | +0.014 |
www | +0.014 |
unt | +0.014 |
ww | +0.014 |
Neg logit contributions | |
ishes | -0.020 |
ware | -0.020 |
unes | -0.020 |
fault | -0.020 |
anks | -0.020 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.001 |
Time | +0.001 |
few | +0.001 |
uren | +0.001 |
Neg logit contributions | |
ishes | -0.003 |
anks | -0.002 |
fault | -0.002 |
unes | -0.002 |
ware | -0.002 |
Token | L |
Token ID | 406 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
ha | +0.009 |
Little | +0.008 |
www | +0.007 |
few | +0.007 |
Time | +0.007 |
Neg logit contributions | |
ishes | -0.017 |
anks | -0.017 |
unes | -0.017 |
ware | -0.017 |
fault | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
ishes | +0.025 |
ware | +0.025 |
anks | +0.025 |
unes | +0.025 |
fault | +0.024 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.010 |
www | -0.009 |
ww | -0.009 |
Time | -0.009 |
Token | there |
Token ID | 612 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
ha | +0.014 |
www | +0.012 |
Little | +0.012 |
ww | +0.011 |
uren | +0.011 |
Neg logit contributions | |
ishes | -0.020 |
ware | -0.020 |
fault | -0.020 |
unes | -0.020 |
anks | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
ishes | +0.003 |
anks | +0.003 |
ware | +0.003 |
unes | +0.003 |
fault | +0.003 |
Neg logit contributions | |
ha | -0.002 |
Little | -0.002 |
www | -0.002 |
Time | -0.002 |
ww | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
fault | +0.009 |
unes | +0.009 |
ishes | +0.009 |
ware | +0.009 |
anks | +0.009 |
Neg logit contributions | |
ha | -0.006 |
www | -0.005 |
Little | -0.005 |
unt | -0.005 |
ww | -0.004 |
Token | k |
Token ID | 479 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ha | +0.015 |
www | +0.012 |
Alice | +0.011 |
Time | +0.011 |
Kelly | +0.011 |
Neg logit contributions | |
ware | -0.023 |
ishes | -0.022 |
rier | -0.021 |
kins | -0.021 |
melon | -0.021 |
Token | ang |
Token ID | 648 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
ha | +0.041 |
Little | +0.037 |
www | +0.036 |
Time | +0.036 |
ww | +0.035 |
Neg logit contributions | |
ishes | -0.030 |
ware | -0.029 |
anks | -0.029 |
unes | -0.029 |
fault | -0.027 |
Token | aroo |
Token ID | 38049 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ha | +0.095 |
Little | +0.087 |
Time | +0.086 |
www | +0.084 |
ww | +0.084 |
Neg logit contributions | |
ware | -0.059 |
ishes | -0.057 |
unes | -0.057 |
anks | -0.056 |
fault | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-04 |
Pos logit contributions | |
ha | +0.020 |
Little | +0.018 |
www | +0.017 |
Time | +0.017 |
ww | +0.017 |
Neg logit contributions | |
ishes | -0.026 |
ware | -0.026 |
anks | -0.026 |
unes | -0.026 |
fault | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | +7.61e-03 |
Pos logit contributions | |
unes | +0.001 |
anks | +0.001 |
ishes | +0.001 |
ware | +0.001 |
aces | +0.001 |
Neg logit contributions | |
ha | -0.001 |
Little | -0.001 |
www | -0.001 |
Time | -0.001 |
few | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
ishes | +0.016 |
ware | +0.016 |
anks | +0.016 |
unes | +0.016 |
fault | +0.015 |
Neg logit contributions | |
ha | -0.012 |
Little | -0.011 |
www | -0.010 |
Time | -0.010 |
unt | -0.010 |
Token | very |
Token ID | 845 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
ishes | +0.007 |
anks | +0.007 |
unes | +0.007 |
ware | +0.007 |
fault | +0.007 |
Neg logit contributions | |
ha | -0.006 |
Little | -0.005 |
www | -0.005 |
Time | -0.005 |
ww | -0.005 |
Token | but |
Token ID | 475 |
Feature activation | +1.51e-05 |
Pos logit contributions | |
ha | +0.027 |
Little | +0.023 |
www | +0.023 |
ww | +0.023 |
unt | +0.022 |
Neg logit contributions | |
ware | -0.024 |
fault | -0.024 |
unes | -0.023 |
aces | -0.023 |
ishes | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | -2.30e-03 |
Pos logit contributions | |
ware | +0.000 |
ishes | +0.000 |
fault | +0.000 |
unes | +0.000 |
anks | +0.000 |
Neg logit contributions | |
ha | -0.000 |
Little | -0.000 |
www | -0.000 |
ww | -0.000 |
few | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.003 |
www | +0.003 |
ww | +0.003 |
few | +0.003 |
Neg logit contributions | |
ware | -0.005 |
ishes | -0.005 |
anks | -0.005 |
unes | -0.005 |
fault | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
fault | +0.009 |
ishes | +0.009 |
anks | +0.009 |
unes | +0.009 |
ware | +0.009 |
Neg logit contributions | |
ha | -0.010 |
Little | -0.009 |
www | -0.009 |
ww | -0.009 |
uren | -0.008 |
Token | hard |
Token ID | 1327 |
Feature activation | +6.25e-03 |
Pos logit contributions | |
ishes | +0.014 |
unes | +0.014 |
ware | +0.014 |
anks | +0.014 |
rier | +0.014 |
Neg logit contributions | |
ha | -0.015 |
Little | -0.012 |
Time | -0.012 |
uren | -0.012 |
Charlie | -0.012 |
Token | working |
Token ID | 16090 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
anks | +0.013 |
fault | +0.013 |
ishes | +0.012 |
ware | +0.012 |
unes | +0.012 |
Neg logit contributions | |
ha | -0.011 |
Little | -0.010 |
www | -0.010 |
ww | -0.009 |
Time | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
ha | +0.091 |
Little | +0.079 |
www | +0.076 |
few | +0.075 |
ww | +0.075 |
Neg logit contributions | |
ishes | -0.116 |
ware | -0.114 |
anks | -0.114 |
unes | -0.114 |
fault | -0.111 |
Token | She |
Token ID | 1375 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
ha | +0.004 |
Little | +0.004 |
Time | +0.004 |
few | +0.004 |
www | +0.003 |
Neg logit contributions | |
ishes | -0.008 |
anks | -0.008 |
ware | -0.008 |
unes | -0.007 |
fault | -0.007 |
Token | loved |
Token ID | 6151 |
Feature activation | -5.24e-03 |
Pos logit contributions | |
ha | +0.009 |
Little | +0.008 |
ww | +0.007 |
www | +0.007 |
Time | +0.007 |
Neg logit contributions | |
ware | -0.012 |
ishes | -0.012 |
unes | -0.012 |
fault | -0.012 |
anks | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +7.10e-04 |
Pos logit contributions | |
ha | +0.010 |
Little | +0.008 |
www | +0.008 |
ww | +0.008 |
uren | +0.008 |
Neg logit contributions | |
ishes | -0.010 |
ware | -0.010 |
unes | -0.010 |
anks | -0.010 |
fault | -0.010 |
Token | pick |
Token ID | 2298 |
Feature activation | -2.80e-03 |
Pos logit contributions | |
ware | +0.001 |
anks | +0.001 |
ishes | +0.001 |
unes | +0.001 |
fault | +0.001 |
Neg logit contributions | |
ha | -0.001 |
ww | -0.001 |
Little | -0.001 |
Time | -0.001 |
www | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ha | +0.008 |
Little | +0.007 |
few | +0.006 |
unt | +0.006 |
T | +0.006 |
Neg logit contributions | |
ware | -0.014 |
ishes | -0.014 |
unes | -0.014 |
anks | -0.014 |
fault | -0.013 |
Token | Tom |
Token ID | 4186 |
Feature activation | -5.06e-04 |
Pos logit contributions | |
ha | +0.015 |
Little | +0.013 |
www | +0.012 |
ww | +0.012 |
few | +0.012 |
Neg logit contributions | |
ishes | -0.026 |
ware | -0.026 |
anks | -0.026 |
unes | -0.026 |
fault | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
ha | +0.001 |
few | +0.001 |
Little | +0.001 |
T | +0.000 |
" | +0.000 |
Neg logit contributions | |
ware | -0.001 |
ishes | -0.001 |
unes | -0.001 |
anks | -0.001 |
ests | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
ha | +0.007 |
Little | +0.006 |
few | +0.005 |
Time | +0.005 |
unt | +0.005 |
Neg logit contributions | |
ishes | -0.015 |
anks | -0.014 |
ware | -0.014 |
unes | -0.014 |
fault | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
ha | +0.009 |
Little | +0.007 |
www | +0.007 |
Time | +0.007 |
few | +0.007 |
Neg logit contributions | |
ishes | -0.016 |
ware | -0.016 |
anks | -0.016 |
unes | -0.016 |
fault | -0.015 |
Token | S |
Token ID | 50 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
ha | +0.008 |
Kelly | +0.006 |
uren | +0.006 |
www | +0.006 |
Little | +0.006 |
Neg logit contributions | |
ware | -0.019 |
ishes | -0.019 |
unes | -0.019 |
rier | -0.019 |
anks | -0.019 |
Token | ara |
Token ID | 3301 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
ha | +0.059 |
Little | +0.049 |
www | +0.047 |
few | +0.046 |
ww | +0.046 |
Neg logit contributions | |
ishes | -0.106 |
ware | -0.106 |
anks | -0.105 |
unes | -0.105 |
fault | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ha | +0.034 |
Little | +0.027 |
" | +0.026 |
www | +0.025 |
unt | +0.025 |
Neg logit contributions | |
unes | -0.057 |
anks | -0.057 |
ware | -0.057 |
ishes | -0.056 |
fault | -0.055 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
ha | +0.014 |
Little | +0.012 |
www | +0.011 |
ww | +0.010 |
Time | +0.010 |
Neg logit contributions | |
ishes | -0.031 |
ware | -0.031 |
anks | -0.031 |
unes | -0.031 |
fault | -0.030 |
Token | are |
Token ID | 389 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
ha | +0.002 |
Little | +0.002 |
www | +0.002 |
few | +0.002 |
Time | +0.002 |
Neg logit contributions | |
ware | -0.002 |
ishes | -0.002 |
unes | -0.002 |
anks | -0.002 |
fault | -0.002 |
Token | scared |
Token ID | 12008 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
ware | +0.004 |
unes | +0.004 |
ishes | +0.004 |
anks | +0.004 |
fault | +0.004 |
Neg logit contributions | |
ha | -0.002 |
few | -0.002 |
Little | -0.002 |
Time | -0.002 |
Alice | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
ha | +0.026 |
Little | +0.023 |
few | +0.022 |
Time | +0.021 |
unt | +0.021 |
Neg logit contributions | |
ishes | -0.040 |
anks | -0.039 |
unes | -0.039 |
ware | -0.039 |
fault | -0.038 |
Token | rocket |
Token ID | 10701 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ha | +0.010 |
Little | +0.009 |
www | +0.009 |
ww | +0.009 |
Time | +0.008 |
Neg logit contributions | |
ware | -0.009 |
ishes | -0.009 |
unes | -0.008 |
anks | -0.008 |
fault | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
ishes | +0.048 |
unes | +0.048 |
anks | +0.047 |
fault | +0.047 |
ware | +0.047 |
Neg logit contributions | |
ha | -0.030 |
Little | -0.025 |
few | -0.024 |
unt | -0.023 |
www | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ha | +0.010 |
Little | +0.009 |
Time | +0.009 |
few | +0.009 |
unt | +0.009 |
Neg logit contributions | |
ishes | -0.010 |
ware | -0.010 |
anks | -0.010 |
unes | -0.009 |
fault | -0.009 |
Token | count |
Token ID | 954 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
ha | +0.019 |
Little | +0.017 |
www | +0.016 |
few | +0.016 |
ww | +0.015 |
Neg logit contributions | |
ishes | -0.026 |
anks | -0.026 |
ware | -0.026 |
unes | -0.026 |
fault | -0.026 |
Token | down |
Token ID | 866 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
anks | +0.013 |
ishes | +0.013 |
unes | +0.012 |
ware | +0.012 |
fault | +0.012 |
Neg logit contributions | |
ha | -0.007 |
Little | -0.006 |
few | -0.006 |
Time | -0.005 |
www | -0.005 |
Token | from |
Token ID | 422 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
ha | +0.074 |
Little | +0.063 |
www | +0.063 |
ww | +0.062 |
Time | +0.059 |
Neg logit contributions | |
ware | -0.104 |
ishes | -0.104 |
anks | -0.104 |
unes | -0.103 |
fault | -0.101 |
Token | ten |
Token ID | 3478 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ishes | +0.106 |
anks | +0.106 |
ware | +0.105 |
unes | +0.105 |
fault | +0.103 |
Neg logit contributions | |
ha | -0.055 |
Little | -0.046 |
www | -0.043 |
few | -0.042 |
ww | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | +1.61e-04 |
Pos logit contributions | |
ha | +0.018 |
Little | +0.016 |
www | +0.016 |
ww | +0.016 |
Time | +0.015 |
Neg logit contributions | |
ware | -0.024 |
ishes | -0.024 |
unes | -0.023 |
anks | -0.023 |
fault | -0.022 |
Token | zero |
Token ID | 6632 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
ware | +0.000 |
ishes | +0.000 |
anks | +0.000 |
unes | +0.000 |
fault | +0.000 |
Neg logit contributions | |
ha | -0.000 |
www | -0.000 |
ww | -0.000 |
Little | -0.000 |
unt | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
anks | +0.005 |
ishes | +0.005 |
unes | +0.005 |
fault | +0.005 |
ware | +0.005 |
Neg logit contributions | |
ha | -0.003 |
Little | -0.003 |
few | -0.003 |
www | -0.003 |
Time | -0.003 |