Token | two |
Token ID | 734 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
Stacy | +0.106 |
kit | +0.101 |
kettle | +0.100 |
sy | +0.096 |
Grac | +0.095 |
Neg logit contributions | |
ust | -0.068 |
adventure | -0.065 |
ight | -0.061 |
all | -0.058 |
eternity | -0.055 |
Token | fingers |
Token ID | 9353 |
Feature activation | +9.69e-03 |
Pos logit contributions | |
Stacy | +0.117 |
kit | +0.114 |
kettle | +0.109 |
violet | +0.104 |
Grac | +0.103 |
Neg logit contributions | |
ust | -0.101 |
adventure | -0.094 |
ight | -0.094 |
eternity | -0.088 |
all | -0.086 |
Token | left |
Token ID | 1364 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
Stacy | +0.021 |
kit | +0.020 |
kettle | +0.020 |
sy | +0.019 |
violet | +0.019 |
Neg logit contributions | |
ust | -0.011 |
ight | -0.010 |
adventure | -0.010 |
all | -0.009 |
eternity | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Stacy | +0.057 |
kit | +0.056 |
kettle | +0.053 |
sy | +0.051 |
tin | +0.051 |
Neg logit contributions | |
ust | -0.042 |
ight | -0.038 |
adventure | -0.037 |
eternity | -0.036 |
all | -0.035 |
Token | Four |
Token ID | 6675 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
kit | +0.030 |
kettle | +0.029 |
Stacy | +0.029 |
tin | +0.028 |
shone | +0.027 |
Neg logit contributions | |
ust | -0.032 |
all | -0.030 |
ight | -0.030 |
eternity | -0.029 |
end | -0.029 |
Token | minus |
Token ID | 20208 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Stacy | +0.095 |
kit | +0.093 |
kettle | +0.090 |
sy | +0.087 |
Grac | +0.086 |
Neg logit contributions | |
ust | -0.080 |
adventure | -0.075 |
ight | -0.075 |
eternity | -0.070 |
anymore | -0.069 |
Token | two |
Token ID | 734 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
Stacy | +0.205 |
kettle | +0.203 |
kit | +0.200 |
Grac | +0.192 |
sy | +0.188 |
Neg logit contributions | |
ust | -0.162 |
ight | -0.159 |
adventure | -0.149 |
anymore | -0.142 |
eternity | -0.141 |
Token | is |
Token ID | 318 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Stacy | +0.115 |
kit | +0.112 |
kettle | +0.108 |
Grac | +0.101 |
violet | +0.101 |
Neg logit contributions | |
ust | -0.088 |
ight | -0.082 |
adventure | -0.082 |
eternity | -0.076 |
anymore | -0.075 |
Token | two |
Token ID | 734 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
Stacy | +0.034 |
kit | +0.033 |
kettle | +0.033 |
sy | +0.032 |
Did | +0.032 |
Neg logit contributions | |
ust | -0.028 |
adventure | -0.027 |
ight | -0.026 |
eternity | -0.025 |
all | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
Stacy | +0.128 |
kit | +0.125 |
kettle | +0.120 |
Grac | +0.115 |
sy | +0.115 |
Neg logit contributions | |
ust | -0.072 |
adventure | -0.066 |
ight | -0.066 |
eternity | -0.061 |
anymore | -0.059 |
Token | See |
Token ID | 4091 |
Feature activation | +7.86e-03 |
Pos logit contributions | |
Stacy | +0.034 |
kit | +0.034 |
kettle | +0.033 |
tin | +0.032 |
shone | +0.031 |
Neg logit contributions | |
ust | -0.037 |
ight | -0.034 |
all | -0.034 |
eternity | -0.033 |
end | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
kit | +0.044 |
Stacy | +0.042 |
kettle | +0.040 |
tin | +0.039 |
sy | +0.039 |
Neg logit contributions | |
ust | -0.044 |
adventure | -0.039 |
ight | -0.039 |
all | -0.038 |
eternity | -0.038 |
Token | are |
Token ID | 389 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
Stacy | +0.053 |
kit | +0.053 |
kettle | +0.050 |
sy | +0.047 |
Grac | +0.046 |
Neg logit contributions | |
ust | -0.061 |
adventure | -0.058 |
ight | -0.056 |
eternity | -0.053 |
all | -0.053 |
Token | good |
Token ID | 922 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
Stacy | +0.050 |
kit | +0.049 |
kettle | +0.048 |
Did | +0.047 |
sy | +0.047 |
Neg logit contributions | |
ust | -0.034 |
adventure | -0.032 |
ight | -0.030 |
all | -0.029 |
happening | -0.028 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
kit | +0.036 |
Stacy | +0.035 |
kettle | +0.032 |
sy | +0.031 |
te | +0.031 |
Neg logit contributions | |
ust | -0.053 |
ight | -0.049 |
adventure | -0.047 |
eternity | -0.047 |
all | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
kit | +0.147 |
Stacy | +0.140 |
Elsa | +0.133 |
te | +0.130 |
kettle | +0.130 |
Neg logit contributions | |
ust | -0.106 |
eternity | -0.092 |
ight | -0.092 |
uct | -0.089 |
all | -0.088 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
adventure | +0.004 |
ust | +0.004 |
exciting | +0.004 |
unexpected | +0.003 |
interesting | +0.003 |
Neg logit contributions | |
piping | -0.005 |
kettle | -0.005 |
Stacy | -0.005 |
kit | -0.005 |
sy | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
kit | +0.240 |
Stacy | +0.237 |
kettle | +0.222 |
sy | +0.219 |
Elsa | +0.218 |
Neg logit contributions | |
ust | -0.136 |
ight | -0.118 |
adventure | -0.114 |
eternity | -0.113 |
all | -0.108 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
kit | +0.042 |
Stacy | +0.041 |
kettle | +0.039 |
tin | +0.038 |
sy | +0.038 |
Neg logit contributions | |
ust | -0.039 |
adventure | -0.035 |
ight | -0.034 |
eternity | -0.034 |
all | -0.034 |
Token | L |
Token ID | 43 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
ust | +0.058 |
ight | +0.053 |
adventure | +0.053 |
eternity | +0.052 |
all | +0.049 |
Neg logit contributions | |
Stacy | -0.038 |
kit | -0.038 |
kettle | -0.034 |
te | -0.033 |
Elsa | -0.033 |
Token | ily |
Token ID | 813 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
ust | +0.010 |
ight | +0.009 |
adventure | +0.009 |
eternity | +0.009 |
all | +0.008 |
Neg logit contributions | |
Stacy | -0.010 |
kit | -0.009 |
kettle | -0.009 |
Elsa | -0.008 |
te | -0.008 |
Token | liked |
Token ID | 8288 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
Stacy | +0.060 |
kit | +0.058 |
kettle | +0.055 |
Grac | +0.053 |
sy | +0.052 |
Neg logit contributions | |
ust | -0.069 |
adventure | -0.067 |
ight | -0.064 |
eternity | -0.063 |
all | -0.062 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
kit | +0.021 |
kettle | +0.019 |
Stacy | +0.018 |
bottle | +0.018 |
tin | +0.017 |
Neg logit contributions | |
ust | -0.038 |
ight | -0.035 |
all | -0.033 |
uct | -0.033 |
eternity | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
kit | +0.091 |
Stacy | +0.089 |
kettle | +0.084 |
sy | +0.082 |
Elsa | +0.082 |
Neg logit contributions | |
ust | -0.055 |
ight | -0.048 |
adventure | -0.047 |
eternity | -0.047 |
all | -0.044 |
Token | their |
Token ID | 511 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
adventure | +0.008 |
ust | +0.007 |
eternity | +0.006 |
exciting | +0.006 |
all | +0.006 |
Neg logit contributions | |
Stacy | -0.011 |
kit | -0.011 |
kettle | -0.011 |
Grac | -0.010 |
piping | -0.010 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
kit | +0.045 |
Stacy | +0.041 |
kettle | +0.041 |
sy | +0.039 |
tin | +0.039 |
Neg logit contributions | |
ust | -0.071 |
ight | -0.066 |
all | -0.062 |
eternity | -0.061 |
uct | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
kit | +0.166 |
Stacy | +0.161 |
kettle | +0.151 |
Elsa | +0.151 |
sy | +0.150 |
Neg logit contributions | |
ust | -0.103 |
ight | -0.090 |
eternity | -0.085 |
adventure | -0.083 |
all | -0.083 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
adventure | +0.015 |
ust | +0.012 |
eternity | +0.012 |
exciting | +0.012 |
behind | +0.011 |
Neg logit contributions | |
Stacy | -0.021 |
kettle | -0.020 |
kit | -0.019 |
piping | -0.019 |
Grac | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
kit | +0.243 |
Stacy | +0.240 |
kettle | +0.226 |
sy | +0.222 |
te | +0.222 |
Neg logit contributions | |
ust | -0.130 |
ight | -0.113 |
adventure | -0.108 |
eternity | -0.107 |
all | -0.102 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
Stacy | +0.034 |
kit | +0.034 |
kettle | +0.030 |
sy | +0.029 |
tin | +0.029 |
Neg logit contributions | |
ust | -0.052 |
adventure | -0.048 |
ight | -0.048 |
eternity | -0.046 |
all | -0.046 |
Token | S |
Token ID | 50 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
ust | +0.051 |
ight | +0.047 |
eternity | +0.045 |
adventure | +0.045 |
uct | +0.043 |
Neg logit contributions | |
kit | -0.031 |
Stacy | -0.031 |
kettle | -0.027 |
Elsa | -0.026 |
te | -0.026 |
Token | ara |
Token ID | 3301 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ust | +0.103 |
eternity | +0.094 |
ight | +0.094 |
adventure | +0.093 |
all | +0.088 |
Neg logit contributions | |
Stacy | -0.069 |
kit | -0.068 |
kettle | -0.063 |
piping | -0.060 |
violet | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -3.51e-03 |
Pos logit contributions | |
Stacy | +0.042 |
kit | +0.041 |
kettle | +0.039 |
sy | +0.038 |
Grac | +0.038 |
Neg logit contributions | |
ust | -0.027 |
adventure | -0.025 |
ight | -0.025 |
eternity | -0.023 |
all | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Stacy | +0.009 |
kit | +0.009 |
sy | +0.008 |
kettle | +0.008 |
Elsa | +0.008 |
Neg logit contributions | |
ust | -0.007 |
ight | -0.006 |
adventure | -0.006 |
uct | -0.006 |
eternity | -0.006 |
Token | You |
Token ID | 921 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
kit | +0.039 |
Stacy | +0.038 |
kettle | +0.038 |
tin | +0.037 |
te | +0.036 |
Neg logit contributions | |
ust | -0.044 |
all | -0.041 |
ight | -0.040 |
eternity | -0.039 |
end | -0.038 |
Token | are |
Token ID | 389 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Stacy | +0.010 |
kit | +0.010 |
kettle | +0.010 |
violet | +0.009 |
piping | +0.009 |
Neg logit contributions | |
ust | -0.010 |
ight | -0.009 |
adventure | -0.009 |
unexpected | -0.008 |
all | -0.008 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
Stacy | +0.055 |
kit | +0.054 |
kettle | +0.053 |
sy | +0.051 |
Did | +0.050 |
Neg logit contributions | |
ust | -0.038 |
ight | -0.034 |
adventure | -0.034 |
all | -0.032 |
unexpected | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
kit | +0.147 |
Stacy | +0.139 |
sy | +0.132 |
kettle | +0.131 |
Elsa | +0.130 |
Neg logit contributions | |
ust | -0.104 |
ight | -0.090 |
eternity | -0.090 |
adventure | -0.088 |
all | -0.086 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ust | +0.012 |
adventure | +0.012 |
unexpected | +0.011 |
happening | +0.010 |
exciting | +0.010 |
Neg logit contributions | |
Stacy | -0.013 |
kit | -0.012 |
kettle | -0.012 |
piping | -0.012 |
violet | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
kit | +0.226 |
Stacy | +0.222 |
kettle | +0.208 |
sy | +0.205 |
Elsa | +0.203 |
Neg logit contributions | |
ust | -0.142 |
ight | -0.125 |
adventure | -0.123 |
eternity | -0.121 |
all | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Stacy | +0.024 |
kit | +0.024 |
kettle | +0.022 |
sy | +0.022 |
Elsa | +0.022 |
Neg logit contributions | |
ust | -0.018 |
ight | -0.016 |
adventure | -0.015 |
eternity | -0.015 |
all | -0.014 |
Token | you |
Token ID | 345 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
adventure | +0.014 |
ust | +0.013 |
unexpected | +0.012 |
exciting | +0.011 |
eternity | +0.011 |
Neg logit contributions | |
Stacy | -0.024 |
kettle | -0.024 |
kit | -0.023 |
violet | -0.022 |
piping | -0.022 |
Token | should |
Token ID | 815 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ust | +0.023 |
ight | +0.022 |
adventure | +0.021 |
anymore | +0.020 |
all | +0.019 |
Neg logit contributions | |
Stacy | -0.024 |
kettle | -0.022 |
kit | -0.022 |
violet | -0.021 |
piping | -0.021 |
Token | be |
Token ID | 307 |
Feature activation | +1.15e-04 |
Pos logit contributions | |
Stacy | +0.029 |
kit | +0.028 |
kettle | +0.027 |
sy | +0.025 |
Did | +0.025 |
Neg logit contributions | |
ust | -0.029 |
adventure | -0.027 |
ight | -0.026 |
all | -0.025 |
eternity | -0.025 |
Token | having |
Token ID | 1719 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
Stacy | +0.083 |
kit | +0.083 |
kettle | +0.077 |
sy | +0.075 |
Grac | +0.074 |
Neg logit contributions | |
ust | -0.069 |
ight | -0.062 |
adventure | -0.062 |
eternity | -0.059 |
all | -0.057 |
Token | trouble |
Token ID | 5876 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
kit | +0.075 |
Stacy | +0.074 |
te | +0.070 |
kettle | +0.070 |
Grac | +0.070 |
Neg logit contributions | |
ust | -0.060 |
ight | -0.055 |
eternity | -0.052 |
adventure | -0.050 |
all | -0.049 |
Token | with |
Token ID | 351 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
ust | +0.045 |
ight | +0.041 |
adventure | +0.039 |
eternity | +0.038 |
all | +0.037 |
Neg logit contributions | |
kit | -0.054 |
Stacy | -0.053 |
kettle | -0.050 |
sy | -0.049 |
Grac | -0.048 |
Token | my |
Token ID | 616 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
Stacy | +0.064 |
kit | +0.062 |
kettle | +0.059 |
Elsa | +0.057 |
Grac | +0.057 |
Neg logit contributions | |
ust | -0.058 |
ight | -0.052 |
adventure | -0.051 |
eternity | -0.050 |
all | -0.048 |
Token | cash |
Token ID | 5003 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
Stacy | +0.036 |
kit | +0.036 |
kettle | +0.034 |
sy | +0.032 |
Grac | +0.032 |
Neg logit contributions | |
ust | -0.043 |
ight | -0.040 |
adventure | -0.039 |
eternity | -0.038 |
all | -0.037 |
Token | register |
Token ID | 7881 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Stacy | +0.069 |
kit | +0.068 |
kettle | +0.065 |
sy | +0.063 |
violet | +0.063 |
Neg logit contributions | |
ust | -0.046 |
ight | -0.041 |
adventure | -0.040 |
eternity | -0.039 |
all | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
Stacy | +0.236 |
kit | +0.233 |
kettle | +0.221 |
sy | +0.216 |
Grac | +0.214 |
Neg logit contributions | |
ust | -0.130 |
ight | -0.115 |
adventure | -0.113 |
eternity | -0.107 |
all | -0.104 |
Token | It |
Token ID | 632 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
kit | +0.021 |
Stacy | +0.020 |
kettle | +0.019 |
groom | +0.018 |
cutter | +0.018 |
Neg logit contributions | |
ust | -0.021 |
ight | -0.019 |
all | -0.019 |
eternity | -0.018 |
uct | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ust | +0.012 |
ight | +0.011 |
adventure | +0.011 |
eternity | +0.010 |
all | +0.010 |
Neg logit contributions | |
Stacy | -0.013 |
kit | -0.012 |
kettle | -0.012 |
violet | -0.011 |
piping | -0.011 |
Token | not |
Token ID | 407 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
Stacy | +0.033 |
kit | +0.032 |
kettle | +0.030 |
sy | +0.030 |
violet | +0.029 |
Neg logit contributions | |
ust | -0.023 |
ight | -0.021 |
adventure | -0.021 |
eternity | -0.020 |
all | -0.019 |
Token | working |
Token ID | 1762 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ust | +0.079 |
ight | +0.072 |
adventure | +0.071 |
eternity | +0.068 |
all | +0.066 |
Neg logit contributions | |
Stacy | -0.106 |
kit | -0.105 |
kettle | -0.099 |
sy | -0.096 |
Grac | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
kit | +0.005 |
Stacy | +0.005 |
sy | +0.004 |
throat | +0.004 |
kettle | +0.004 |
Neg logit contributions | |
ust | -0.004 |
ight | -0.004 |
uct | -0.003 |
eternity | -0.003 |
adventure | -0.003 |
Token | You |
Token ID | 921 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
kit | +0.041 |
Stacy | +0.040 |
kettle | +0.038 |
tin | +0.037 |
violet | +0.036 |
Neg logit contributions | |
ust | -0.048 |
ight | -0.043 |
eternity | -0.042 |
all | -0.042 |
adventure | -0.042 |
Token | are |
Token ID | 389 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Stacy | +0.004 |
kit | +0.004 |
kettle | +0.004 |
violet | +0.004 |
piping | +0.004 |
Neg logit contributions | |
ust | -0.006 |
ight | -0.006 |
adventure | -0.006 |
all | -0.006 |
eternity | -0.006 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
Stacy | +0.053 |
kit | +0.051 |
kettle | +0.050 |
piping | +0.048 |
sy | +0.047 |
Neg logit contributions | |
ust | -0.036 |
ight | -0.033 |
adventure | -0.032 |
all | -0.030 |
eternity | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
kit | +0.137 |
Stacy | +0.128 |
sy | +0.121 |
Elsa | +0.121 |
te | +0.121 |
Neg logit contributions | |
ust | -0.112 |
ight | -0.099 |
eternity | -0.098 |
adventure | -0.095 |
all | -0.095 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ust | +0.014 |
adventure | +0.013 |
ight | +0.012 |
all | +0.011 |
eternity | +0.011 |
Neg logit contributions | |
Stacy | -0.018 |
kit | -0.018 |
kettle | -0.017 |
violet | -0.017 |
piping | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
kit | +0.217 |
Stacy | +0.214 |
kettle | +0.201 |
sy | +0.198 |
te | +0.196 |
Neg logit contributions | |
ust | -0.147 |
ight | -0.131 |
adventure | -0.128 |
eternity | -0.127 |
all | -0.123 |
Token | You |
Token ID | 921 |
Feature activation | +4.43e-04 |
Pos logit contributions | |
kit | +0.041 |
Stacy | +0.041 |
kettle | +0.038 |
tin | +0.037 |
violet | +0.037 |
Neg logit contributions | |
ust | -0.051 |
ight | -0.046 |
eternity | -0.045 |
adventure | -0.045 |
all | -0.045 |
Token | should |
Token ID | 815 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
Stacy | +0.001 |
kit | +0.001 |
kettle | +0.001 |
violet | +0.001 |
piping | +0.001 |
Neg logit contributions | |
ust | -0.001 |
adventure | -0.001 |
ight | -0.001 |
all | -0.001 |
anymore | -0.001 |
Token | love |
Token ID | 1842 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Stacy | +0.034 |
kit | +0.034 |
kettle | +0.031 |
Did | +0.030 |
sy | +0.030 |
Neg logit contributions | |
ust | -0.030 |
adventure | -0.028 |
ight | -0.027 |
eternity | -0.026 |
all | -0.025 |
Token | each |
Token ID | 1123 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
ust | +0.043 |
ight | +0.040 |
adventure | +0.039 |
eternity | +0.038 |
all | +0.036 |
Neg logit contributions | |
Stacy | -0.054 |
kit | -0.053 |
kettle | -0.050 |
sy | -0.049 |
Grac | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
kit | +0.033 |
Stacy | +0.032 |
kettle | +0.030 |
sy | +0.030 |
te | +0.030 |
Neg logit contributions | |
ust | -0.020 |
ight | -0.018 |
adventure | -0.017 |
eternity | -0.017 |
uct | -0.017 |
Token | We |
Token ID | 775 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
kit | +0.071 |
Stacy | +0.069 |
kettle | +0.067 |
tin | +0.063 |
violet | +0.063 |
Neg logit contributions | |
ust | -0.075 |
ight | -0.067 |
eternity | -0.066 |
adventure | -0.065 |
all | -0.065 |
Token | are |
Token ID | 389 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Stacy | +0.039 |
kit | +0.038 |
kettle | +0.035 |
sy | +0.034 |
violet | +0.034 |
Neg logit contributions | |
ust | -0.053 |
ight | -0.049 |
adventure | -0.049 |
eternity | -0.047 |
all | -0.046 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
Stacy | +0.043 |
kit | +0.043 |
kettle | +0.040 |
sy | +0.039 |
te | +0.039 |
Neg logit contributions | |
ust | -0.041 |
ight | -0.038 |
adventure | -0.037 |
eternity | -0.036 |
all | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
kit | +0.136 |
Stacy | +0.123 |
te | +0.122 |
sy | +0.120 |
Elsa | +0.120 |
Neg logit contributions | |
ust | -0.108 |
ight | -0.095 |
eternity | -0.094 |
uct | -0.094 |
all | -0.093 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
adventure | +0.014 |
ust | +0.014 |
unexpected | +0.012 |
eternity | +0.012 |
ight | +0.012 |
Neg logit contributions | |
Stacy | -0.016 |
kit | -0.016 |
kettle | -0.016 |
violet | -0.015 |
piping | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
kit | +0.224 |
Stacy | +0.214 |
kettle | +0.202 |
sy | +0.202 |
te | +0.202 |
Neg logit contributions | |
ust | -0.145 |
ight | -0.127 |
eternity | -0.123 |
all | -0.122 |
adventure | -0.120 |
Token | We |
Token ID | 775 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
kit | +0.053 |
Stacy | +0.052 |
kettle | +0.049 |
tin | +0.047 |
violet | +0.047 |
Neg logit contributions | |
ust | -0.062 |
ight | -0.056 |
adventure | -0.055 |
eternity | -0.055 |
all | -0.054 |
Token | should |
Token ID | 815 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Stacy | +0.037 |
kit | +0.036 |
kettle | +0.033 |
sy | +0.032 |
violet | +0.032 |
Neg logit contributions | |
ust | -0.049 |
ight | -0.045 |
adventure | -0.045 |
eternity | -0.043 |
all | -0.043 |
Token | share |
Token ID | 2648 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Stacy | +0.017 |
kit | +0.017 |
kettle | +0.016 |
sy | +0.015 |
Grac | +0.015 |
Neg logit contributions | |
ust | -0.018 |
adventure | -0.017 |
ight | -0.017 |
eternity | -0.016 |
all | -0.016 |
Token | our |
Token ID | 674 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
kit | +0.054 |
Elsa | +0.049 |
Stacy | +0.048 |
bottle | +0.048 |
dolls | +0.047 |
Neg logit contributions | |
ust | -0.068 |
ight | -0.061 |
rated | -0.060 |
uct | -0.057 |
eternity | -0.057 |
Token | help |
Token ID | 1037 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ust | +0.010 |
adventure | +0.009 |
ight | +0.009 |
eternity | +0.009 |
all | +0.009 |
Neg logit contributions | |
Stacy | -0.008 |
kit | -0.007 |
kettle | -0.007 |
violet | -0.007 |
sy | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
Stacy | +0.022 |
kit | +0.022 |
kettle | +0.020 |
sy | +0.020 |
Grac | +0.019 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.022 |
adventure | -0.022 |
eternity | -0.021 |
all | -0.021 |
Token | fixed |
Token ID | 5969 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
adventure | +0.057 |
ust | +0.050 |
all | +0.047 |
unexpected | +0.046 |
tomorrow | +0.046 |
Neg logit contributions | |
violet | -0.063 |
Stacy | -0.063 |
piping | -0.061 |
kettle | -0.061 |
kit | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
Stacy | +0.040 |
kit | +0.039 |
kettle | +0.037 |
sy | +0.036 |
Grac | +0.035 |
Neg logit contributions | |
ust | -0.038 |
ight | -0.035 |
adventure | -0.035 |
eternity | -0.034 |
all | -0.033 |
Token | cash |
Token ID | 5003 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ust | +0.025 |
adventure | +0.023 |
ight | +0.023 |
eternity | +0.022 |
all | +0.022 |
Neg logit contributions | |
Stacy | -0.019 |
kit | -0.018 |
kettle | -0.017 |
violet | -0.016 |
sy | -0.016 |
Token | register |
Token ID | 7881 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Stacy | +0.057 |
kit | +0.055 |
kettle | +0.054 |
violet | +0.053 |
Grac | +0.052 |
Neg logit contributions | |
ust | -0.032 |
ight | -0.029 |
adventure | -0.026 |
all | -0.026 |
eternity | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
Stacy | +0.244 |
kit | +0.234 |
kettle | +0.231 |
violet | +0.223 |
piping | +0.222 |
Neg logit contributions | |
ust | -0.113 |
ight | -0.102 |
adventure | -0.101 |
eternity | -0.092 |
all | -0.092 |
Token | The |
Token ID | 383 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
ust | +0.015 |
all | +0.014 |
ight | +0.013 |
uct | +0.013 |
eternity | +0.013 |
Neg logit contributions | |
kit | -0.013 |
Stacy | -0.012 |
kettle | -0.012 |
sy | -0.011 |
groom | -0.011 |
Token | shop |
Token ID | 6128 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
Stacy | +0.006 |
kit | +0.005 |
Did | +0.005 |
violet | +0.005 |
kettle | +0.005 |
Neg logit contributions | |
adventure | -0.008 |
ust | -0.007 |
ight | -0.007 |
unexpected | -0.007 |
next | -0.007 |
Token | keeper |
Token ID | 13884 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
Stacy | +0.107 |
violet | +0.099 |
piping | +0.098 |
kettle | +0.097 |
tul | +0.096 |
Neg logit contributions | |
ust | -0.065 |
adventure | -0.064 |
ight | -0.063 |
all | -0.057 |
happening | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -7.68e-04 |
Pos logit contributions | |
Stacy | +0.049 |
kit | +0.047 |
kettle | +0.045 |
violet | +0.043 |
piping | +0.042 |
Neg logit contributions | |
ust | -0.058 |
ight | -0.056 |
adventure | -0.056 |
eternity | -0.053 |
all | -0.053 |
Token | " |
Token ID | 366 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
Stacy | +0.026 |
kit | +0.025 |
kettle | +0.024 |
piping | +0.023 |
tin | +0.022 |
Neg logit contributions | |
all | -0.028 |
ust | -0.028 |
eternity | -0.027 |
happening | -0.027 |
adventure | -0.026 |
Token | You |
Token ID | 1639 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Stacy | +0.023 |
kit | +0.022 |
kettle | +0.021 |
sy | +0.020 |
Grac | +0.020 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.022 |
adventure | -0.021 |
all | -0.021 |
eternity | -0.021 |
Token | are |
Token ID | 389 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
Stacy | +0.017 |
kit | +0.017 |
kettle | +0.016 |
sy | +0.015 |
violet | +0.015 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.022 |
adventure | -0.022 |
eternity | -0.021 |
all | -0.021 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
Stacy | +0.058 |
kit | +0.058 |
kettle | +0.053 |
Elsa | +0.053 |
violet | +0.053 |
Neg logit contributions | |
ust | -0.048 |
ight | -0.043 |
adventure | -0.043 |
eternity | -0.043 |
all | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -7.85e-03 |
Pos logit contributions | |
kit | +0.122 |
Stacy | +0.117 |
kettle | +0.107 |
sy | +0.107 |
Elsa | +0.106 |
Neg logit contributions | |
ust | -0.116 |
ight | -0.104 |
eternity | -0.102 |
adventure | -0.102 |
all | -0.099 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
adventure | +0.011 |
ust | +0.011 |
eternity | +0.010 |
ight | +0.010 |
all | +0.010 |
Neg logit contributions | |
Stacy | -0.014 |
kit | -0.014 |
kettle | -0.014 |
violet | -0.013 |
Grac | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
Stacy | +0.232 |
kit | +0.229 |
kettle | +0.218 |
sy | +0.212 |
Grac | +0.210 |
Neg logit contributions | |
ust | -0.126 |
ight | -0.111 |
adventure | -0.110 |
eternity | -0.104 |
all | -0.101 |
Token | You |
Token ID | 921 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
kit | +0.063 |
kettle | +0.061 |
Stacy | +0.060 |
tin | +0.058 |
groom | +0.057 |
Neg logit contributions | |
ust | -0.057 |
eternity | -0.052 |
all | -0.052 |
adventure | -0.051 |
ight | -0.050 |
Token | should |
Token ID | 815 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Stacy | +0.004 |
kit | +0.004 |
kettle | +0.004 |
sy | +0.004 |
violet | +0.004 |
Neg logit contributions | |
ust | -0.006 |
ight | -0.006 |
adventure | -0.006 |
eternity | -0.005 |
all | -0.005 |
Token | love |
Token ID | 1842 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
Stacy | +0.026 |
kit | +0.025 |
kettle | +0.024 |
sy | +0.023 |
Grac | +0.023 |
Neg logit contributions | |
ust | -0.020 |
adventure | -0.019 |
ight | -0.018 |
all | -0.017 |
eternity | -0.017 |
Token | each |
Token ID | 1123 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
ust | +0.045 |
ight | +0.042 |
eternity | +0.038 |
adventure | +0.038 |
uct | +0.036 |
Neg logit contributions | |
Stacy | -0.064 |
kit | -0.064 |
kettle | -0.058 |
sy | -0.058 |
Elsa | -0.058 |
Token | ? |
Token ID | 30 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
kit | +0.047 |
Stacy | +0.042 |
bottle | +0.040 |
Elsa | +0.040 |
kettle | +0.040 |
Neg logit contributions | |
ust | -0.046 |
ight | -0.040 |
urious | -0.037 |
eternity | -0.037 |
uct | -0.036 |
Token | You |
Token ID | 921 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
kit | +0.069 |
Stacy | +0.069 |
groom | +0.069 |
kettle | +0.068 |
violet | +0.068 |
Neg logit contributions | |
all | -0.052 |
ust | -0.051 |
end | -0.048 |
eternity | -0.048 |
either | -0.047 |
Token | are |
Token ID | 389 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
Stacy | +0.010 |
kit | +0.010 |
kettle | +0.009 |
sy | +0.009 |
Grac | +0.009 |
Neg logit contributions | |
ust | -0.016 |
ight | -0.015 |
adventure | -0.015 |
eternity | -0.014 |
all | -0.014 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
Stacy | +0.045 |
kit | +0.044 |
kettle | +0.041 |
sy | +0.040 |
Elsa | +0.040 |
Neg logit contributions | |
ust | -0.038 |
ight | -0.035 |
adventure | -0.034 |
eternity | -0.033 |
all | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
kit | +0.138 |
Stacy | +0.126 |
kettle | +0.121 |
te | +0.121 |
sy | +0.121 |
Neg logit contributions | |
ust | -0.108 |
eternity | -0.094 |
ight | -0.093 |
all | -0.090 |
adventure | -0.089 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ust | +0.008 |
adventure | +0.008 |
happening | +0.007 |
ight | +0.006 |
unexpected | +0.006 |
Neg logit contributions | |
Stacy | -0.010 |
kit | -0.010 |
kettle | -0.010 |
violet | -0.010 |
Grac | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
kit | +0.216 |
Stacy | +0.204 |
kettle | +0.196 |
sy | +0.192 |
te | +0.192 |
Neg logit contributions | |
ust | -0.149 |
ight | -0.130 |
eternity | -0.128 |
adventure | -0.126 |
all | -0.124 |
Token | You |
Token ID | 921 |
Feature activation | +5.25e-04 |
Pos logit contributions | |
kit | +0.052 |
Stacy | +0.051 |
kettle | +0.049 |
tin | +0.048 |
violet | +0.047 |
Neg logit contributions | |
ust | -0.053 |
ight | -0.048 |
all | -0.048 |
eternity | -0.047 |
adventure | -0.047 |
Token | should |
Token ID | 815 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Stacy | +0.001 |
kit | +0.001 |
kettle | +0.001 |
sy | +0.001 |
Grac | +0.001 |
Neg logit contributions | |
ust | -0.001 |
ight | -0.001 |
adventure | -0.001 |
eternity | -0.001 |
all | -0.001 |
Token | share |
Token ID | 2648 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
Stacy | +0.029 |
kit | +0.029 |
kettle | +0.027 |
sy | +0.026 |
Grac | +0.026 |
Neg logit contributions | |
ust | -0.030 |
adventure | -0.028 |
ight | -0.027 |
eternity | -0.026 |
all | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
kit | +0.052 |
Stacy | +0.051 |
Elsa | +0.047 |
te | +0.047 |
sy | +0.046 |
Neg logit contributions | |
ust | -0.058 |
ight | -0.052 |
eternity | -0.051 |
adventure | -0.049 |
rated | -0.049 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
Stacy | +0.058 |
kit | +0.057 |
kettle | +0.054 |
sy | +0.052 |
Grac | +0.051 |
Neg logit contributions | |
ust | -0.048 |
ight | -0.044 |
adventure | -0.043 |
eternity | -0.042 |
all | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
Stacy | +0.006 |
kit | +0.006 |
kettle | +0.005 |
sy | +0.005 |
Grac | +0.005 |
Neg logit contributions | |
ust | -0.003 |
ight | -0.003 |
adventure | -0.003 |
eternity | -0.003 |
all | -0.003 |
Token | be |
Token ID | 307 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Stacy | +0.011 |
kit | +0.011 |
kettle | +0.010 |
tin | +0.010 |
sy | +0.010 |
Neg logit contributions | |
ust | -0.013 |
adventure | -0.012 |
eternity | -0.012 |
ight | -0.011 |
all | -0.011 |
Token | brother |
Token ID | 3956 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
kit | +0.044 |
Stacy | +0.043 |
kettle | +0.040 |
sy | +0.039 |
Grac | +0.039 |
Neg logit contributions | |
ust | -0.043 |
ight | -0.039 |
adventure | -0.038 |
eternity | -0.038 |
all | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
kit | +0.114 |
Stacy | +0.102 |
Elsa | +0.100 |
te | +0.097 |
sy | +0.097 |
Neg logit contributions | |
ust | -0.098 |
eternity | -0.086 |
ight | -0.085 |
all | -0.085 |
uct | -0.084 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
adventure | +0.017 |
ust | +0.013 |
exciting | +0.013 |
tomorrow | +0.012 |
next | +0.012 |
Neg logit contributions | |
Stacy | -0.020 |
piping | -0.019 |
kettle | -0.018 |
violet | -0.018 |
acey | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
kit | +0.215 |
Stacy | +0.202 |
te | +0.193 |
Elsa | +0.191 |
kettle | +0.190 |
Neg logit contributions | |
ust | -0.151 |
ight | -0.130 |
eternity | -0.130 |
all | -0.127 |
uct | -0.120 |
Token | They |
Token ID | 1119 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
kit | +0.039 |
Stacy | +0.039 |
kettle | +0.034 |
sy | +0.034 |
tin | +0.032 |
Neg logit contributions | |
ust | -0.079 |
adventure | -0.074 |
ight | -0.073 |
eternity | -0.072 |
all | -0.071 |
Token | did |
Token ID | 750 |
Feature activation | +5.85e-03 |
Pos logit contributions | |
Stacy | +0.056 |
kit | +0.056 |
kettle | +0.052 |
sy | +0.050 |
piping | +0.050 |
Neg logit contributions | |
ust | -0.061 |
adventure | -0.058 |
ight | -0.056 |
eternity | -0.053 |
all | -0.052 |
Token | not |
Token ID | 407 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
Stacy | +0.009 |
kit | +0.009 |
violet | +0.008 |
Elsa | +0.008 |
brush | +0.008 |
Neg logit contributions | |
ust | -0.010 |
ight | -0.009 |
adventure | -0.009 |
eternity | -0.009 |
ach | -0.008 |
Token | want |
Token ID | 765 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
ust | +0.130 |
ight | +0.122 |
adventure | +0.116 |
eternity | +0.116 |
all | +0.116 |
Neg logit contributions | |
Stacy | -0.104 |
kit | -0.104 |
kettle | -0.094 |
brush | -0.093 |
sy | -0.092 |
Token | ided |
Token ID | 1384 |
Feature activation | +6.08e-04 |
Pos logit contributions | |
ust | +0.033 |
ight | +0.030 |
all | +0.029 |
anymore | +0.028 |
eternity | +0.027 |
Neg logit contributions | |
kettle | -0.051 |
Stacy | -0.050 |
te | -0.047 |
kit | -0.047 |
tin | -0.047 |
Token | it |
Token ID | 340 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
Stacy | +0.001 |
kit | +0.001 |
kettle | +0.001 |
sy | +0.001 |
violet | +0.001 |
Neg logit contributions | |
adventure | -0.001 |
ust | -0.001 |
all | -0.001 |
ight | -0.001 |
anymore | -0.001 |
Token | into |
Token ID | 656 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.017 |
adventure | +0.016 |
eternity | +0.016 |
all | +0.015 |
Neg logit contributions | |
Stacy | -0.029 |
kit | -0.029 |
kettle | -0.027 |
sy | -0.027 |
Grac | -0.026 |
Token | two |
Token ID | 734 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
kit | +0.069 |
Stacy | +0.068 |
kettle | +0.065 |
sy | +0.063 |
Did | +0.062 |
Neg logit contributions | |
ust | -0.058 |
adventure | -0.055 |
ight | -0.053 |
eternity | -0.051 |
unexpected | -0.050 |
Token | pig |
Token ID | 12967 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
Stacy | +0.100 |
kit | +0.099 |
kettle | +0.093 |
sy | +0.090 |
tin | +0.089 |
Neg logit contributions | |
ust | -0.092 |
ight | -0.084 |
adventure | -0.083 |
eternity | -0.081 |
all | -0.079 |
Token | tails |
Token ID | 26404 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Stacy | +0.017 |
piping | +0.015 |
kit | +0.015 |
kettle | +0.014 |
Did | +0.014 |
Neg logit contributions | |
ust | -0.042 |
adventure | -0.041 |
ight | -0.039 |
all | -0.038 |
anymore | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
Stacy | +0.273 |
kit | +0.264 |
kettle | +0.254 |
piping | +0.253 |
sy | +0.252 |
Neg logit contributions | |
ust | -0.079 |
adventure | -0.073 |
ight | -0.072 |
eternity | -0.063 |
anymore | -0.062 |
Token | |
Token ID | 220 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
all | +0.024 |
ust | +0.024 |
anymore | +0.024 |
eternity | +0.023 |
adventure | +0.023 |
Neg logit contributions | |
kit | -0.052 |
Stacy | -0.050 |
kettle | -0.049 |
sy | -0.049 |
groom | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
ust | +0.004 |
adventure | +0.003 |
ight | +0.003 |
eternity | +0.003 |
all | +0.003 |
Neg logit contributions | |
Stacy | -0.003 |
kit | -0.003 |
kettle | -0.003 |
Grac | -0.003 |
Elsa | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
ust | +0.062 |
ight | +0.057 |
adventure | +0.056 |
eternity | +0.054 |
all | +0.052 |
Neg logit contributions | |
Stacy | -0.057 |
kit | -0.055 |
kettle | -0.051 |
Grac | -0.049 |
Elsa | -0.049 |
Token | One |
Token ID | 3198 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ust | +0.042 |
ight | +0.037 |
adventure | +0.037 |
eternity | +0.035 |
all | +0.034 |
Neg logit contributions | |
Stacy | -0.066 |
kit | -0.065 |
kettle | -0.061 |
sy | -0.060 |
Grac | -0.059 |
Token | her |
Token ID | 607 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
Stacy | +0.012 |
kit | +0.012 |
kettle | +0.011 |
tin | +0.011 |
sy | +0.011 |
Neg logit contributions | |
ust | -0.011 |
ight | -0.009 |
adventure | -0.009 |
eternity | -0.009 |
all | -0.009 |
Token | legs |
Token ID | 7405 |
Feature activation | +6.66e-03 |
Pos logit contributions | |
kit | +0.007 |
Stacy | +0.006 |
brush | +0.006 |
bottle | +0.006 |
te | +0.006 |
Neg logit contributions | |
ust | -0.010 |
ight | -0.009 |
eternity | -0.009 |
all | -0.009 |
uct | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
kit | +0.012 |
Stacy | +0.012 |
tin | +0.011 |
brush | +0.011 |
cutter | +0.011 |
Neg logit contributions | |
ust | -0.010 |
eternity | -0.009 |
ight | -0.009 |
adventure | -0.009 |
uct | -0.008 |
Token | kick |
Token ID | 4829 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
adventure | +0.021 |
ust | +0.018 |
behind | +0.018 |
eternity | +0.017 |
all | +0.017 |
Neg logit contributions | |
Stacy | -0.028 |
kettle | -0.028 |
kit | -0.027 |
acey | -0.026 |
piping | -0.026 |
Token | out |
Token ID | 503 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
ust | +0.016 |
adventure | +0.014 |
ight | +0.014 |
eternity | +0.013 |
all | +0.013 |
Neg logit contributions | |
Stacy | -0.022 |
kit | -0.022 |
kettle | -0.021 |
sy | -0.020 |
violet | -0.020 |
Token | wards |
Token ID | 2017 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Stacy | +0.063 |
kit | +0.063 |
kettle | +0.060 |
sy | +0.057 |
violet | +0.057 |
Neg logit contributions | |
ust | -0.042 |
ight | -0.038 |
adventure | -0.038 |
all | -0.036 |
eternity | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Stacy | +0.241 |
kit | +0.237 |
kettle | +0.232 |
piping | +0.229 |
violet | +0.227 |
Neg logit contributions | |
adventure | -0.098 |
ust | -0.096 |
ight | -0.084 |
all | -0.083 |
eternity | -0.081 |
Token |
|
Token ID | 198 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ust | +0.017 |
all | +0.016 |
adventure | +0.015 |
ax | +0.015 |
ight | +0.014 |
Neg logit contributions | |
kit | -0.021 |
kettle | -0.020 |
sy | -0.019 |
piping | -0.019 |
tul | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
ust | +0.041 |
ight | +0.037 |
adventure | +0.037 |
eternity | +0.036 |
all | +0.035 |
Neg logit contributions | |
Stacy | -0.043 |
kit | -0.042 |
kettle | -0.039 |
sy | -0.038 |
Grac | -0.038 |
Token | Finally |
Token ID | 11158 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
ust | +0.034 |
ight | +0.031 |
adventure | +0.031 |
eternity | +0.030 |
all | +0.029 |
Neg logit contributions | |
Stacy | -0.039 |
kit | -0.038 |
kettle | -0.036 |
sy | -0.035 |
violet | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
kit | +0.058 |
Stacy | +0.057 |
kettle | +0.057 |
sy | +0.056 |
violet | +0.055 |
Neg logit contributions | |
adventure | -0.032 |
ust | -0.030 |
eternity | -0.029 |
all | -0.028 |
anymore | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | -9.36e-03 |
Pos logit contributions | |
Stacy | +0.012 |
kit | +0.012 |
kettle | +0.011 |
sy | +0.011 |
violet | +0.011 |
Neg logit contributions | |
ust | -0.006 |
ight | -0.006 |
adventure | -0.006 |
eternity | -0.005 |
all | -0.005 |
Token | display |
Token ID | 3359 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
ust | +0.011 |
adventure | +0.011 |
ight | +0.010 |
eternity | +0.010 |
all | +0.010 |
Neg logit contributions | |
kit | -0.019 |
Stacy | -0.019 |
kettle | -0.018 |
sy | -0.018 |
Did | -0.018 |
Token | near |
Token ID | 1474 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
Stacy | +0.061 |
kit | +0.061 |
kettle | +0.058 |
sy | +0.056 |
Grac | +0.056 |
Neg logit contributions | |
ust | -0.031 |
ight | -0.028 |
adventure | -0.027 |
eternity | -0.026 |
all | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
ust | +0.033 |
ight | +0.030 |
adventure | +0.030 |
eternity | +0.029 |
all | +0.028 |
Neg logit contributions | |
Stacy | -0.038 |
kit | -0.038 |
kettle | -0.036 |
sy | -0.035 |
violet | -0.034 |
Token | cash |
Token ID | 5003 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
adventure | +0.053 |
ust | +0.051 |
ight | +0.049 |
anymore | +0.048 |
unexpected | +0.048 |
Neg logit contributions | |
Stacy | -0.045 |
kit | -0.042 |
Did | -0.039 |
violet | -0.038 |
kettle | -0.038 |
Token | register |
Token ID | 7881 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Stacy | +0.039 |
kit | +0.038 |
kettle | +0.036 |
Grac | +0.035 |
sy | +0.035 |
Neg logit contributions | |
ust | -0.029 |
ight | -0.026 |
adventure | -0.026 |
eternity | -0.025 |
all | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
Stacy | +0.255 |
kit | +0.247 |
kettle | +0.240 |
sy | +0.235 |
violet | +0.233 |
Neg logit contributions | |
ust | -0.096 |
adventure | -0.086 |
ight | -0.084 |
eternity | -0.075 |
all | -0.074 |
Token | They |
Token ID | 1119 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ust | +0.012 |
uct | +0.011 |
anymore | +0.011 |
ight | +0.011 |
all | +0.011 |
Neg logit contributions | |
kit | -0.012 |
Stacy | -0.012 |
sy | -0.011 |
kettle | -0.011 |
groom | -0.011 |
Token | looked |
Token ID | 3114 |
Feature activation | -5.29e-04 |
Pos logit contributions | |
kit | +0.029 |
Stacy | +0.029 |
kettle | +0.027 |
sy | +0.027 |
Elsa | +0.026 |
Neg logit contributions | |
ust | -0.023 |
adventure | -0.022 |
ight | -0.021 |
uct | -0.020 |
all | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ust | +0.001 |
ight | +0.001 |
adventure | +0.001 |
eternity | +0.001 |
all | +0.001 |
Neg logit contributions | |
Stacy | -0.001 |
kit | -0.001 |
kettle | -0.001 |
Grac | -0.001 |
tin | -0.001 |
Token | y |
Token ID | 331 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
te | +0.024 |
Grac | +0.023 |
tin | +0.023 |
Stacy | +0.023 |
lav | +0.023 |
Neg logit contributions | |
ust | -0.033 |
eternity | -0.032 |
iver | -0.032 |
all | -0.032 |
ight | -0.031 |
Token | Max |
Token ID | 5436 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
ust | +0.022 |
adventure | +0.021 |
eternity | +0.020 |
ight | +0.020 |
all | +0.019 |
Neg logit contributions | |
kit | -0.027 |
Stacy | -0.026 |
kettle | -0.026 |
piping | -0.025 |
tin | -0.024 |
Token | were |
Token ID | 547 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
Stacy | +0.009 |
kit | +0.009 |
kettle | +0.008 |
sy | +0.008 |
piping | +0.008 |
Neg logit contributions | |
ust | -0.011 |
adventure | -0.010 |
ight | -0.010 |
eternity | -0.010 |
anymore | -0.010 |
Token | normal |
Token ID | 3487 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
kit | +0.056 |
Stacy | +0.056 |
kettle | +0.054 |
sy | +0.053 |
tin | +0.051 |
Neg logit contributions | |
ust | -0.038 |
adventure | -0.035 |
ight | -0.034 |
all | -0.032 |
anymore | -0.031 |
Token | brother |
Token ID | 3956 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
kit | +0.039 |
Stacy | +0.038 |
kettle | +0.036 |
te | +0.035 |
sy | +0.035 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.021 |
adventure | -0.020 |
eternity | -0.020 |
uct | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
kit | +0.127 |
Stacy | +0.122 |
Elsa | +0.114 |
te | +0.114 |
kettle | +0.113 |
Neg logit contributions | |
ust | -0.089 |
ight | -0.078 |
eternity | -0.077 |
uct | -0.074 |
all | -0.074 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
adventure | +0.021 |
ust | +0.018 |
exciting | +0.017 |
happening | +0.016 |
behind | +0.016 |
Neg logit contributions | |
piping | -0.025 |
Stacy | -0.024 |
kettle | -0.024 |
violet | -0.023 |
kit | -0.022 |
Token | again |
Token ID | 757 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
Stacy | +0.242 |
kit | +0.236 |
kettle | +0.228 |
sy | +0.222 |
violet | +0.221 |
Neg logit contributions | |
ust | -0.107 |
adventure | -0.095 |
ight | -0.094 |
eternity | -0.086 |
all | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
Stacy | +0.022 |
kit | +0.022 |
kettle | +0.021 |
sy | +0.020 |
violet | +0.020 |
Neg logit contributions | |
ust | -0.011 |
ight | -0.009 |
adventure | -0.009 |
eternity | -0.009 |
all | -0.008 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
kit | +0.019 |
Stacy | +0.018 |
kettle | +0.017 |
tin | +0.017 |
sy | +0.017 |
Neg logit contributions | |
ust | -0.017 |
adventure | -0.015 |
anymore | -0.015 |
ight | -0.015 |
eternity | -0.015 |
Token | Tim |
Token ID | 14967 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
ust | +0.046 |
ight | +0.041 |
eternity | +0.041 |
adventure | +0.040 |
rated | +0.039 |
Neg logit contributions | |
kit | -0.026 |
Stacy | -0.025 |
Elsa | -0.022 |
kettle | -0.021 |
te | -0.021 |
Token | had |
Token ID | 550 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
ust | +0.034 |
ight | +0.031 |
adventure | +0.030 |
eternity | +0.030 |
all | +0.029 |
Neg logit contributions | |
Stacy | -0.039 |
kit | -0.039 |
kettle | -0.036 |
sy | -0.035 |
tin | -0.035 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
kit | +0.048 |
Stacy | +0.048 |
kettle | +0.045 |
piping | +0.043 |
Did | +0.043 |
Neg logit contributions | |
ust | -0.054 |
adventure | -0.052 |
ight | -0.049 |
eternity | -0.049 |
all | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
Stacy | +0.093 |
kit | +0.093 |
kettle | +0.087 |
sy | +0.085 |
tin | +0.085 |
Neg logit contributions | |
ust | -0.047 |
ight | -0.041 |
adventure | -0.040 |
eternity | -0.038 |
all | -0.037 |
Token | You |
Token ID | 921 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
kettle | +0.098 |
kit | +0.097 |
Stacy | +0.096 |
groom | +0.095 |
tin | +0.091 |
Neg logit contributions | |
ust | -0.060 |
all | -0.057 |
eternity | -0.056 |
adventure | -0.054 |
ight | -0.051 |
Token | are |
Token ID | 389 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
Stacy | +0.025 |
kit | +0.024 |
kettle | +0.023 |
sy | +0.023 |
piping | +0.022 |
Neg logit contributions | |
ust | -0.026 |
adventure | -0.025 |
ight | -0.025 |
unexpected | -0.023 |
wing | -0.023 |
Token | my |
Token ID | 616 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
Stacy | +0.050 |
kit | +0.049 |
kettle | +0.047 |
sy | +0.046 |
Did | +0.044 |
Neg logit contributions | |
ust | -0.040 |
adventure | -0.037 |
ight | -0.037 |
all | -0.034 |
eternity | -0.033 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Stacy | +0.055 |
kit | +0.053 |
kettle | +0.051 |
Did | +0.049 |
piping | +0.048 |
Neg logit contributions | |
ust | -0.061 |
adventure | -0.057 |
ight | -0.055 |
anymore | -0.051 |
eternity | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -9.12e-03 |
Pos logit contributions | |
kit | +0.229 |
Stacy | +0.228 |
kettle | +0.214 |
sy | +0.210 |
Elsa | +0.208 |
Neg logit contributions | |
ust | -0.119 |
ight | -0.104 |
adventure | -0.101 |
eternity | -0.098 |
all | -0.094 |
Token | I |
Token ID | 314 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
adventure | +0.012 |
ust | +0.011 |
exciting | +0.010 |
unexpected | +0.010 |
happening | +0.009 |
Neg logit contributions | |
kettle | -0.017 |
kit | -0.017 |
Stacy | -0.017 |
piping | -0.017 |
nozzle | -0.016 |
Token | love |
Token ID | 1842 |
Feature activation | -3.95e-03 |
Pos logit contributions | |
Stacy | +0.096 |
kit | +0.089 |
kettle | +0.088 |
violet | +0.087 |
piping | +0.086 |
Neg logit contributions | |
ust | -0.076 |
adventure | -0.070 |
ight | -0.066 |
anymore | -0.064 |
all | -0.064 |
Token | you |
Token ID | 345 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ust | +0.005 |
ight | +0.004 |
adventure | +0.004 |
eternity | +0.004 |
all | +0.004 |
Neg logit contributions | |
Stacy | -0.009 |
kit | -0.009 |
kettle | -0.008 |
sy | -0.008 |
violet | -0.008 |
Token | too |
Token ID | 1165 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
ust | +0.014 |
ight | +0.013 |
adventure | +0.013 |
eternity | +0.012 |
all | +0.012 |
Neg logit contributions | |
Stacy | -0.025 |
kit | -0.025 |
kettle | -0.024 |
Elsa | -0.023 |
sy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
kit | +0.018 |
Stacy | +0.018 |
Elsa | +0.017 |
te | +0.017 |
sy | +0.017 |
Neg logit contributions | |
ust | -0.015 |
eternity | -0.013 |
unexpected | -0.013 |
adventure | -0.013 |
ach | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
kit | +0.054 |
Stacy | +0.053 |
kettle | +0.050 |
sy | +0.048 |
Grac | +0.048 |
Neg logit contributions | |
ust | -0.047 |
adventure | -0.044 |
ight | -0.042 |
eternity | -0.042 |
all | -0.042 |
Token | You |
Token ID | 1639 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
Stacy | +0.021 |
kit | +0.020 |
sy | +0.019 |
kettle | +0.018 |
tin | +0.018 |
Neg logit contributions | |
ust | -0.028 |
adventure | -0.027 |
ight | -0.027 |
eternity | -0.026 |
anymore | -0.025 |
Token | are |
Token ID | 389 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
kit | +0.007 |
Stacy | +0.006 |
kettle | +0.006 |
sy | +0.005 |
Grac | +0.005 |
Neg logit contributions | |
ust | -0.014 |
ight | -0.013 |
eternity | -0.013 |
adventure | -0.013 |
all | -0.013 |
Token | my |
Token ID | 616 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
kit | +0.058 |
Stacy | +0.057 |
Elsa | +0.053 |
violet | +0.052 |
te | +0.051 |
Neg logit contributions | |
ust | -0.052 |
eternity | -0.047 |
ight | -0.046 |
adventure | -0.045 |
urious | -0.044 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Stacy | +0.054 |
kit | +0.054 |
kettle | +0.049 |
sy | +0.047 |
te | +0.047 |
Neg logit contributions | |
ust | -0.070 |
ight | -0.066 |
adventure | -0.064 |
eternity | -0.063 |
all | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -8.09e-03 |
Pos logit contributions | |
kit | +0.202 |
Stacy | +0.182 |
sy | +0.177 |
Elsa | +0.175 |
te | +0.175 |
Neg logit contributions | |
ust | -0.157 |
ight | -0.137 |
eternity | -0.136 |
uct | -0.133 |
all | -0.131 |
Token | I |
Token ID | 314 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
ust | +0.011 |
adventure | +0.011 |
ight | +0.010 |
eternity | +0.010 |
all | +0.010 |
Neg logit contributions | |
kit | -0.015 |
Stacy | -0.014 |
kettle | -0.014 |
sy | -0.013 |
Grac | -0.013 |
Token | will |
Token ID | 481 |
Feature activation | +7.59e-03 |
Pos logit contributions | |
Stacy | +0.049 |
kit | +0.048 |
kettle | +0.043 |
sy | +0.040 |
violet | +0.040 |
Neg logit contributions | |
ust | -0.108 |
ight | -0.101 |
adventure | -0.101 |
eternity | -0.098 |
all | -0.097 |
Token | always |
Token ID | 1464 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
Stacy | +0.011 |
kit | +0.011 |
kettle | +0.010 |
sy | +0.010 |
Grac | +0.010 |
Neg logit contributions | |
ust | -0.014 |
ight | -0.013 |
adventure | -0.013 |
eternity | -0.012 |
all | -0.012 |
Token | protect |
Token ID | 1805 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
kit | +0.013 |
Stacy | +0.012 |
brush | +0.012 |
tin | +0.011 |
sy | +0.011 |
Neg logit contributions | |
ust | -0.019 |
ight | -0.018 |
eternity | -0.017 |
all | -0.016 |
uct | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ust | +0.027 |
adventure | +0.026 |
ight | +0.025 |
eternity | +0.024 |
all | +0.023 |
Neg logit contributions | |
Stacy | -0.027 |
kit | -0.026 |
kettle | -0.024 |
Grac | -0.024 |
violet | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
Stacy | +0.046 |
kit | +0.046 |
kettle | +0.043 |
sy | +0.042 |
tin | +0.042 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.021 |
adventure | -0.021 |
eternity | -0.020 |
all | -0.019 |
Token | dad |
Token ID | 9955 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
adventure | +0.014 |
ust | +0.013 |
eternity | +0.011 |
ight | +0.011 |
all | +0.011 |
Neg logit contributions | |
Stacy | -0.022 |
violet | -0.022 |
kettle | -0.021 |
kit | -0.021 |
Grac | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
kit | +0.031 |
Stacy | +0.031 |
kettle | +0.029 |
sy | +0.029 |
tin | +0.028 |
Neg logit contributions | |
ust | -0.019 |
ight | -0.017 |
adventure | -0.016 |
eternity | -0.016 |
all | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
adventure | +0.023 |
ust | +0.022 |
eternity | +0.019 |
behind | +0.019 |
ight | +0.019 |
Neg logit contributions | |
Stacy | -0.030 |
violet | -0.029 |
kettle | -0.028 |
kit | -0.028 |
piping | -0.027 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Stacy | +0.017 |
kit | +0.016 |
kettle | +0.015 |
Grac | +0.015 |
violet | +0.015 |
Neg logit contributions | |
ust | -0.020 |
adventure | -0.020 |
ight | -0.018 |
eternity | -0.018 |
all | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
kit | +0.223 |
Stacy | +0.221 |
kettle | +0.208 |
sy | +0.205 |
tin | +0.201 |
Neg logit contributions | |
ust | -0.125 |
ight | -0.109 |
adventure | -0.105 |
eternity | -0.102 |
all | -0.100 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e-04 |
Pos logit contributions | |
kit | +0.045 |
Stacy | +0.044 |
kettle | +0.042 |
violet | +0.041 |
sy | +0.040 |
Neg logit contributions | |
ust | -0.039 |
adventure | -0.035 |
ight | -0.034 |
all | -0.033 |
eternity | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
ust | +0.001 |
ight | +0.001 |
adventure | +0.001 |
eternity | +0.001 |
rated | +0.001 |
Neg logit contributions | |
Stacy | -0.001 |
kit | -0.001 |
kettle | -0.001 |
Elsa | -0.001 |
Grac | -0.001 |
Token | Ben |
Token ID | 11696 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
Stacy | +0.003 |
kit | +0.002 |
kettle | +0.002 |
sy | +0.002 |
tin | +0.002 |
Neg logit contributions | |
ust | -0.002 |
adventure | -0.002 |
ight | -0.002 |
eternity | -0.002 |
all | -0.002 |
Token | nodded |
Token ID | 14464 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
Stacy | +0.017 |
kit | +0.017 |
kettle | +0.016 |
sy | +0.015 |
te | +0.015 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.022 |
adventure | -0.022 |
eternity | -0.022 |
all | -0.021 |
Token | find |
Token ID | 1064 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
Stacy | +0.031 |
kit | +0.030 |
kettle | +0.028 |
sy | +0.027 |
Elsa | +0.027 |
Neg logit contributions | |
ust | -0.033 |
adventure | -0.031 |
ight | -0.030 |
eternity | -0.029 |
all | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
ust | +0.005 |
ight | +0.004 |
eternity | +0.004 |
adventure | +0.004 |
all | +0.004 |
Neg logit contributions | |
kit | -0.006 |
Stacy | -0.006 |
tin | -0.006 |
kettle | -0.006 |
Grac | -0.006 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
adventure | +0.052 |
ust | +0.044 |
eternity | +0.043 |
exciting | +0.042 |
behind | +0.042 |
Neg logit contributions | |
Stacy | -0.066 |
kit | -0.064 |
kettle | -0.063 |
sy | -0.061 |
violet | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-03 |
Pos logit contributions | |
ust | +0.030 |
ight | +0.027 |
eternity | +0.025 |
adventure | +0.025 |
all | +0.024 |
Neg logit contributions | |
Stacy | -0.040 |
kit | -0.040 |
kettle | -0.037 |
Grac | -0.037 |
tin | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Stacy | +0.002 |
kit | +0.002 |
kettle | +0.002 |
sy | +0.002 |
Grac | +0.002 |
Neg logit contributions | |
ust | -0.002 |
ight | -0.002 |
adventure | -0.002 |
eternity | -0.001 |
all | -0.001 |
Token | register |
Token ID | 7881 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ust | +0.039 |
adventure | +0.039 |
ight | +0.037 |
eternity | +0.035 |
unexpected | +0.035 |
Neg logit contributions | |
Stacy | -0.036 |
kit | -0.035 |
kettle | -0.032 |
sy | -0.032 |
Did | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
Stacy | +0.253 |
kit | +0.240 |
kettle | +0.238 |
violet | +0.236 |
sy | +0.235 |
Neg logit contributions | |
ust | -0.088 |
adventure | -0.083 |
ight | -0.076 |
all | -0.068 |
anymore | -0.068 |
Token | His |
Token ID | 2399 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
ust | +0.025 |
all | +0.023 |
ight | +0.023 |
eternity | +0.023 |
adventure | +0.022 |
Neg logit contributions | |
kit | -0.028 |
Stacy | -0.028 |
kettle | -0.027 |
sy | -0.027 |
tul | -0.026 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ust | +0.012 |
adventure | +0.012 |
ight | +0.011 |
eternity | +0.011 |
all | +0.010 |
Neg logit contributions | |
Stacy | -0.012 |
kit | -0.012 |
kettle | -0.011 |
sy | -0.011 |
Grac | -0.011 |
Token | paid |
Token ID | 3432 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
Stacy | +0.054 |
kit | +0.051 |
kettle | +0.050 |
sy | +0.050 |
violet | +0.050 |
Neg logit contributions | |
ust | -0.046 |
ight | -0.045 |
adventure | -0.045 |
all | -0.043 |
uct | -0.040 |
Token | for |
Token ID | 329 |
Feature activation | -6.42e-04 |
Pos logit contributions | |
kit | +0.048 |
Stacy | +0.047 |
Grac | +0.041 |
Elsa | +0.041 |
tin | +0.039 |
Neg logit contributions | |
ust | -0.062 |
urious | -0.054 |
iver | -0.053 |
ight | -0.052 |
rated | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
Stacy | +0.000 |
kit | +0.000 |
kettle | +0.000 |
Grac | +0.000 |
Did | +0.000 |
Neg logit contributions | |
ust | -0.001 |
ight | -0.001 |
adventure | -0.001 |
eternity | -0.001 |
rated | -0.001 |
Token | Sam |
Token ID | 16305 |
Feature activation | -7.10e-03 |
Pos logit contributions | |
Stacy | +0.003 |
kit | +0.003 |
kettle | +0.003 |
sy | +0.002 |
Grac | +0.002 |
Neg logit contributions | |
ust | -0.002 |
ight | -0.001 |
adventure | -0.001 |
eternity | -0.001 |
all | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ust | +0.012 |
ight | +0.011 |
adventure | +0.010 |
eternity | +0.010 |
all | +0.010 |
Neg logit contributions | |
Stacy | -0.012 |
kit | -0.012 |
kettle | -0.011 |
sy | -0.011 |
Grac | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Stacy | +0.073 |
kit | +0.069 |
kettle | +0.065 |
Grac | +0.065 |
sy | +0.063 |
Neg logit contributions | |
ust | -0.071 |
adventure | -0.071 |
ight | -0.067 |
eternity | -0.064 |
anymore | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
Stacy | +0.068 |
kit | +0.065 |
kettle | +0.062 |
Grac | +0.061 |
sy | +0.059 |
Neg logit contributions | |
ight | -0.071 |
ust | -0.071 |
adventure | -0.069 |
eternity | -0.066 |
all | -0.065 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
adventure | +0.021 |
ust | +0.020 |
eternity | +0.018 |
ight | +0.018 |
all | +0.017 |
Neg logit contributions | |
Stacy | -0.031 |
kit | -0.030 |
kettle | -0.029 |
violet | -0.029 |
Grac | -0.028 |
Token | are |
Token ID | 389 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
Stacy | +0.192 |
kit | +0.187 |
kettle | +0.180 |
sy | +0.173 |
violet | +0.173 |
Neg logit contributions | |
ust | -0.146 |
adventure | -0.139 |
ight | -0.139 |
eternity | -0.130 |
anymore | -0.129 |
Token | angry |
Token ID | 7954 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
Stacy | +0.040 |
kit | +0.038 |
kettle | +0.037 |
violet | +0.036 |
Did | +0.036 |
Neg logit contributions | |
ust | -0.027 |
ight | -0.025 |
adventure | -0.024 |
happening | -0.023 |
all | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
ust | +0.067 |
rated | +0.061 |
ight | +0.060 |
uct | +0.059 |
adventure | +0.058 |
Neg logit contributions | |
kit | -0.058 |
Stacy | -0.054 |
sisters | -0.053 |
te | -0.052 |
Did | -0.051 |
Token | They |
Token ID | 1119 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
kit | +0.043 |
Stacy | +0.042 |
kettle | +0.038 |
piping | +0.037 |
sy | +0.037 |
Neg logit contributions | |
ust | -0.079 |
adventure | -0.075 |
ight | -0.073 |
eternity | -0.073 |
anymore | -0.072 |
Token | run |
Token ID | 1057 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
Stacy | +0.041 |
kit | +0.041 |
kettle | +0.038 |
sy | +0.036 |
Grac | +0.036 |
Neg logit contributions | |
ust | -0.048 |
ight | -0.044 |
adventure | -0.044 |
eternity | -0.042 |
all | -0.042 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
ust | +0.006 |
adventure | +0.006 |
eternity | +0.006 |
ight | +0.005 |
all | +0.005 |
Neg logit contributions | |
kit | -0.007 |
Stacy | -0.007 |
sy | -0.006 |
kettle | -0.006 |
violet | -0.006 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ust | +0.009 |
ight | +0.008 |
adventure | +0.008 |
eternity | +0.008 |
all | +0.008 |
Neg logit contributions | |
Stacy | -0.007 |
kit | -0.007 |
kettle | -0.006 |
te | -0.006 |
sy | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ust | +0.043 |
ight | +0.039 |
adventure | +0.037 |
eternity | +0.037 |
all | +0.036 |
Neg logit contributions | |
Stacy | -0.043 |
kit | -0.042 |
kettle | -0.039 |
Grac | -0.037 |
sy | -0.037 |
Token | weather |
Token ID | 6193 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
ust | +0.027 |
ight | +0.025 |
adventure | +0.024 |
eternity | +0.024 |
all | +0.023 |
Neg logit contributions | |
Stacy | -0.024 |
kit | -0.024 |
kettle | -0.022 |
sy | -0.022 |
tin | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ust | +0.052 |
ight | +0.046 |
adventure | +0.045 |
eternity | +0.045 |
all | +0.042 |
Neg logit contributions | |
kit | -0.053 |
Stacy | -0.052 |
kettle | -0.050 |
tin | -0.048 |
te | -0.047 |
Token | uncom |
Token ID | 8820 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ust | +0.019 |
ight | +0.017 |
adventure | +0.017 |
eternity | +0.016 |
all | +0.016 |
Neg logit contributions | |
Stacy | -0.020 |
kit | -0.020 |
kettle | -0.019 |
sy | -0.018 |
tin | -0.018 |
Token | fort |
Token ID | 3319 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ust | +0.244 |
adventure | +0.229 |
eternity | +0.224 |
ight | +0.222 |
all | +0.212 |
Neg logit contributions | |
kit | -0.263 |
Stacy | -0.248 |
tin | -0.237 |
kettle | -0.235 |
violet | -0.232 |
Token | ably |
Token ID | 1346 |
Feature activation | +4.68e-04 |
Pos logit contributions | |
eternity | +0.124 |
uct | +0.118 |
adventure | +0.117 |
unexpected | +0.116 |
ust | +0.111 |
Neg logit contributions | |
kit | -0.188 |
Stacy | -0.176 |
kettle | -0.169 |
tin | -0.168 |
band | -0.167 |
Token | hot |
Token ID | 3024 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
kit | +0.001 |
Stacy | +0.001 |
kettle | +0.001 |
tin | +0.001 |
te | +0.001 |
Neg logit contributions | |
ust | -0.001 |
ight | -0.001 |
eternity | -0.001 |
adventure | -0.001 |
all | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ust | +0.055 |
ight | +0.048 |
uct | +0.044 |
urious | +0.042 |
eternity | +0.042 |
Neg logit contributions | |
kit | -0.062 |
kettle | -0.060 |
Stacy | -0.059 |
tin | -0.057 |
bottle | -0.057 |
Token | She |
Token ID | 1375 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
ust | +0.029 |
adventure | +0.028 |
ight | +0.028 |
eternity | +0.027 |
all | +0.027 |
Neg logit contributions | |
kit | -0.014 |
Stacy | -0.014 |
kettle | -0.013 |
sy | -0.012 |
violet | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Stacy | +0.028 |
kit | +0.028 |
kettle | +0.025 |
Grac | +0.024 |
te | +0.024 |
Neg logit contributions | |
ust | -0.047 |
ight | -0.044 |
adventure | -0.042 |
eternity | -0.042 |
all | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ust | +0.042 |
ight | +0.038 |
eternity | +0.037 |
adventure | +0.037 |
rated | +0.036 |
Neg logit contributions | |
Stacy | -0.033 |
kit | -0.033 |
kettle | -0.031 |
Elsa | -0.030 |
te | -0.030 |
Token | little |
Token ID | 1310 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
ust | +0.014 |
adventure | +0.012 |
ight | +0.012 |
eternity | +0.011 |
all | +0.011 |
Neg logit contributions | |
kit | -0.021 |
Stacy | -0.021 |
kettle | -0.019 |
sy | -0.019 |
Grac | -0.019 |
Token | car |
Token ID | 1097 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
Stacy | +0.007 |
kit | +0.007 |
Did | +0.006 |
kettle | +0.006 |
piping | +0.006 |
Neg logit contributions | |
ust | -0.008 |
adventure | -0.008 |
ight | -0.007 |
eternity | -0.007 |
unexpected | -0.007 |
Token | named |
Token ID | 3706 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ust | +0.009 |
adventure | +0.009 |
ight | +0.009 |
eternity | +0.009 |
all | +0.008 |
Neg logit contributions | |
Stacy | -0.009 |
kit | -0.009 |
kettle | -0.008 |
Grac | -0.008 |
violet | -0.008 |
Token | Spe |
Token ID | 2531 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Stacy | +0.098 |
kit | +0.098 |
kettle | +0.090 |
Grac | +0.090 |
Elsa | +0.089 |
Neg logit contributions | |
ust | -0.090 |
ight | -0.080 |
eternity | -0.077 |
adventure | -0.076 |
unexpected | -0.075 |
Token | edy |
Token ID | 4716 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
rated | +0.190 |
eternity | +0.186 |
ust | +0.185 |
accidents | +0.183 |
threats | +0.180 |
Neg logit contributions | |
kit | -0.207 |
violet | -0.207 |
paints | -0.199 |
acey | -0.195 |
comb | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ust | +0.088 |
ight | +0.078 |
adventure | +0.074 |
eternity | +0.074 |
uct | +0.070 |
Neg logit contributions | |
kit | -0.139 |
Stacy | -0.136 |
kettle | -0.127 |
sy | -0.125 |
te | -0.125 |
Token | Spe |
Token ID | 2531 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ust | +0.016 |
ight | +0.014 |
adventure | +0.014 |
eternity | +0.013 |
all | +0.013 |
Neg logit contributions | |
kit | -0.024 |
Stacy | -0.024 |
kettle | -0.022 |
sy | -0.022 |
violet | -0.022 |
Token | edy |
Token ID | 4716 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
eternity | +0.171 |
ust | +0.171 |
rated | +0.159 |
threats | +0.157 |
unatt | +0.157 |
Neg logit contributions | |
kit | -0.165 |
paints | -0.152 |
acey | -0.149 |
violet | -0.147 |
drew | -0.144 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
ust | +0.102 |
ight | +0.095 |
adventure | +0.094 |
eternity | +0.092 |
all | +0.090 |
Neg logit contributions | |
Stacy | -0.071 |
kit | -0.070 |
kettle | -0.064 |
sy | -0.062 |
Grac | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
kit | +0.050 |
Stacy | +0.050 |
kettle | +0.046 |
te | +0.044 |
Elsa | +0.044 |
Neg logit contributions | |
ust | -0.064 |
ight | -0.059 |
adventure | -0.057 |
eternity | -0.057 |
uct | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ust | +0.026 |
ight | +0.024 |
adventure | +0.024 |
eternity | +0.023 |
all | +0.022 |
Neg logit contributions | |
Stacy | -0.029 |
kit | -0.028 |
kettle | -0.026 |
Grac | -0.025 |
violet | -0.025 |
Token | pink |
Token ID | 11398 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
ust | +0.017 |
ight | +0.015 |
adventure | +0.015 |
eternity | +0.014 |
all | +0.014 |
Neg logit contributions | |
Stacy | -0.021 |
kit | -0.021 |
kettle | -0.020 |
sy | -0.019 |
Grac | -0.019 |
Token | car |
Token ID | 1097 |
Feature activation | -7.38e-03 |
Pos logit contributions | |
adventure | +0.025 |
ust | +0.022 |
eternity | +0.022 |
anymore | +0.021 |
ight | +0.020 |
Neg logit contributions | |
Stacy | -0.027 |
kit | -0.025 |
Did | -0.024 |
Grac | -0.023 |
piping | -0.023 |
Token | named |
Token ID | 3706 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
adventure | +0.013 |
ust | +0.013 |
ight | +0.013 |
eternity | +0.012 |
all | +0.012 |
Neg logit contributions | |
Stacy | -0.011 |
kit | -0.010 |
kettle | -0.010 |
Grac | -0.010 |
Elsa | -0.010 |
Token | Spe |
Token ID | 2531 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Stacy | +0.092 |
kit | +0.089 |
Elsa | +0.085 |
Grac | +0.085 |
violet | +0.083 |
Neg logit contributions | |
ust | -0.068 |
ight | -0.060 |
adventure | -0.057 |
eternity | -0.056 |
urious | -0.053 |
Token | edy |
Token ID | 4716 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
ust | +0.187 |
eternity | +0.164 |
alright | +0.160 |
unatt | +0.160 |
accidents | +0.159 |
Neg logit contributions | |
violet | -0.235 |
kit | -0.232 |
paints | -0.229 |
Stacy | -0.218 |
brushes | -0.218 |
Token | liked |
Token ID | 8288 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
ust | +0.143 |
ight | +0.131 |
eternity | +0.126 |
adventure | +0.125 |
uct | +0.123 |
Neg logit contributions | |
kit | -0.089 |
Stacy | -0.085 |
kettle | -0.078 |
Did | -0.077 |
te | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
ust | +0.086 |
ight | +0.080 |
eternity | +0.073 |
uct | +0.071 |
wing | +0.070 |
Neg logit contributions | |
kit | -0.064 |
Stacy | -0.061 |
kettle | -0.058 |
sy | -0.057 |
te | -0.056 |
Token | go |
Token ID | 467 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
ust | +0.042 |
adventure | +0.040 |
ight | +0.038 |
eternity | +0.037 |
all | +0.036 |
Neg logit contributions | |
Stacy | -0.050 |
kit | -0.049 |
kettle | -0.046 |
Grac | -0.045 |
sy | -0.045 |
Token | fast |
Token ID | 3049 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ust | +0.084 |
ight | +0.077 |
uct | +0.071 |
eternity | +0.071 |
urious | +0.067 |
Neg logit contributions | |
kit | -0.068 |
Stacy | -0.064 |
kettle | -0.061 |
sy | -0.060 |
tin | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Stacy | +0.024 |
kit | +0.024 |
kettle | +0.022 |
Grac | +0.021 |
te | +0.020 |
Neg logit contributions | |
ust | -0.041 |
ight | -0.038 |
adventure | -0.037 |
eternity | -0.037 |
all | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ust | +0.048 |
ight | +0.044 |
eternity | +0.042 |
adventure | +0.041 |
rated | +0.040 |
Neg logit contributions | |
Stacy | -0.036 |
kit | -0.035 |
kettle | -0.034 |
Elsa | -0.033 |
te | -0.032 |
Token | little |
Token ID | 1310 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
ust | +0.016 |
adventure | +0.015 |
ight | +0.014 |
eternity | +0.013 |
all | +0.013 |
Neg logit contributions | |
kit | -0.025 |
Stacy | -0.025 |
kettle | -0.023 |
sy | -0.023 |
Grac | -0.023 |
Token | crab |
Token ID | 32202 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
Stacy | +0.005 |
kit | +0.005 |
Did | +0.005 |
piping | +0.005 |
violet | +0.005 |
Neg logit contributions | |
adventure | -0.006 |
ust | -0.006 |
eternity | -0.005 |
ight | -0.005 |
unexpected | -0.005 |
Token | named |
Token ID | 3706 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
ust | +0.102 |
adventure | +0.097 |
ight | +0.096 |
eternity | +0.092 |
all | +0.091 |
Neg logit contributions | |
Stacy | -0.062 |
kit | -0.060 |
kettle | -0.054 |
piping | -0.053 |
Grac | -0.053 |
Token | Cr |
Token ID | 3864 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Stacy | +0.101 |
Grac | +0.097 |
violet | +0.095 |
Elsa | +0.095 |
kit | +0.094 |
Neg logit contributions | |
ust | -0.082 |
ight | -0.073 |
wing | -0.066 |
rated | -0.065 |
urious | -0.065 |
Token | ust |
Token ID | 436 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
adventure | +0.140 |
eternity | +0.135 |
happening | +0.115 |
uct | +0.112 |
behind | +0.110 |
Neg logit contributions | |
Stacy | -0.300 |
acey | -0.286 |
kit | -0.283 |
te | -0.280 |
kettle | -0.279 |
Token | y |
Token ID | 88 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ust | +0.189 |
ight | +0.176 |
adventure | +0.174 |
eternity | +0.169 |
all | +0.165 |
Neg logit contributions | |
Stacy | -0.148 |
kit | -0.146 |
kettle | -0.135 |
violet | -0.129 |
sy | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.015 |
adventure | +0.015 |
eternity | +0.014 |
all | +0.014 |
Neg logit contributions | |
Stacy | -0.041 |
kit | -0.041 |
kettle | -0.039 |
sy | -0.038 |
Grac | -0.038 |
Token | Cr |
Token ID | 3864 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ust | +0.024 |
adventure | +0.022 |
ight | +0.021 |
all | +0.020 |
eternity | +0.020 |
Neg logit contributions | |
Stacy | -0.035 |
kit | -0.034 |
kettle | -0.033 |
sy | -0.031 |
Elsa | -0.031 |
Token | ust |
Token ID | 436 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
adventure | +0.083 |
eternity | +0.081 |
happening | +0.061 |
behind | +0.059 |
uct | +0.053 |
Neg logit contributions | |
Stacy | -0.306 |
acey | -0.301 |
kit | -0.296 |
Grac | -0.290 |
te | -0.290 |
Token | a |
Token ID | 257 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ust | +0.054 |
ight | +0.048 |
rated | +0.045 |
eternity | +0.044 |
ach | +0.043 |
Neg logit contributions | |
Stacy | -0.039 |
kit | -0.039 |
kettle | -0.037 |
bottle | -0.035 |
tul | -0.035 |
Token | family |
Token ID | 1641 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
ust | +0.024 |
adventure | +0.024 |
ight | +0.021 |
unexpected | +0.021 |
eternity | +0.019 |
Neg logit contributions | |
Stacy | -0.042 |
kit | -0.042 |
Did | -0.039 |
kettle | -0.038 |
Grac | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
ust | +0.004 |
adventure | +0.004 |
ight | +0.004 |
eternity | +0.004 |
all | +0.004 |
Neg logit contributions | |
Stacy | -0.006 |
kit | -0.006 |
violet | -0.005 |
kettle | -0.005 |
Elsa | -0.005 |
Token | turtles |
Token ID | 36288 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
Stacy | +0.048 |
kit | +0.048 |
kettle | +0.045 |
sy | +0.043 |
violet | +0.043 |
Neg logit contributions | |
ust | -0.040 |
adventure | -0.039 |
ight | -0.037 |
eternity | -0.036 |
all | -0.035 |
Token | sun |
Token ID | 4252 |
Feature activation | -8.34e-03 |
Pos logit contributions | |
ust | +0.076 |
ight | +0.069 |
adventure | +0.066 |
eternity | +0.065 |
all | +0.064 |
Neg logit contributions | |
kit | -0.085 |
Stacy | -0.084 |
kettle | -0.079 |
sy | -0.077 |
te | -0.076 |
Token | bat |
Token ID | 8664 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ust | +0.015 |
ight | +0.014 |
adventure | +0.013 |
eternity | +0.013 |
all | +0.013 |
Neg logit contributions | |
kit | -0.013 |
Stacy | -0.013 |
kettle | -0.012 |
sy | -0.012 |
tin | -0.012 |
Token | hing |
Token ID | 722 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
ust | +0.225 |
adventure | +0.211 |
eternity | +0.198 |
unexpected | +0.194 |
ight | +0.194 |
Neg logit contributions | |
kit | -0.216 |
Stacy | -0.209 |
kettle | -0.204 |
Did | -0.188 |
Grac | -0.188 |
Token | in |
Token ID | 287 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ust | +0.056 |
ight | +0.049 |
uct | +0.046 |
eternity | +0.045 |
adventure | +0.045 |
Neg logit contributions | |
kit | -0.063 |
Stacy | -0.062 |
kettle | -0.061 |
te | -0.060 |
tin | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
Stacy | +0.036 |
kit | +0.035 |
kettle | +0.033 |
Grac | +0.032 |
te | +0.032 |
Neg logit contributions | |
ust | -0.037 |
ight | -0.033 |
eternity | -0.031 |
adventure | -0.031 |
all | -0.030 |
Token | nearby |
Token ID | 6716 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
kit | +0.008 |
Stacy | +0.008 |
Did | +0.008 |
sy | +0.007 |
Grac | +0.007 |
Neg logit contributions | |
adventure | -0.006 |
ust | -0.005 |
unexpected | -0.005 |
ight | -0.005 |
exciting | -0.004 |
Token | pond |
Token ID | 16723 |
Feature activation | -8.09e-04 |
Pos logit contributions | |
ust | +0.043 |
ight | +0.040 |
adventure | +0.039 |
eternity | +0.038 |
all | +0.037 |
Neg logit contributions | |
Stacy | -0.037 |
kit | -0.037 |
kettle | -0.034 |
sy | -0.033 |
violet | -0.033 |
Token | learned |
Token ID | 4499 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
adventure | +0.051 |
eternity | +0.044 |
ust | +0.042 |
behind | +0.042 |
happening | +0.042 |
Neg logit contributions | |
kit | -0.049 |
kettle | -0.049 |
Stacy | -0.048 |
sy | -0.046 |
piping | -0.046 |
Token | even |
Token ID | 772 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
Stacy | +0.016 |
kit | +0.016 |
kettle | +0.015 |
sy | +0.015 |
Grac | +0.014 |
Neg logit contributions | |
ust | -0.012 |
ight | -0.011 |
adventure | -0.010 |
eternity | -0.010 |
all | -0.010 |
Token | more |
Token ID | 517 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ust | +0.045 |
ight | +0.040 |
adventure | +0.040 |
eternity | +0.038 |
all | +0.037 |
Neg logit contributions | |
Stacy | -0.071 |
kit | -0.070 |
kettle | -0.067 |
sy | -0.064 |
Grac | -0.064 |
Token | about |
Token ID | 546 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
kit | +0.093 |
Stacy | +0.093 |
sy | +0.085 |
kettle | +0.084 |
violet | +0.084 |
Neg logit contributions | |
ust | -0.052 |
ight | -0.046 |
eternity | -0.043 |
adventure | -0.042 |
all | -0.040 |
Token | how |
Token ID | 703 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
ust | +0.021 |
adventure | +0.020 |
ight | +0.019 |
eternity | +0.019 |
all | +0.018 |
Neg logit contributions | |
Stacy | -0.024 |
kit | -0.024 |
kettle | -0.023 |
sy | -0.022 |
tin | -0.021 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Stacy | +0.036 |
kit | +0.036 |
kettle | +0.033 |
sy | +0.032 |
Grac | +0.032 |
Neg logit contributions | |
ust | -0.032 |
ight | -0.029 |
adventure | -0.029 |
eternity | -0.028 |
all | -0.027 |
Token | oes |
Token ID | 3028 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ust | +0.263 |
adventure | +0.262 |
eternity | +0.261 |
ight | +0.257 |
uct | +0.256 |
Neg logit contributions | |
kit | -0.138 |
Stacy | -0.137 |
kettle | -0.123 |
Did | -0.123 |
violet | -0.122 |
Token | work |
Token ID | 670 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.016 |
adventure | +0.016 |
eternity | +0.016 |
all | +0.015 |
Neg logit contributions | |
Stacy | -0.021 |
kit | -0.021 |
kettle | -0.020 |
sy | -0.019 |
Grac | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
kit | +0.017 |
Stacy | +0.017 |
kettle | +0.016 |
tin | +0.016 |
sy | +0.016 |
Neg logit contributions | |
ust | -0.011 |
ight | -0.009 |
adventure | -0.009 |
eternity | -0.009 |
all | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ust | +0.029 |
all | +0.026 |
adventure | +0.026 |
eternity | +0.026 |
ight | +0.026 |
Neg logit contributions | |
kit | -0.032 |
Stacy | -0.031 |
kettle | -0.030 |
sy | -0.030 |
tin | -0.029 |
Token | thought |
Token ID | 1807 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
kit | +0.038 |
Stacy | +0.038 |
kettle | +0.037 |
sy | +0.035 |
piping | +0.035 |
Neg logit contributions | |
ust | -0.035 |
adventure | -0.034 |
ight | -0.032 |
all | -0.031 |
eternity | -0.030 |
Token | big |
Token ID | 1263 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
adventure | +0.014 |
ust | +0.013 |
unexpected | +0.012 |
exciting | +0.011 |
ight | +0.011 |
Neg logit contributions | |
Stacy | -0.023 |
kit | -0.021 |
Did | -0.021 |
Grac | -0.020 |
kettle | -0.020 |
Token | book |
Token ID | 1492 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
adventure | +0.040 |
eternity | +0.035 |
anymore | +0.034 |
ust | +0.034 |
unexpected | +0.033 |
Neg logit contributions | |
Stacy | -0.030 |
kit | -0.025 |
Did | -0.025 |
Grac | -0.025 |
acey | -0.024 |
Token | with |
Token ID | 351 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ust | +0.057 |
ight | +0.049 |
adventure | +0.049 |
eternity | +0.048 |
all | +0.047 |
Neg logit contributions | |
kit | -0.071 |
Stacy | -0.068 |
kettle | -0.065 |
tin | -0.063 |
te | -0.063 |
Token | pictures |
Token ID | 5986 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
Stacy | +0.021 |
kit | +0.021 |
kettle | +0.020 |
sy | +0.019 |
Grac | +0.018 |
Neg logit contributions | |
adventure | -0.016 |
ust | -0.015 |
ight | -0.015 |
unexpected | -0.014 |
eternity | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
ust | +0.009 |
adventure | +0.008 |
ight | +0.008 |
eternity | +0.008 |
all | +0.007 |
Neg logit contributions | |
Stacy | -0.015 |
kit | -0.014 |
kettle | -0.013 |
sy | -0.013 |
Grac | -0.013 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Stacy | +0.012 |
kit | +0.011 |
kettle | +0.011 |
sy | +0.010 |
Did | +0.010 |
Neg logit contributions | |
adventure | -0.008 |
ust | -0.008 |
ight | -0.007 |
eternity | -0.007 |
anymore | -0.007 |
Token | oes |
Token ID | 3028 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
ust | +0.280 |
uct | +0.275 |
eternity | +0.275 |
adventure | +0.271 |
unexpected | +0.270 |
Neg logit contributions | |
kit | -0.131 |
kettle | -0.118 |
Stacy | -0.114 |
paints | -0.110 |
violet | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ust | +0.009 |
ight | +0.008 |
adventure | +0.007 |
eternity | +0.007 |
all | +0.007 |
Neg logit contributions | |
kit | -0.016 |
Stacy | -0.016 |
kettle | -0.015 |
sy | -0.015 |
tin | -0.015 |
Token | Vol |
Token ID | 4709 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
ust | +0.027 |
ight | +0.025 |
adventure | +0.025 |
eternity | +0.024 |
all | +0.024 |
Neg logit contributions | |
Stacy | -0.017 |
kit | -0.017 |
kettle | -0.015 |
sy | -0.015 |
tin | -0.014 |
Token | can |
Token ID | 5171 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ust | +0.141 |
adventure | +0.134 |
ight | +0.130 |
eternity | +0.128 |
all | +0.121 |
Neg logit contributions | |
kit | -0.091 |
Stacy | -0.091 |
kettle | -0.081 |
Did | -0.077 |
tin | -0.076 |
Token | oes |
Token ID | 3028 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
ust | +0.020 |
ight | +0.019 |
adventure | +0.018 |
eternity | +0.018 |
all | +0.017 |
Neg logit contributions | |
kit | -0.020 |
Stacy | -0.020 |
kettle | -0.019 |
sy | -0.018 |
Grac | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | +7.93e-03 |
Pos logit contributions | |
kit | +0.006 |
Stacy | +0.006 |
sy | +0.006 |
tul | +0.006 |
piping | +0.006 |
Neg logit contributions | |
ust | -0.006 |
adventure | -0.006 |
anymore | -0.005 |
eternity | -0.005 |
all | -0.005 |
Token | book |
Token ID | 1492 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
Stacy | +0.011 |
kit | +0.011 |
Grac | +0.010 |
kettle | +0.010 |
sy | +0.010 |
Neg logit contributions | |
adventure | -0.015 |
ust | -0.014 |
ight | -0.014 |
eternity | -0.013 |
anymore | -0.013 |
Token | has |
Token ID | 468 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
ust | +0.034 |
adventure | +0.033 |
ight | +0.033 |
anymore | +0.031 |
behind | +0.031 |
Neg logit contributions | |
Stacy | -0.020 |
kit | -0.018 |
kettle | -0.017 |
Grac | -0.017 |
sy | -0.017 |
Token | pictures |
Token ID | 5986 |
Feature activation | -3.67e-03 |
Pos logit contributions | |
Stacy | +0.064 |
kit | +0.062 |
kettle | +0.059 |
Grac | +0.058 |
sy | +0.056 |
Neg logit contributions | |
adventure | -0.044 |
ust | -0.042 |
ight | -0.041 |
unexpected | -0.038 |
exciting | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
adventure | +0.004 |
ust | +0.004 |
ight | +0.004 |
anymore | +0.004 |
all | +0.004 |
Neg logit contributions | |
Stacy | -0.008 |
kit | -0.007 |
kettle | -0.007 |
Grac | -0.007 |
sy | -0.007 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Stacy | +0.015 |
kit | +0.015 |
kettle | +0.014 |
sy | +0.013 |
piping | +0.013 |
Neg logit contributions | |
ust | -0.012 |
adventure | -0.011 |
ight | -0.010 |
eternity | -0.010 |
anymore | -0.010 |
Token | oes |
Token ID | 3028 |
Feature activation | -6.77e-03 |
Pos logit contributions | |
ust | +0.269 |
eternity | +0.259 |
adventure | +0.257 |
uct | +0.257 |
ight | +0.255 |
Neg logit contributions | |
kit | -0.153 |
Stacy | -0.142 |
kettle | -0.138 |
violet | -0.129 |
tin | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-03 |
Pos logit contributions | |
ust | +0.007 |
ight | +0.007 |
adventure | +0.006 |
eternity | +0.006 |
all | +0.006 |
Neg logit contributions | |
Stacy | -0.015 |
kit | -0.015 |
kettle | -0.014 |
sy | -0.014 |
Grac | -0.014 |
Token | Vol |
Token ID | 4709 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
kit | +0.003 |
Stacy | +0.003 |
sy | +0.003 |
kettle | +0.003 |
violet | +0.003 |
Neg logit contributions | |
ust | -0.004 |
adventure | -0.003 |
ight | -0.003 |
eternity | -0.003 |
anymore | -0.003 |
Token | can |
Token ID | 5171 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ust | +0.132 |
ight | +0.123 |
adventure | +0.123 |
eternity | +0.119 |
all | +0.116 |
Neg logit contributions | |
Stacy | -0.089 |
kit | -0.088 |
kettle | -0.080 |
sy | -0.076 |
tin | -0.075 |
Token | oes |
Token ID | 3028 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
ust | +0.023 |
ight | +0.021 |
adventure | +0.021 |
eternity | +0.020 |
all | +0.019 |
Neg logit contributions | |
kit | -0.023 |
Stacy | -0.023 |
kettle | -0.022 |
sy | -0.021 |
Grac | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
adventure | +0.013 |
ust | +0.012 |
unexpected | +0.011 |
exciting | +0.010 |
happening | +0.010 |
Neg logit contributions | |
Stacy | -0.022 |
kit | -0.020 |
Did | -0.020 |
Grac | -0.019 |
kettle | -0.019 |
Token | book |
Token ID | 1492 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
adventure | +0.038 |
eternity | +0.033 |
anymore | +0.033 |
ust | +0.033 |
unexpected | +0.032 |
Neg logit contributions | |
Stacy | -0.028 |
kit | -0.024 |
Did | -0.024 |
Grac | -0.023 |
acey | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ust | +0.057 |
ight | +0.050 |
adventure | +0.050 |
eternity | +0.049 |
all | +0.047 |
Neg logit contributions | |
kit | -0.071 |
Stacy | -0.069 |
kettle | -0.066 |
tin | -0.064 |
te | -0.063 |
Token | pictures |
Token ID | 5986 |
Feature activation | -6.24e-03 |
Pos logit contributions | |
Stacy | +0.021 |
kit | +0.020 |
kettle | +0.020 |
sy | +0.019 |
Grac | +0.018 |
Neg logit contributions | |
adventure | -0.016 |
ust | -0.016 |
ight | -0.015 |
eternity | -0.014 |
unexpected | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
ust | +0.008 |
adventure | +0.007 |
ight | +0.007 |
eternity | +0.007 |
all | +0.007 |
Neg logit contributions | |
Stacy | -0.013 |
kit | -0.012 |
kettle | -0.012 |
Grac | -0.012 |
sy | -0.012 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Stacy | +0.015 |
kit | +0.015 |
kettle | +0.014 |
sy | +0.013 |
piping | +0.013 |
Neg logit contributions | |
adventure | -0.011 |
ust | -0.010 |
ight | -0.009 |
eternity | -0.009 |
anymore | -0.009 |
Token | oes |
Token ID | 3028 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
ust | +0.278 |
uct | +0.275 |
eternity | +0.275 |
adventure | +0.270 |
unexpected | +0.269 |
Neg logit contributions | |
kit | -0.131 |
kettle | -0.118 |
Stacy | -0.113 |
paints | -0.110 |
violet | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
ust | +0.010 |
ight | +0.009 |
adventure | +0.008 |
eternity | +0.008 |
all | +0.008 |
Neg logit contributions | |
kit | -0.018 |
Stacy | -0.018 |
kettle | -0.017 |
sy | -0.016 |
tin | -0.016 |
Token | Vol |
Token ID | 4709 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
ust | +0.029 |
ight | +0.027 |
adventure | +0.027 |
eternity | +0.026 |
all | +0.025 |
Neg logit contributions | |
Stacy | -0.017 |
kit | -0.017 |
kettle | -0.015 |
sy | -0.015 |
Grac | -0.014 |
Token | can |
Token ID | 5171 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ust | +0.141 |
adventure | +0.134 |
ight | +0.130 |
eternity | +0.127 |
all | +0.121 |
Neg logit contributions | |
kit | -0.089 |
Stacy | -0.089 |
kettle | -0.080 |
Did | -0.075 |
tin | -0.075 |
Token | oes |
Token ID | 3028 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.017 |
adventure | +0.016 |
eternity | +0.016 |
all | +0.015 |
Neg logit contributions | |
kit | -0.018 |
Stacy | -0.018 |
kettle | -0.017 |
sy | -0.016 |
Grac | -0.016 |
Token | teach |
Token ID | 4545 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Stacy | +0.028 |
kit | +0.027 |
kettle | +0.026 |
sy | +0.025 |
Elsa | +0.025 |
Neg logit contributions | |
adventure | -0.028 |
ust | -0.028 |
all | -0.026 |
ight | -0.026 |
eternity | -0.026 |
Token | you |
Token ID | 345 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
Stacy | +0.039 |
kit | +0.038 |
Elsa | +0.036 |
Grac | +0.036 |
kettle | +0.035 |
Neg logit contributions | |
ust | -0.028 |
ight | -0.024 |
adventure | -0.023 |
eternity | -0.023 |
rated | -0.022 |
Token | something |
Token ID | 1223 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
ust | +0.055 |
ight | +0.050 |
adventure | +0.049 |
eternity | +0.047 |
all | +0.046 |
Neg logit contributions | |
Stacy | -0.076 |
kit | -0.075 |
kettle | -0.071 |
sy | -0.068 |
violet | -0.068 |
Token | special |
Token ID | 2041 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
ust | +0.037 |
ight | +0.034 |
adventure | +0.033 |
eternity | +0.032 |
all | +0.031 |
Neg logit contributions | |
Stacy | -0.052 |
kit | -0.051 |
kettle | -0.048 |
sy | -0.047 |
Grac | -0.046 |
Token | about |
Token ID | 546 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ust | +0.037 |
ight | +0.033 |
adventure | +0.032 |
eternity | +0.031 |
all | +0.030 |
Neg logit contributions | |
Stacy | -0.062 |
kit | -0.061 |
kettle | -0.058 |
sy | -0.056 |
Grac | -0.056 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.016 |
adventure | +0.016 |
eternity | +0.015 |
all | +0.015 |
Neg logit contributions | |
Stacy | -0.019 |
kit | -0.018 |
kettle | -0.017 |
violet | -0.017 |
te | -0.017 |
Token | oes |
Token ID | 3028 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
uct | +0.292 |
adventure | +0.284 |
eternity | +0.283 |
unexpected | +0.281 |
ust | +0.275 |
Neg logit contributions | |
kit | -0.098 |
violet | -0.090 |
Stacy | -0.090 |
vals | -0.087 |
kettle | -0.085 |
Token | ." |
Token ID | 526 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.016 |
adventure | +0.015 |
eternity | +0.015 |
uct | +0.015 |
Neg logit contributions | |
Stacy | -0.025 |
kit | -0.025 |
kettle | -0.023 |
tin | -0.023 |
te | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
kit | +0.008 |
sy | +0.008 |
Stacy | +0.007 |
groom | +0.007 |
kettle | +0.007 |
Neg logit contributions | |
adventure | -0.006 |
all | -0.005 |
eternity | -0.005 |
ust | -0.005 |
ight | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
ust | +0.076 |
ight | +0.069 |
adventure | +0.068 |
eternity | +0.067 |
all | +0.063 |
Neg logit contributions | |
Stacy | -0.060 |
kit | -0.057 |
kettle | -0.053 |
Grac | -0.051 |
Elsa | -0.051 |
Token | So |
Token ID | 2396 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
ust | +0.048 |
ight | +0.043 |
adventure | +0.042 |
all | +0.040 |
eternity | +0.039 |
Neg logit contributions | |
kit | -0.071 |
Stacy | -0.071 |
kettle | -0.066 |
sy | -0.066 |
Grac | -0.064 |
Token | little |
Token ID | 1310 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ust | +0.041 |
ight | +0.037 |
eternity | +0.035 |
uct | +0.035 |
all | +0.035 |
Neg logit contributions | |
Stacy | -0.038 |
kettle | -0.038 |
Grac | -0.036 |
kit | -0.036 |
te | -0.036 |
Token | girl |
Token ID | 2576 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
kit | +0.015 |
Stacy | +0.014 |
sy | +0.013 |
piping | +0.013 |
kettle | +0.012 |
Neg logit contributions | |
ust | -0.024 |
adventure | -0.024 |
ight | -0.023 |
all | -0.022 |
eternity | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
Stacy | +0.131 |
kit | +0.128 |
sy | +0.127 |
kettle | +0.127 |
piping | +0.121 |
Neg logit contributions | |
adventure | -0.053 |
ust | -0.052 |
ight | -0.046 |
all | -0.046 |
eternity | -0.041 |
Token | about |
Token ID | 546 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
Stacy | +0.014 |
kit | +0.014 |
sy | +0.013 |
kettle | +0.013 |
Elsa | +0.013 |
Neg logit contributions | |
ust | -0.010 |
adventure | -0.010 |
ight | -0.009 |
eternity | -0.009 |
all | -0.009 |
Token | how |
Token ID | 703 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ust | +0.003 |
ight | +0.002 |
adventure | +0.002 |
eternity | +0.002 |
all | +0.002 |
Neg logit contributions | |
Stacy | -0.003 |
kit | -0.003 |
kettle | -0.003 |
sy | -0.003 |
Grac | -0.003 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Stacy | +0.038 |
kit | +0.036 |
kettle | +0.035 |
tin | +0.034 |
violet | +0.034 |
Neg logit contributions | |
ust | -0.041 |
ight | -0.038 |
eternity | -0.036 |
adventure | -0.036 |
all | -0.035 |
Token | oes |
Token ID | 3028 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
adventure | +0.260 |
eternity | +0.260 |
uct | +0.256 |
ust | +0.255 |
ight | +0.251 |
Neg logit contributions | |
kit | -0.131 |
Stacy | -0.129 |
kettle | -0.121 |
Did | -0.121 |
tin | -0.119 |
Token | work |
Token ID | 670 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
ust | +0.040 |
ight | +0.037 |
adventure | +0.036 |
eternity | +0.035 |
all | +0.034 |
Neg logit contributions | |
Stacy | -0.032 |
kit | -0.031 |
kettle | -0.029 |
sy | -0.028 |
tin | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -7.16e-03 |
Pos logit contributions | |
kit | +0.016 |
Stacy | +0.015 |
kettle | +0.014 |
tin | +0.014 |
Grac | +0.014 |
Neg logit contributions | |
ust | -0.011 |
ight | -0.010 |
eternity | -0.009 |
adventure | -0.009 |
uct | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
all | +0.012 |
ust | +0.012 |
eternity | +0.012 |
adventure | +0.011 |
ight | +0.011 |
Neg logit contributions | |
kit | -0.011 |
Stacy | -0.010 |
sy | -0.010 |
kettle | -0.010 |
groom | -0.010 |
Token | taught |
Token ID | 7817 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
Stacy | +0.036 |
kit | +0.035 |
kettle | +0.033 |
sy | +0.032 |
Elsa | +0.032 |
Neg logit contributions | |
ust | -0.041 |
adventure | -0.040 |
ight | -0.038 |
all | -0.037 |
eternity | -0.037 |
Token | creatures |
Token ID | 8109 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ust | +0.022 |
ight | +0.019 |
eternity | +0.019 |
adventure | +0.018 |
uct | +0.018 |
Neg logit contributions | |
kit | -0.032 |
Stacy | -0.032 |
kettle | -0.030 |
te | -0.029 |
tin | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ust | +0.021 |
adventure | +0.018 |
ight | +0.018 |
eternity | +0.017 |
all | +0.016 |
Neg logit contributions | |
Stacy | -0.052 |
kit | -0.051 |
kettle | -0.048 |
sy | -0.048 |
Grac | -0.047 |
Token | One |
Token ID | 1881 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ust | +0.050 |
adventure | +0.047 |
ight | +0.046 |
eternity | +0.045 |
all | +0.044 |
Neg logit contributions | |
Stacy | -0.052 |
kit | -0.052 |
kettle | -0.048 |
sy | -0.047 |
Elsa | -0.045 |
Token | day |
Token ID | 1110 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
ust | +0.028 |
ight | +0.027 |
uct | +0.027 |
eternity | +0.025 |
anymore | +0.024 |
Neg logit contributions | |
Stacy | -0.015 |
kettle | -0.015 |
bottle | -0.013 |
violet | -0.013 |
te | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
Stacy | +0.050 |
kit | +0.049 |
kettle | +0.046 |
sy | +0.045 |
tin | +0.044 |
Neg logit contributions | |
ust | -0.040 |
adventure | -0.037 |
ight | -0.037 |
eternity | -0.035 |
all | -0.035 |
Token | Cr |
Token ID | 3864 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ust | +0.023 |
adventure | +0.022 |
ight | +0.020 |
eternity | +0.020 |
all | +0.020 |
Neg logit contributions | |
Stacy | -0.030 |
kit | -0.030 |
kettle | -0.028 |
sy | -0.027 |
piping | -0.027 |
Token | ust |
Token ID | 436 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
adventure | +0.093 |
eternity | +0.089 |
happening | +0.071 |
behind | +0.067 |
uct | +0.063 |
Neg logit contributions | |
Stacy | -0.315 |
acey | -0.306 |
kit | -0.299 |
te | -0.294 |
Grac | -0.293 |
Token | y |
Token ID | 88 |
Feature activation | -4.08e-04 |
Pos logit contributions | |
ust | +0.168 |
ight | +0.158 |
adventure | +0.156 |
eternity | +0.153 |
all | +0.149 |
Neg logit contributions | |
Stacy | -0.124 |
kit | -0.122 |
kettle | -0.113 |
tin | -0.109 |
violet | -0.109 |
Token | found |
Token ID | 1043 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ust | +0.001 |
ight | +0.001 |
uct | +0.001 |
eternity | +0.001 |
all | +0.001 |
Neg logit contributions | |
Stacy | -0.000 |
kettle | -0.000 |
kit | -0.000 |
te | -0.000 |
throat | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
ust | +0.035 |
adventure | +0.033 |
ight | +0.032 |
eternity | +0.031 |
all | +0.030 |
Neg logit contributions | |
Stacy | -0.049 |
kit | -0.048 |
kettle | -0.045 |
sy | -0.044 |
tin | -0.043 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
adventure | +0.020 |
ust | +0.020 |
unexpected | +0.018 |
ight | +0.017 |
exciting | +0.016 |
Neg logit contributions | |
Stacy | -0.034 |
kit | -0.033 |
Did | -0.031 |
Elsa | -0.030 |
sy | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
ust | +0.044 |
adventure | +0.041 |
ight | +0.041 |
all | +0.039 |
eternity | +0.038 |
Neg logit contributions | |
kit | -0.037 |
Stacy | -0.036 |
kettle | -0.035 |
sy | -0.034 |
piping | -0.033 |
Token | little |
Token ID | 1310 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
Stacy | +0.009 |
kit | +0.009 |
kettle | +0.008 |
tin | +0.008 |
te | +0.008 |
Neg logit contributions | |
ust | -0.008 |
ight | -0.007 |
eternity | -0.007 |
adventure | -0.007 |
all | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
kit | +0.042 |
Stacy | +0.041 |
sy | +0.039 |
piping | +0.039 |
kettle | +0.039 |
Neg logit contributions | |
ust | -0.058 |
adventure | -0.057 |
ight | -0.053 |
anymore | -0.052 |
behind | -0.050 |
Token | was |
Token ID | 373 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Stacy | +0.106 |
kit | +0.104 |
kettle | +0.099 |
sy | +0.096 |
piping | +0.094 |
Neg logit contributions | |
ust | -0.108 |
ight | -0.100 |
adventure | -0.099 |
eternity | -0.094 |
all | -0.093 |
Token | so |
Token ID | 523 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Stacy | +0.037 |
kit | +0.037 |
kettle | +0.034 |
violet | +0.033 |
te | +0.033 |
Neg logit contributions | |
ust | -0.031 |
ight | -0.028 |
adventure | -0.028 |
eternity | -0.027 |
all | -0.026 |
Token | ins |
Token ID | 1035 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Stacy | +0.025 |
kit | +0.022 |
Grac | +0.022 |
te | +0.022 |
brush | +0.022 |
Neg logit contributions | |
ust | -0.026 |
eternity | -0.026 |
adventure | -0.025 |
ight | -0.025 |
anymore | -0.024 |
Token | istent |
Token ID | 7609 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
adventure | +0.192 |
ust | +0.175 |
eternity | +0.167 |
behind | +0.164 |
unexpected | +0.159 |
Neg logit contributions | |
kit | -0.224 |
Stacy | -0.220 |
acey | -0.201 |
cutter | -0.200 |
kettle | -0.197 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ust | +0.047 |
ight | +0.042 |
adventure | +0.041 |
eternity | +0.039 |
all | +0.037 |
Neg logit contributions | |
Stacy | -0.079 |
kit | -0.078 |
kettle | -0.073 |
sy | -0.071 |
tin | -0.071 |
Token | her |
Token ID | 607 |
Feature activation | +3.98e-03 |
Pos logit contributions | |
kit | +0.013 |
Stacy | +0.013 |
kettle | +0.012 |
sy | +0.011 |
violet | +0.011 |
Neg logit contributions | |
ust | -0.025 |
adventure | -0.024 |
ight | -0.024 |
eternity | -0.023 |
all | -0.023 |
Token | mum |
Token ID | 25682 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Stacy | +0.005 |
kit | +0.005 |
throat | +0.004 |
kettle | +0.004 |
brush | +0.004 |
Neg logit contributions | |
ust | -0.008 |
ight | -0.008 |
all | -0.008 |
eternity | -0.008 |
uct | -0.007 |
Token | finally |
Token ID | 3443 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
Stacy | +0.032 |
kit | +0.031 |
kettle | +0.030 |
sy | +0.029 |
piping | +0.028 |
Neg logit contributions | |
ust | -0.038 |
ight | -0.036 |
adventure | -0.035 |
eternity | -0.034 |
all | -0.034 |
Token | They |
Token ID | 1119 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
Stacy | +0.026 |
kit | +0.025 |
kettle | +0.022 |
sy | +0.022 |
Grac | +0.021 |
Neg logit contributions | |
ust | -0.051 |
adventure | -0.048 |
ight | -0.048 |
eternity | -0.047 |
all | -0.047 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
kit | +0.042 |
Stacy | +0.042 |
kettle | +0.038 |
sy | +0.038 |
piping | +0.037 |
Neg logit contributions | |
ust | -0.039 |
adventure | -0.037 |
ight | -0.036 |
eternity | -0.033 |
all | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
Stacy | +0.031 |
kit | +0.031 |
kettle | +0.029 |
sy | +0.028 |
te | +0.028 |
Neg logit contributions | |
ust | -0.034 |
ight | -0.032 |
eternity | -0.030 |
adventure | -0.030 |
all | -0.029 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ust | +0.005 |
adventure | +0.005 |
ight | +0.004 |
unexpected | +0.004 |
eternity | +0.004 |
Neg logit contributions | |
Stacy | -0.004 |
kit | -0.004 |
Elsa | -0.004 |
kettle | -0.004 |
Grac | -0.004 |
Token | about |
Token ID | 546 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
kit | +0.027 |
Stacy | +0.027 |
kettle | +0.026 |
bottle | +0.025 |
lav | +0.024 |
Neg logit contributions | |
ust | -0.022 |
uct | -0.020 |
ight | -0.019 |
urious | -0.019 |
adventure | -0.018 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ust | +0.038 |
ight | +0.035 |
adventure | +0.033 |
eternity | +0.033 |
all | +0.032 |
Neg logit contributions | |
Stacy | -0.038 |
kit | -0.037 |
kettle | -0.035 |
sy | -0.034 |
violet | -0.034 |
Token | oes |
Token ID | 3028 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
uct | +0.279 |
ust | +0.268 |
eternity | +0.267 |
adventure | +0.262 |
ight | +0.261 |
Neg logit contributions | |
kit | -0.115 |
kettle | -0.109 |
paints | -0.099 |
vals | -0.097 |
Stacy | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ust | +0.004 |
ight | +0.003 |
adventure | +0.003 |
eternity | +0.003 |
all | +0.003 |
Neg logit contributions | |
Stacy | -0.006 |
kit | -0.006 |
kettle | -0.006 |
sy | -0.006 |
tin | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
Stacy | +0.021 |
kit | +0.020 |
kettle | +0.018 |
sy | +0.017 |
Grac | +0.016 |
Neg logit contributions | |
ust | -0.051 |
ight | -0.048 |
adventure | -0.048 |
eternity | -0.047 |
all | -0.046 |
Token | thanked |
Token ID | 26280 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
kit | +0.046 |
Stacy | +0.046 |
kettle | +0.042 |
sy | +0.041 |
piping | +0.041 |
Neg logit contributions | |
ust | -0.046 |
adventure | -0.044 |
ight | -0.042 |
eternity | -0.039 |
unexpected | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -8.56e-05 |
Pos logit contributions | |
Stacy | +0.017 |
kit | +0.016 |
kettle | +0.016 |
violet | +0.015 |
Grac | +0.015 |
Neg logit contributions | |
ust | -0.025 |
ight | -0.023 |
rated | -0.020 |
uct | -0.020 |
iver | -0.020 |
Token | just |
Token ID | 655 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
Stacy | +0.053 |
kit | +0.051 |
kettle | +0.047 |
sy | +0.047 |
violet | +0.046 |
Neg logit contributions | |
ust | -0.055 |
ight | -0.050 |
adventure | -0.049 |
eternity | -0.046 |
all | -0.046 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
Stacy | +0.003 |
kit | +0.003 |
kettle | +0.003 |
sy | +0.003 |
violet | +0.003 |
Neg logit contributions | |
ust | -0.002 |
adventure | -0.002 |
ight | -0.002 |
eternity | -0.002 |
unexpected | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ust | +0.038 |
ight | +0.035 |
eternity | +0.032 |
uct | +0.032 |
all | +0.032 |
Neg logit contributions | |
kit | -0.030 |
Stacy | -0.030 |
kettle | -0.028 |
Elsa | -0.027 |
Grac | -0.027 |
Token | write |
Token ID | 3551 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
ust | +0.035 |
ight | +0.033 |
adventure | +0.032 |
eternity | +0.032 |
all | +0.031 |
Neg logit contributions | |
Stacy | -0.028 |
kit | -0.028 |
kettle | -0.026 |
sy | -0.025 |
Grac | -0.024 |
Token | about |
Token ID | 546 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
kit | +0.013 |
Stacy | +0.013 |
Elsa | +0.012 |
kettle | +0.012 |
tin | +0.011 |
Neg logit contributions | |
ust | -0.013 |
ight | -0.011 |
eternity | -0.011 |
adventure | -0.011 |
uct | -0.011 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ust | +0.007 |
ight | +0.007 |
rated | +0.006 |
uct | +0.006 |
all | +0.006 |
Neg logit contributions | |
Stacy | -0.006 |
kit | -0.005 |
Elsa | -0.005 |
kettle | -0.005 |
violet | -0.005 |
Token | oes |
Token ID | 3028 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
unexpected | +0.282 |
uct | +0.281 |
ust | +0.280 |
eternity | +0.279 |
adventure | +0.278 |
Neg logit contributions | |
kit | -0.115 |
kettle | -0.102 |
Stacy | -0.096 |
paints | -0.094 |
coloring | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
ust | +0.007 |
ight | +0.006 |
adventure | +0.006 |
eternity | +0.006 |
uct | +0.005 |
Neg logit contributions | |
kit | -0.009 |
Stacy | -0.009 |
kettle | -0.009 |
sy | -0.009 |
Elsa | -0.009 |
Token | We |
Token ID | 775 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
kit | +0.040 |
Stacy | +0.040 |
kettle | +0.036 |
sy | +0.035 |
tin | +0.035 |
Neg logit contributions | |
ust | -0.048 |
adventure | -0.044 |
ight | -0.043 |
eternity | -0.043 |
all | -0.042 |
Token | like |
Token ID | 588 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Stacy | +0.044 |
kit | +0.042 |
kettle | +0.040 |
sy | +0.039 |
violet | +0.038 |
Neg logit contributions | |
ust | -0.044 |
ight | -0.040 |
adventure | -0.039 |
eternity | -0.037 |
all | -0.036 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ust | +0.026 |
ight | +0.024 |
adventure | +0.023 |
eternity | +0.023 |
all | +0.022 |
Neg logit contributions | |
Stacy | -0.030 |
kit | -0.030 |
kettle | -0.028 |
sy | -0.027 |
Grac | -0.027 |
Token | but |
Token ID | 475 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ust | +0.013 |
adventure | +0.011 |
ight | +0.011 |
eternity | +0.011 |
all | +0.011 |
Neg logit contributions | |
Stacy | -0.020 |
kit | -0.020 |
kettle | -0.019 |
sy | -0.019 |
violet | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +7.11e-04 |
Pos logit contributions | |
ust | +0.053 |
adventure | +0.049 |
ight | +0.048 |
eternity | +0.046 |
all | +0.045 |
Neg logit contributions | |
Stacy | -0.068 |
kit | -0.068 |
kettle | -0.064 |
sy | -0.062 |
Grac | -0.061 |
Token | other |
Token ID | 584 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
Stacy | +0.001 |
kit | +0.001 |
kettle | +0.001 |
Grac | +0.001 |
sy | +0.001 |
Neg logit contributions | |
ust | -0.001 |
adventure | -0.001 |
ight | -0.001 |
eternity | -0.001 |
all | -0.001 |
Token | animal |
Token ID | 5044 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
kit | +0.054 |
Stacy | +0.053 |
kettle | +0.049 |
te | +0.049 |
tin | +0.049 |
Neg logit contributions | |
ust | -0.065 |
ight | -0.060 |
adventure | -0.057 |
eternity | -0.057 |
all | -0.057 |
Token | was |
Token ID | 373 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
ust | +0.014 |
ight | +0.013 |
adventure | +0.013 |
eternity | +0.013 |
all | +0.013 |
Neg logit contributions | |
kit | -0.012 |
Stacy | -0.012 |
kettle | -0.011 |
te | -0.010 |
sy | -0.010 |
Token | ins |
Token ID | 1035 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Stacy | +0.005 |
kit | +0.005 |
kettle | +0.004 |
sy | +0.004 |
violet | +0.004 |
Neg logit contributions | |
ust | -0.004 |
ight | -0.004 |
adventure | -0.004 |
eternity | -0.004 |
all | -0.003 |
Token | istent |
Token ID | 7609 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
adventure | +0.203 |
eternity | +0.178 |
ust | +0.178 |
behind | +0.176 |
unexpected | +0.171 |
Neg logit contributions | |
kit | -0.209 |
Stacy | -0.198 |
acey | -0.185 |
cutter | -0.183 |
kettle | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ust | +0.046 |
ight | +0.042 |
adventure | +0.040 |
eternity | +0.039 |
ach | +0.039 |
Neg logit contributions | |
kit | -0.061 |
Stacy | -0.056 |
bottle | -0.053 |
tin | -0.053 |
cutter | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
ust | +0.043 |
ight | +0.040 |
adventure | +0.040 |
eternity | +0.039 |
all | +0.038 |
Neg logit contributions | |
Stacy | -0.040 |
kit | -0.040 |
kettle | -0.037 |
sy | -0.036 |
tin | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ust | +0.071 |
ight | +0.065 |
adventure | +0.065 |
eternity | +0.064 |
rated | +0.060 |
Neg logit contributions | |
Stacy | -0.049 |
kit | -0.047 |
kettle | -0.041 |
Grac | -0.041 |
Did | -0.041 |
Token | The |
Token ID | 464 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
ust | +0.050 |
adventure | +0.046 |
ight | +0.045 |
eternity | +0.044 |
all | +0.042 |
Neg logit contributions | |
Stacy | -0.057 |
kit | -0.056 |
kettle | -0.052 |
violet | -0.051 |
tin | -0.051 |
Token | truck |
Token ID | 7779 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
Stacy | +0.067 |
kit | +0.065 |
kettle | +0.061 |
violet | +0.060 |
sy | +0.059 |
Neg logit contributions | |
ust | -0.067 |
adventure | -0.064 |
ight | -0.062 |
eternity | -0.060 |
all | -0.058 |
Token | named |
Token ID | 3706 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
ust | +0.040 |
ight | +0.037 |
adventure | +0.035 |
eternity | +0.035 |
all | +0.035 |
Neg logit contributions | |
kit | -0.024 |
Stacy | -0.022 |
kettle | -0.020 |
sy | -0.020 |
te | -0.019 |
Token | Big |
Token ID | 4403 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
kit | +0.075 |
Stacy | +0.074 |
Grac | +0.066 |
sy | +0.065 |
Doll | +0.064 |
Neg logit contributions | |
ust | -0.086 |
ight | -0.080 |
eternity | -0.075 |
ized | -0.072 |
adventure | -0.072 |
Token | T |
Token ID | 309 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
ust | +0.066 |
ight | +0.060 |
uct | +0.054 |
eternity | +0.054 |
iver | +0.053 |
Neg logit contributions | |
kit | -0.051 |
Stacy | -0.045 |
Doll | -0.042 |
sy | -0.042 |
bottle | -0.041 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
ust | +0.100 |
uct | +0.094 |
unexpected | +0.094 |
rated | +0.093 |
ight | +0.091 |
Neg logit contributions | |
kit | -0.107 |
acey | -0.096 |
Stacy | -0.094 |
sy | -0.091 |
Doll | -0.091 |
Token | Spe |
Token ID | 2531 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ust | +0.030 |
ight | +0.026 |
eternity | +0.024 |
adventure | +0.024 |
rated | +0.023 |
Neg logit contributions | |
kit | -0.034 |
Stacy | -0.032 |
sy | -0.030 |
Did | -0.030 |
kettle | -0.029 |
Token | edy |
Token ID | 4716 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
eternity | +0.184 |
ust | +0.180 |
anymore | +0.175 |
accidents | +0.162 |
rated | +0.160 |
Neg logit contributions | |
kit | -0.212 |
acey | -0.170 |
tails | -0.168 |
comb | -0.168 |
printer | -0.168 |
Token | stuck |
Token ID | 7819 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ust | +0.104 |
ight | +0.091 |
rated | +0.087 |
uct | +0.087 |
eternity | +0.086 |
Neg logit contributions | |
kit | -0.111 |
sewing | -0.098 |
te | -0.097 |
brush | -0.096 |
coloring | -0.096 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
kit | +0.019 |
Stacy | +0.018 |
kettle | +0.017 |
tin | +0.017 |
sy | +0.017 |
Neg logit contributions | |
ust | -0.016 |
ight | -0.014 |
eternity | -0.014 |
all | -0.013 |
adventure | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
kit | +0.020 |
Stacy | +0.019 |
kettle | +0.018 |
sy | +0.017 |
bottle | +0.017 |
Neg logit contributions | |
ust | -0.023 |
ight | -0.020 |
eternity | -0.019 |
rated | -0.019 |
uct | -0.019 |
Token | sand |
Token ID | 6450 |
Feature activation | -8.80e-03 |
Pos logit contributions | |
Stacy | +0.010 |
kit | +0.010 |
kettle | +0.009 |
sy | +0.009 |
tin | +0.009 |
Neg logit contributions | |
ust | -0.009 |
ight | -0.008 |
adventure | -0.008 |
eternity | -0.007 |
all | -0.007 |
Token | named |
Token ID | 3706 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
ust | +0.102 |
adventure | +0.097 |
ight | +0.096 |
eternity | +0.092 |
all | +0.091 |
Neg logit contributions | |
Stacy | -0.062 |
kit | -0.060 |
kettle | -0.054 |
piping | -0.053 |
Grac | -0.053 |
Token | Cr |
Token ID | 3864 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Stacy | +0.101 |
Grac | +0.097 |
violet | +0.095 |
Elsa | +0.095 |
kit | +0.094 |
Neg logit contributions | |
ust | -0.082 |
ight | -0.073 |
wing | -0.066 |
rated | -0.065 |
urious | -0.065 |
Token | ust |
Token ID | 436 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
adventure | +0.140 |
eternity | +0.135 |
happening | +0.115 |
uct | +0.112 |
behind | +0.110 |
Neg logit contributions | |
Stacy | -0.300 |
acey | -0.286 |
kit | -0.283 |
te | -0.280 |
kettle | -0.279 |
Token | y |
Token ID | 88 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ust | +0.189 |
ight | +0.176 |
adventure | +0.174 |
eternity | +0.169 |
all | +0.165 |
Neg logit contributions | |
Stacy | -0.148 |
kit | -0.146 |
kettle | -0.135 |
violet | -0.129 |
sy | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.015 |
adventure | +0.015 |
eternity | +0.014 |
all | +0.014 |
Neg logit contributions | |
Stacy | -0.041 |
kit | -0.041 |
kettle | -0.039 |
sy | -0.038 |
Grac | -0.038 |
Token | Cr |
Token ID | 3864 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ust | +0.024 |
adventure | +0.022 |
ight | +0.021 |
all | +0.020 |
eternity | +0.020 |
Neg logit contributions | |
Stacy | -0.035 |
kit | -0.034 |
kettle | -0.033 |
sy | -0.031 |
Elsa | -0.031 |
Token | ust |
Token ID | 436 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
adventure | +0.083 |
eternity | +0.081 |
happening | +0.061 |
behind | +0.059 |
uct | +0.053 |
Neg logit contributions | |
Stacy | -0.306 |
acey | -0.301 |
kit | -0.296 |
Grac | -0.290 |
te | -0.290 |
Token | y |
Token ID | 88 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
ust | +0.161 |
ight | +0.149 |
adventure | +0.148 |
eternity | +0.144 |
all | +0.141 |
Neg logit contributions | |
Stacy | -0.131 |
kit | -0.130 |
kettle | -0.120 |
sy | -0.115 |
Grac | -0.115 |
Token | lived |
Token ID | 5615 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
Stacy | +0.009 |
kit | +0.009 |
kettle | +0.008 |
sy | +0.007 |
Grac | +0.007 |
Neg logit contributions | |
ust | -0.013 |
ight | -0.012 |
adventure | -0.012 |
eternity | -0.012 |
all | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ust | +0.047 |
ight | +0.042 |
adventure | +0.041 |
eternity | +0.040 |
all | +0.038 |
Neg logit contributions | |
Stacy | -0.069 |
kit | -0.068 |
kettle | -0.064 |
sy | -0.062 |
Grac | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
Stacy | +0.021 |
kit | +0.021 |
kettle | +0.019 |
violet | +0.019 |
Elsa | +0.019 |
Neg logit contributions | |
ust | -0.020 |
ight | -0.018 |
adventure | -0.018 |
eternity | -0.017 |
all | -0.017 |
Token | Cars |
Token ID | 25277 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
kit | +0.036 |
Stacy | +0.034 |
sy | +0.031 |
kettle | +0.031 |
tin | +0.030 |
Neg logit contributions | |
ust | -0.049 |
adventure | -0.044 |
ight | -0.044 |
all | -0.044 |
anymore | -0.043 |
Token | didn |
Token ID | 1422 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
Stacy | +0.010 |
kit | +0.010 |
kettle | +0.010 |
violet | +0.009 |
Grac | +0.009 |
Neg logit contributions | |
ust | -0.007 |
adventure | -0.006 |
ight | -0.006 |
eternity | -0.006 |
all | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
ust | +0.100 |
adventure | +0.093 |
ight | +0.092 |
eternity | +0.089 |
uct | +0.088 |
Neg logit contributions | |
kit | -0.046 |
Stacy | -0.045 |
sy | -0.041 |
kettle | -0.040 |
te | -0.038 |
Token | fly |
Token ID | 6129 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ust | +0.072 |
adventure | +0.066 |
ight | +0.063 |
eternity | +0.060 |
all | +0.060 |
Neg logit contributions | |
Stacy | -0.094 |
kit | -0.091 |
kettle | -0.087 |
violet | -0.084 |
piping | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
ust | +0.045 |
uct | +0.045 |
eternity | +0.042 |
ight | +0.042 |
urious | +0.040 |
Neg logit contributions | |
kit | -0.051 |
Stacy | -0.047 |
bottle | -0.046 |
sy | -0.046 |
te | -0.046 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ust | +0.004 |
ight | +0.004 |
uct | +0.003 |
all | +0.003 |
eternity | +0.003 |
Neg logit contributions | |
kit | -0.003 |
Stacy | -0.003 |
sy | -0.002 |
brush | -0.002 |
kettle | -0.002 |
Token | oes |
Token ID | 3028 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
uct | +0.270 |
ust | +0.265 |
eternity | +0.264 |
unexpected | +0.260 |
ight | +0.259 |
Neg logit contributions | |
kit | -0.131 |
kettle | -0.109 |
Stacy | -0.108 |
brush | -0.101 |
sy | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ust | +0.014 |
ight | +0.013 |
eternity | +0.012 |
adventure | +0.012 |
uct | +0.012 |
Neg logit contributions | |
kit | -0.019 |
Stacy | -0.019 |
sy | -0.018 |
kettle | -0.017 |
te | -0.017 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
kit | +0.028 |
Stacy | +0.027 |
kettle | +0.024 |
tin | +0.024 |
sy | +0.024 |
Neg logit contributions | |
ust | -0.045 |
ight | -0.041 |
adventure | -0.041 |
all | -0.041 |
eternity | -0.040 |
Token | L |
Token ID | 43 |
Feature activation | -6.69e-03 |
Pos logit contributions | |
ust | +0.059 |
ight | +0.055 |
adventure | +0.054 |
eternity | +0.053 |
all | +0.051 |
Neg logit contributions | |
kit | -0.041 |
Stacy | -0.041 |
kettle | -0.037 |
Elsa | -0.035 |
Grac | -0.035 |
Token | ily |
Token ID | 813 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
ust | +0.011 |
ight | +0.010 |
adventure | +0.010 |
eternity | +0.010 |
all | +0.010 |
Neg logit contributions | |
Stacy | -0.011 |
kit | -0.011 |
kettle | -0.010 |
sy | -0.010 |
violet | -0.010 |
Token | away |
Token ID | 1497 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ust | +0.021 |
ight | +0.019 |
adventure | +0.018 |
eternity | +0.018 |
all | +0.017 |
Neg logit contributions | |
kit | -0.030 |
Stacy | -0.030 |
kettle | -0.028 |
sy | -0.027 |
tin | -0.027 |
Token | from |
Token ID | 422 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
Stacy | +0.024 |
kit | +0.024 |
Grac | +0.023 |
sy | +0.023 |
kettle | +0.022 |
Neg logit contributions | |
ust | -0.015 |
ight | -0.014 |
uct | -0.014 |
eternity | -0.013 |
adventure | -0.013 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
Stacy | +0.003 |
kit | +0.003 |
kettle | +0.002 |
Elsa | +0.002 |
Grac | +0.002 |
Neg logit contributions | |
ust | -0.003 |
ight | -0.002 |
all | -0.002 |
adventure | -0.002 |
uct | -0.002 |
Token | things |
Token ID | 1243 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ust | +0.047 |
ight | +0.043 |
uct | +0.040 |
all | +0.039 |
rig | +0.036 |
Neg logit contributions | |
kit | -0.041 |
Stacy | -0.038 |
drawer | -0.036 |
sy | -0.036 |
throat | -0.036 |
Token | like |
Token ID | 588 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
ust | +0.023 |
ight | +0.021 |
urious | +0.021 |
eternity | +0.020 |
uct | +0.020 |
Neg logit contributions | |
kit | -0.028 |
Stacy | -0.025 |
sy | -0.024 |
Elsa | -0.024 |
tin | -0.023 |
Token | volcan |
Token ID | 17516 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ust | +0.053 |
ight | +0.049 |
eternity | +0.044 |
adventure | +0.043 |
uct | +0.043 |
Neg logit contributions | |
kit | -0.059 |
Stacy | -0.058 |
kettle | -0.054 |
sy | -0.054 |
Grac | -0.053 |
Token | oes |
Token ID | 3028 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
uct | +0.291 |
eternity | +0.280 |
unexpected | +0.275 |
adventure | +0.274 |
ight | +0.273 |
Neg logit contributions | |
kit | -0.094 |
paints | -0.080 |
kettle | -0.079 |
brush | -0.072 |
Did | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ust | +0.002 |
ight | +0.002 |
eternity | +0.001 |
uct | +0.001 |
adventure | +0.001 |
Neg logit contributions | |
kit | -0.002 |
Stacy | -0.002 |
sy | -0.002 |
kettle | -0.002 |
te | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
ust | +0.037 |
ight | +0.034 |
adventure | +0.033 |
eternity | +0.032 |
all | +0.031 |
Neg logit contributions | |
Stacy | -0.031 |
kit | -0.031 |
kettle | -0.029 |
Grac | -0.028 |
sy | -0.027 |
Token | Once |
Token ID | 7454 |
Feature activation | -6.69e-05 |
Pos logit contributions | |
ust | +0.072 |
ight | +0.064 |
eternity | +0.063 |
adventure | +0.063 |
rated | +0.062 |
Neg logit contributions | |
kit | -0.034 |
Stacy | -0.033 |
Did | -0.028 |
Elsa | -0.028 |
Grac | -0.027 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
ust | +0.000 |
eternity | +0.000 |
ight | +0.000 |
adventure | +0.000 |
ach | +0.000 |
Neg logit contributions | |
Stacy | -0.000 |
kit | -0.000 |
Grac | -0.000 |
kettle | -0.000 |
Elsa | -0.000 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
Stacy | +0.031 |
kit | +0.030 |
kettle | +0.028 |
sy | +0.027 |
Grac | +0.026 |
Neg logit contributions | |
ust | -0.042 |
ight | -0.039 |
adventure | -0.039 |
eternity | -0.037 |
all | -0.037 |
Token | Tom |
Token ID | 13787 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
ust | +0.058 |
ight | +0.053 |
adventure | +0.052 |
eternity | +0.052 |
uct | +0.049 |
Neg logit contributions | |
kit | -0.037 |
Stacy | -0.037 |
kettle | -0.033 |
Elsa | -0.032 |
te | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
ust | +0.034 |
ight | +0.031 |
adventure | +0.031 |
eternity | +0.029 |
all | +0.029 |
Neg logit contributions | |
Stacy | -0.039 |
kit | -0.039 |
kettle | -0.036 |
sy | -0.035 |
Grac | -0.035 |
Token | Mia |
Token ID | 32189 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
adventure | +0.050 |
ust | +0.047 |
all | +0.041 |
eternity | +0.041 |
ight | +0.039 |
Neg logit contributions | |
Stacy | -0.105 |
kit | -0.105 |
kettle | -0.104 |
sy | -0.098 |
tin | -0.098 |
Token | are |
Token ID | 389 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Stacy | +0.013 |
kit | +0.013 |
kettle | +0.011 |
te | +0.011 |
tin | +0.011 |
Neg logit contributions | |
ust | -0.020 |
ight | -0.019 |
eternity | -0.018 |
adventure | -0.018 |
all | -0.018 |
Token | friends |
Token ID | 2460 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
Stacy | +0.022 |
kit | +0.022 |
sy | +0.020 |
kettle | +0.020 |
violet | +0.020 |
Neg logit contributions | |
ust | -0.017 |
adventure | -0.015 |
ight | -0.015 |
all | -0.015 |
eternity | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
Stacy | +0.115 |
kit | +0.115 |
kettle | +0.106 |
te | +0.106 |
Elsa | +0.106 |
Neg logit contributions | |
ust | -0.076 |
ight | -0.066 |
adventure | -0.065 |
eternity | -0.062 |
rated | -0.060 |
Token | They |
Token ID | 1119 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
Stacy | +0.007 |
kit | +0.007 |
kettle | +0.006 |
sy | +0.006 |
Grac | +0.006 |
Neg logit contributions | |
ust | -0.010 |
ight | -0.009 |
adventure | -0.009 |
eternity | -0.009 |
all | -0.009 |
Token | like |
Token ID | 588 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
kit | +0.033 |
Stacy | +0.032 |
kettle | +0.031 |
sy | +0.031 |
throat | +0.029 |
Neg logit contributions | |
adventure | -0.013 |
ust | -0.013 |
all | -0.011 |
ight | -0.011 |
exciting | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
adventure | +0.031 |
ust | +0.029 |
all | +0.026 |
eternity | +0.025 |
happening | +0.024 |
Neg logit contributions | |
Stacy | -0.057 |
kit | -0.055 |
kettle | -0.053 |
piping | -0.051 |
tin | -0.051 |
Token | play |
Token ID | 711 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
ust | +0.022 |
adventure | +0.021 |
ight | +0.020 |
eternity | +0.019 |
all | +0.019 |
Neg logit contributions | |
Stacy | -0.024 |
kit | -0.024 |
kettle | -0.022 |
sy | -0.021 |
Grac | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
Stacy | +0.051 |
kit | +0.050 |
kettle | +0.048 |
sy | +0.046 |
tin | +0.046 |
Neg logit contributions | |
ust | -0.027 |
ight | -0.024 |
adventure | -0.023 |
eternity | -0.022 |
all | -0.022 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
ust | +0.045 |
adventure | +0.042 |
ight | +0.042 |
eternity | +0.040 |
all | +0.039 |
Neg logit contributions | |
Stacy | -0.041 |
kit | -0.040 |
kettle | -0.037 |
sy | -0.037 |
violet | -0.036 |
Token | many |
Token ID | 867 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ust | +0.027 |
adventure | +0.026 |
ight | +0.025 |
eternity | +0.024 |
all | +0.023 |
Neg logit contributions | |
Stacy | -0.035 |
kit | -0.034 |
kettle | -0.032 |
sy | -0.031 |
violet | -0.031 |
Token | shiny |
Token ID | 22441 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
kit | +0.019 |
Stacy | +0.019 |
kettle | +0.018 |
tin | +0.017 |
te | +0.017 |
Neg logit contributions | |
ust | -0.022 |
ight | -0.020 |
eternity | -0.020 |
all | -0.020 |
adventure | -0.019 |
Token | things |
Token ID | 1243 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
ust | +0.024 |
adventure | +0.023 |
ight | +0.022 |
eternity | +0.021 |
anymore | +0.021 |
Neg logit contributions | |
Stacy | -0.033 |
kit | -0.032 |
kettle | -0.030 |
violet | -0.029 |
Elsa | -0.029 |
Token | inside |
Token ID | 2641 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
ust | +0.038 |
ight | +0.033 |
adventure | +0.032 |
eternity | +0.031 |
all | +0.030 |
Neg logit contributions | |
kit | -0.060 |
Stacy | -0.060 |
kettle | -0.057 |
tin | -0.055 |
sy | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
Stacy | +0.112 |
kit | +0.110 |
kettle | +0.105 |
sy | +0.103 |
violet | +0.102 |
Neg logit contributions | |
ust | -0.049 |
adventure | -0.043 |
ight | -0.043 |
eternity | -0.040 |
all | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ust | +0.006 |
adventure | +0.006 |
ight | +0.006 |
eternity | +0.005 |
all | +0.005 |
Neg logit contributions | |
kit | -0.005 |
Stacy | -0.005 |
sy | -0.004 |
groom | -0.004 |
piping | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
kit | +0.036 |
Stacy | +0.035 |
sy | +0.034 |
kettle | +0.033 |
piping | +0.033 |
Neg logit contributions | |
ust | -0.029 |
adventure | -0.028 |
ight | -0.026 |
behind | -0.025 |
unexpected | -0.024 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
Stacy | +0.045 |
kit | +0.044 |
kettle | +0.041 |
sy | +0.041 |
Did | +0.039 |
Neg logit contributions | |
ust | -0.035 |
adventure | -0.034 |
ight | -0.032 |
happening | -0.030 |
behind | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ust | +0.002 |
ight | +0.001 |
uct | +0.001 |
eternity | +0.001 |
rated | +0.001 |
Neg logit contributions | |
kit | -0.002 |
Stacy | -0.002 |
kettle | -0.002 |
te | -0.002 |
Grac | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
kit | +0.010 |
Stacy | +0.010 |
kettle | +0.009 |
te | +0.009 |
throat | +0.009 |
Neg logit contributions | |
ust | -0.007 |
ight | -0.006 |
uct | -0.006 |
eternity | -0.006 |
adventure | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
kit | +0.024 |
Stacy | +0.023 |
kettle | +0.022 |
sy | +0.022 |
tin | +0.021 |
Neg logit contributions | |
ust | -0.023 |
ight | -0.021 |
adventure | -0.021 |
eternity | -0.021 |
all | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
ust | +0.005 |
ight | +0.005 |
adventure | +0.004 |
eternity | +0.004 |
rated | +0.004 |
Neg logit contributions | |
Stacy | -0.005 |
kit | -0.004 |
kettle | -0.004 |
violet | -0.004 |
Grac | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
ust | +0.004 |
adventure | +0.004 |
ight | +0.004 |
eternity | +0.004 |
all | +0.003 |
Neg logit contributions | |
Stacy | -0.004 |
kit | -0.004 |
kettle | -0.004 |
violet | -0.004 |
sy | -0.004 |
Token | people |
Token ID | 661 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
Stacy | +0.002 |
kit | +0.002 |
kettle | +0.002 |
sy | +0.002 |
te | +0.002 |
Neg logit contributions | |
ust | -0.002 |
ight | -0.002 |
adventure | -0.002 |
eternity | -0.002 |
all | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
Stacy | +0.032 |
kit | +0.031 |
kettle | +0.029 |
sy | +0.028 |
Grac | +0.028 |
Neg logit contributions | |
ust | -0.031 |
ight | -0.029 |
adventure | -0.029 |
eternity | -0.028 |
all | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Stacy | +0.126 |
kit | +0.126 |
kettle | +0.120 |
sy | +0.119 |
tin | +0.117 |
Neg logit contributions | |
adventure | -0.069 |
ust | -0.064 |
eternity | -0.061 |
anymore | -0.060 |
ight | -0.060 |
Token | truck |
Token ID | 7779 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
Stacy | +0.038 |
kit | +0.037 |
Did | +0.034 |
sy | +0.034 |
Grac | +0.034 |
Neg logit contributions | |
adventure | -0.029 |
ust | -0.028 |
ight | -0.026 |
unexpected | -0.025 |
eternity | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
Stacy | +0.028 |
kit | +0.027 |
kettle | +0.025 |
sy | +0.025 |
Grac | +0.025 |
Neg logit contributions | |
ust | -0.031 |
ight | -0.029 |
adventure | -0.029 |
eternity | -0.028 |
all | -0.027 |
Token | outside |
Token ID | 2354 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
adventure | +0.026 |
ust | +0.024 |
eternity | +0.022 |
behind | +0.021 |
anymore | +0.021 |
Neg logit contributions | |
kit | -0.040 |
Stacy | -0.040 |
kettle | -0.038 |
piping | -0.037 |
violet | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
Stacy | +0.079 |
kit | +0.078 |
sy | +0.073 |
kettle | +0.073 |
violet | +0.072 |
Neg logit contributions | |
ust | -0.046 |
adventure | -0.043 |
ight | -0.041 |
eternity | -0.040 |
anymore | -0.040 |
Token | all |
Token ID | 477 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
ust | +0.023 |
ight | +0.021 |
adventure | +0.021 |
eternity | +0.020 |
all | +0.020 |
Neg logit contributions | |
Stacy | -0.030 |
kit | -0.029 |
kettle | -0.027 |
sy | -0.027 |
Grac | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +4.27e-03 |
Pos logit contributions | |
Stacy | +0.019 |
kit | +0.019 |
kettle | +0.018 |
sy | +0.017 |
Grac | +0.017 |
Neg logit contributions | |
ust | -0.014 |
ight | -0.013 |
adventure | -0.013 |
eternity | -0.012 |
all | -0.012 |
Token | fun |
Token ID | 1257 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
kit | +0.008 |
Stacy | +0.008 |
brush | +0.007 |
violet | +0.007 |
kettle | +0.007 |
Neg logit contributions | |
ust | -0.006 |
ight | -0.006 |
all | -0.005 |
eternity | -0.005 |
uct | -0.005 |
Token | times |
Token ID | 1661 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
ust | +0.014 |
ight | +0.013 |
eternity | +0.012 |
all | +0.012 |
adventure | +0.012 |
Neg logit contributions | |
Stacy | -0.009 |
kit | -0.009 |
kettle | -0.008 |
Grac | -0.008 |
te | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
Stacy | +0.003 |
kit | +0.003 |
kettle | +0.003 |
sy | +0.002 |
Grac | +0.002 |
Neg logit contributions | |
ust | -0.006 |
ight | -0.005 |
adventure | -0.005 |
eternity | -0.005 |
all | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
ust | +0.075 |
ight | +0.071 |
eternity | +0.069 |
adventure | +0.068 |
all | +0.067 |
Neg logit contributions | |
Stacy | -0.032 |
kit | -0.030 |
kettle | -0.025 |
Elsa | -0.025 |
Grac | -0.025 |
Token | at |
Token ID | 379 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
kit | +0.082 |
Stacy | +0.080 |
kettle | +0.072 |
te | +0.072 |
Elsa | +0.071 |
Neg logit contributions | |
ust | -0.080 |
ight | -0.071 |
eternity | -0.070 |
adventure | -0.066 |
uct | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ust | +0.055 |
ight | +0.050 |
eternity | +0.045 |
adventure | +0.045 |
all | +0.044 |
Neg logit contributions | |
Stacy | -0.058 |
kit | -0.058 |
kettle | -0.052 |
Grac | -0.052 |
Elsa | -0.052 |
Token | park |
Token ID | 3952 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ust | +0.051 |
ight | +0.047 |
all | +0.044 |
eternity | +0.044 |
ach | +0.043 |
Neg logit contributions | |
kit | -0.041 |
Stacy | -0.040 |
violet | -0.038 |
kettle | -0.037 |
te | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
kit | +0.030 |
Stacy | +0.030 |
kettle | +0.028 |
sy | +0.027 |
tin | +0.027 |
Neg logit contributions | |
ust | -0.019 |
ight | -0.017 |
adventure | -0.016 |
eternity | -0.015 |
all | -0.015 |
Token | smiled |
Token ID | 13541 |
Feature activation | -8.69e-04 |
Pos logit contributions | |
adventure | +0.050 |
ust | +0.049 |
eternity | +0.046 |
ight | +0.045 |
all | +0.045 |
Neg logit contributions | |
kit | -0.057 |
Stacy | -0.057 |
kettle | -0.055 |
sy | -0.053 |
piping | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
ust | +0.009 |
ight | +0.008 |
eternity | +0.008 |
uct | +0.007 |
all | +0.007 |
Neg logit contributions | |
kit | -0.006 |
Stacy | -0.006 |
kettle | -0.005 |
bottle | -0.005 |
tin | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
Stacy | +0.013 |
kit | +0.013 |
kettle | +0.012 |
sy | +0.012 |
Grac | +0.012 |
Neg logit contributions | |
ust | -0.008 |
ight | -0.007 |
adventure | -0.007 |
eternity | -0.007 |
all | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Stacy | +0.013 |
kit | +0.013 |
kettle | +0.012 |
sy | +0.011 |
Grac | +0.011 |
Neg logit contributions | |
ust | -0.022 |
ight | -0.020 |
adventure | -0.020 |
eternity | -0.020 |
all | -0.019 |
Token | knew |
Token ID | 2993 |
Feature activation | -6.37e-03 |
Pos logit contributions | |
ust | +0.040 |
ight | +0.037 |
eternity | +0.037 |
adventure | +0.036 |
all | +0.036 |
Neg logit contributions | |
Stacy | -0.031 |
kit | -0.030 |
kettle | -0.029 |
tin | -0.028 |
Grac | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
ust | +0.011 |
ight | +0.010 |
eternity | +0.010 |
adventure | +0.010 |
all | +0.009 |
Neg logit contributions | |
Stacy | -0.010 |
kit | -0.010 |
kettle | -0.009 |
Grac | -0.009 |
violet | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
ust | +0.082 |
ight | +0.078 |
adventure | +0.076 |
eternity | +0.076 |
all | +0.075 |
Neg logit contributions | |
Stacy | -0.042 |
kit | -0.042 |
kettle | -0.037 |
Grac | -0.035 |
tin | -0.035 |
Token | found |
Token ID | 1043 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
kit | +0.080 |
Stacy | +0.079 |
kettle | +0.073 |
tin | +0.070 |
violet | +0.070 |
Neg logit contributions | |
ust | -0.082 |
ight | -0.076 |
eternity | -0.072 |
adventure | -0.071 |
all | -0.070 |
Token | what |
Token ID | 644 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
ust | +0.018 |
ight | +0.016 |
adventure | +0.015 |
eternity | +0.015 |
all | +0.015 |
Neg logit contributions | |
kit | -0.019 |
Stacy | -0.019 |
kettle | -0.018 |
Grac | -0.017 |
tin | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
Stacy | +0.011 |
kit | +0.011 |
kettle | +0.010 |
sy | +0.010 |
Grac | +0.010 |
Neg logit contributions | |
ust | -0.016 |
ight | -0.015 |
adventure | -0.014 |
eternity | -0.014 |
all | -0.014 |
Token | were |
Token ID | 547 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ust | +0.053 |
ight | +0.051 |
eternity | +0.049 |
all | +0.048 |
uct | +0.047 |
Neg logit contributions | |
kit | -0.022 |
Stacy | -0.021 |
Did | -0.019 |
tin | -0.019 |
Grac | -0.018 |
Token | looking |
Token ID | 2045 |
Feature activation | +7.21e-04 |
Pos logit contributions | |
kit | +0.034 |
Stacy | +0.031 |
kettle | +0.031 |
te | +0.030 |
tin | +0.030 |
Neg logit contributions | |
ust | -0.036 |
ight | -0.033 |
eternity | -0.031 |
uct | -0.030 |
urious | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
ust | +0.044 |
ight | +0.038 |
adventure | +0.038 |
eternity | +0.036 |
all | +0.034 |
Neg logit contributions | |
Stacy | -0.092 |
kit | -0.091 |
kettle | -0.087 |
sy | -0.085 |
violet | -0.084 |
Token | She |
Token ID | 1375 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
ust | +0.017 |
ight | +0.016 |
adventure | +0.016 |
eternity | +0.015 |
all | +0.015 |
Neg logit contributions | |
Stacy | -0.013 |
kit | -0.013 |
kettle | -0.012 |
sy | -0.011 |
te | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -1.01e-03 |
Pos logit contributions | |
kit | +0.010 |
Stacy | +0.010 |
kettle | +0.010 |
sy | +0.009 |
violet | +0.009 |
Neg logit contributions | |
ust | -0.013 |
adventure | -0.012 |
ight | -0.012 |
eternity | -0.011 |
all | -0.011 |
Token | three |
Token ID | 1115 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
adventure | +0.001 |
ust | +0.001 |
all | +0.001 |
behind | +0.001 |
exciting | +0.001 |
Neg logit contributions | |
kit | -0.002 |
sy | -0.002 |
Stacy | -0.002 |
cartridge | -0.002 |
cutter | -0.002 |
Token | years |
Token ID | 812 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
Stacy | +0.154 |
kit | +0.153 |
te | +0.150 |
kettle | +0.149 |
tin | +0.146 |
Neg logit contributions | |
ust | -0.082 |
ight | -0.068 |
eternity | -0.068 |
all | -0.067 |
adventure | -0.065 |
Token | old |
Token ID | 1468 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
Stacy | +0.008 |
kit | +0.007 |
kettle | +0.007 |
te | +0.007 |
Grac | +0.007 |
Neg logit contributions | |
ust | -0.007 |
ight | -0.006 |
eternity | -0.005 |
adventure | -0.005 |
uct | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Stacy | +0.099 |
kit | +0.097 |
kettle | +0.095 |
piping | +0.092 |
sy | +0.092 |
Neg logit contributions | |
ust | -0.031 |
adventure | -0.031 |
anymore | -0.027 |
ight | -0.026 |
eternity | -0.026 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
exciting | +0.024 |
interesting | +0.022 |
adventure | +0.022 |
ust | +0.022 |
amazing | +0.021 |
Neg logit contributions | |
kit | -0.037 |
sy | -0.036 |
kettle | -0.035 |
te | -0.033 |
cartridge | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
ust | +0.039 |
adventure | +0.038 |
ight | +0.035 |
eternity | +0.035 |
all | +0.034 |
Neg logit contributions | |
Stacy | -0.051 |
kit | -0.050 |
kettle | -0.047 |
sy | -0.045 |
violet | -0.045 |
Token | water |
Token ID | 1660 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ust | +0.008 |
adventure | +0.008 |
ight | +0.007 |
eternity | +0.007 |
all | +0.007 |
Neg logit contributions | |
Stacy | -0.009 |
kit | -0.008 |
kettle | -0.008 |
sy | -0.008 |
violet | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Stacy | +0.025 |
kit | +0.024 |
kettle | +0.023 |
sy | +0.023 |
violet | +0.022 |
Neg logit contributions | |
ust | -0.010 |
adventure | -0.009 |
ight | -0.008 |
anymore | -0.008 |
eternity | -0.007 |
Token | how |
Token ID | 703 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
Stacy | +0.078 |
kit | +0.077 |
kettle | +0.072 |
Grac | +0.070 |
Elsa | +0.070 |
Neg logit contributions | |
ust | -0.068 |
ight | -0.062 |
adventure | -0.060 |
eternity | -0.059 |
all | -0.057 |
Token | much |
Token ID | 881 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
Stacy | +0.056 |
kit | +0.055 |
kettle | +0.051 |
sy | +0.050 |
Grac | +0.049 |
Neg logit contributions | |
ust | -0.050 |
ight | -0.046 |
adventure | -0.045 |
eternity | -0.044 |
all | -0.043 |
Token | her |
Token ID | 607 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
ust | +0.027 |
ight | +0.025 |
adventure | +0.025 |
eternity | +0.024 |
all | +0.023 |
Neg logit contributions | |
Stacy | -0.024 |
kit | -0.023 |
kettle | -0.022 |
sy | -0.021 |
violet | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
kit | +0.008 |
Stacy | +0.008 |
sy | +0.007 |
kettle | +0.007 |
piping | +0.007 |
Neg logit contributions | |
ust | -0.010 |
ight | -0.009 |
eternity | -0.009 |
all | -0.008 |
uct | -0.008 |
Token | my |
Token ID | 1820 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
Stacy | +0.010 |
kettle | +0.009 |
kit | +0.009 |
violet | +0.009 |
sy | +0.009 |
Neg logit contributions | |
ust | -0.006 |
ight | -0.006 |
adventure | -0.006 |
all | -0.005 |
eternity | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ust | +0.015 |
adventure | +0.015 |
ight | +0.014 |
all | +0.014 |
eternity | +0.014 |
Neg logit contributions | |
Stacy | -0.013 |
kit | -0.013 |
kettle | -0.012 |
violet | -0.012 |
sy | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
ust | +0.032 |
adventure | +0.030 |
ight | +0.029 |
all | +0.029 |
eternity | +0.028 |
Neg logit contributions | |
Stacy | -0.028 |
kit | -0.028 |
kettle | -0.027 |
sy | -0.025 |
violet | -0.025 |
Token | give |
Token ID | 1577 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ust | +0.009 |
adventure | +0.009 |
ight | +0.009 |
eternity | +0.008 |
all | +0.008 |
Neg logit contributions | |
Stacy | -0.009 |
kit | -0.009 |
kettle | -0.008 |
sy | -0.008 |
violet | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +9.72e-04 |
Pos logit contributions | |
Stacy | +0.035 |
kit | +0.034 |
kettle | +0.032 |
sy | +0.031 |
violet | +0.031 |
Neg logit contributions | |
ust | -0.042 |
ight | -0.039 |
adventure | -0.039 |
eternity | -0.037 |
all | -0.037 |
Token | things |
Token ID | 1243 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
Stacy | +0.002 |
kit | +0.002 |
kettle | +0.002 |
violet | +0.002 |
sy | +0.002 |
Neg logit contributions | |
ust | -0.001 |
adventure | -0.001 |
ight | -0.001 |
eternity | -0.001 |
all | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
ust | +0.026 |
ight | +0.024 |
eternity | +0.023 |
adventure | +0.023 |
all | +0.021 |
Neg logit contributions | |
kit | -0.033 |
Stacy | -0.033 |
tin | -0.030 |
kettle | -0.030 |
Grac | -0.030 |
Token | stopped |
Token ID | 5025 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ust | +0.041 |
ight | +0.038 |
adventure | +0.038 |
eternity | +0.037 |
all | +0.036 |
Neg logit contributions | |
Stacy | -0.031 |
kit | -0.031 |
kettle | -0.029 |
sy | -0.027 |
Grac | -0.027 |
Token | soon |
Token ID | 2582 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
ust | +0.033 |
ight | +0.031 |
adventure | +0.029 |
eternity | +0.028 |
uct | +0.028 |
Neg logit contributions | |
Stacy | -0.036 |
kit | -0.036 |
kettle | -0.034 |
sy | -0.033 |
Grac | -0.033 |
Token | after |
Token ID | 706 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
kit | +0.014 |
Stacy | +0.014 |
kettle | +0.013 |
sy | +0.013 |
tin | +0.013 |
Neg logit contributions | |
ust | -0.009 |
ight | -0.008 |
adventure | -0.007 |
eternity | -0.007 |
all | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
ust | +0.053 |
ight | +0.045 |
rig | +0.042 |
rated | +0.041 |
urious | +0.040 |
Neg logit contributions | |
kit | -0.038 |
coloring | -0.037 |
Stacy | -0.037 |
kettle | -0.036 |
sisters | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
Stacy | +0.004 |
kit | +0.004 |
kettle | +0.004 |
tin | +0.004 |
te | +0.003 |
Neg logit contributions | |
ust | -0.003 |
ight | -0.003 |
adventure | -0.003 |
eternity | -0.002 |
all | -0.002 |
Token | when |
Token ID | 618 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ust | +0.055 |
ight | +0.047 |
ach | +0.044 |
iver | +0.043 |
end | +0.043 |
Neg logit contributions | |
kit | -0.056 |
Stacy | -0.056 |
piping | -0.053 |
Did | -0.052 |
tin | -0.052 |
Token | it |
Token ID | 340 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
Stacy | +0.027 |
kit | +0.026 |
piping | +0.025 |
kettle | +0.024 |
Did | +0.023 |
Neg logit contributions | |
ust | -0.040 |
ight | -0.037 |
rig | -0.034 |
ach | -0.033 |
iver | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ust | +0.065 |
ight | +0.060 |
eternity | +0.060 |
adventure | +0.059 |
ach | +0.056 |
Neg logit contributions | |
Stacy | -0.037 |
kit | -0.036 |
kettle | -0.035 |
te | -0.033 |
tin | -0.031 |
Token | over |
Token ID | 625 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
kit | +0.029 |
kettle | +0.029 |
Stacy | +0.029 |
brush | +0.028 |
te | +0.027 |
Neg logit contributions | |
ust | -0.025 |
ight | -0.022 |
eternity | -0.021 |
urious | -0.021 |
adventure | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
kit | +0.029 |
Stacy | +0.028 |
kettle | +0.027 |
tin | +0.026 |
Grac | +0.026 |
Neg logit contributions | |
ust | -0.031 |
ight | -0.028 |
adventure | -0.025 |
eternity | -0.025 |
uct | -0.025 |
Token | John |
Token ID | 1757 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
Stacy | +0.013 |
kit | +0.013 |
kettle | +0.012 |
Did | +0.012 |
tin | +0.012 |
Neg logit contributions | |
ust | -0.014 |
ight | -0.013 |
ach | -0.012 |
adventure | -0.012 |
iver | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
ust | +0.051 |
ight | +0.047 |
adventure | +0.047 |
eternity | +0.045 |
all | +0.044 |
Neg logit contributions | |
Stacy | -0.055 |
kit | -0.054 |
kettle | -0.050 |
sy | -0.049 |
Grac | -0.048 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
Stacy | +0.029 |
kit | +0.028 |
kettle | +0.027 |
violet | +0.026 |
Grac | +0.026 |
Neg logit contributions | |
ust | -0.030 |
ight | -0.029 |
adventure | -0.029 |
eternity | -0.027 |
all | -0.027 |
Token | that |
Token ID | 326 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
kit | +0.025 |
Stacy | +0.025 |
kettle | +0.023 |
sy | +0.023 |
Elsa | +0.022 |
Neg logit contributions | |
ust | -0.023 |
ight | -0.021 |
eternity | -0.020 |
adventure | -0.020 |
all | -0.018 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
Stacy | +0.019 |
kit | +0.019 |
sy | +0.018 |
Grac | +0.017 |
kettle | +0.017 |
Neg logit contributions | |
ust | -0.023 |
ight | -0.021 |
uct | -0.019 |
eternity | -0.019 |
ach | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
ust | +0.007 |
ight | +0.007 |
uct | +0.006 |
all | +0.006 |
eternity | +0.006 |
Neg logit contributions | |
kit | -0.006 |
Stacy | -0.006 |
sy | -0.005 |
Elsa | -0.005 |
brush | -0.005 |
Token | even |
Token ID | 772 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
ust | +0.002 |
ight | +0.002 |
eternity | +0.002 |
uct | +0.002 |
adventure | +0.002 |
Neg logit contributions | |
Stacy | -0.002 |
kit | -0.002 |
sy | -0.002 |
kettle | -0.002 |
Grac | -0.002 |
Token | when |
Token ID | 618 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
ust | +0.026 |
ight | +0.024 |
eternity | +0.023 |
adventure | +0.023 |
all | +0.022 |
Neg logit contributions | |
Stacy | -0.032 |
kit | -0.032 |
sy | -0.029 |
kettle | -0.029 |
tin | -0.029 |
Token | we |
Token ID | 356 |
Feature activation | +8.25e-03 |
Pos logit contributions | |
Stacy | +0.048 |
kit | +0.048 |
kettle | +0.043 |
sy | +0.043 |
Grac | +0.043 |
Neg logit contributions | |
ust | -0.050 |
ight | -0.047 |
eternity | -0.042 |
uct | -0.042 |
adventure | -0.042 |
Token | feel |
Token ID | 1254 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
kit | +0.011 |
Stacy | +0.011 |
brush | +0.010 |
sy | +0.010 |
kettle | +0.010 |
Neg logit contributions | |
ust | -0.016 |
ight | -0.015 |
eternity | -0.015 |
adventure | -0.015 |
all | -0.014 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
Stacy | +0.068 |
kit | +0.068 |
kettle | +0.063 |
sy | +0.063 |
tin | +0.061 |
Neg logit contributions | |
ust | -0.062 |
ight | -0.056 |
adventure | -0.054 |
eternity | -0.053 |
all | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
kit | +0.030 |
Stacy | +0.030 |
kettle | +0.028 |
sy | +0.028 |
tin | +0.027 |
Neg logit contributions | |
ust | -0.022 |
ight | -0.020 |
adventure | -0.018 |
eternity | -0.018 |
uct | -0.018 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
Stacy | +0.044 |
kit | +0.044 |
kettle | +0.044 |
sy | +0.042 |
piping | +0.041 |
Neg logit contributions | |
ust | -0.039 |
adventure | -0.039 |
all | -0.036 |
ight | -0.036 |
eternity | -0.033 |
Token | proud |
Token ID | 6613 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
kit | +0.063 |
Stacy | +0.061 |
kettle | +0.060 |
sy | +0.058 |
tin | +0.056 |
Neg logit contributions | |
ust | -0.039 |
adventure | -0.036 |
ight | -0.035 |
all | -0.034 |
unexpected | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Stacy | +0.073 |
kit | +0.072 |
kettle | +0.070 |
piping | +0.069 |
sy | +0.068 |
Neg logit contributions | |
ust | -0.039 |
adventure | -0.038 |
all | -0.035 |
ight | -0.035 |
eternity | -0.033 |
Token | herself |
Token ID | 5223 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
Stacy | +0.046 |
kit | +0.045 |
Grac | +0.041 |
kettle | +0.041 |
Elsa | +0.041 |
Neg logit contributions | |
ust | -0.045 |
ight | -0.041 |
adventure | -0.039 |
eternity | -0.038 |
all | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
kit | +0.035 |
Stacy | +0.035 |
kettle | +0.032 |
sy | +0.031 |
Elsa | +0.031 |
Neg logit contributions | |
ust | -0.030 |
ight | -0.028 |
adventure | -0.026 |
eternity | -0.026 |
all | -0.025 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
adventure | +0.018 |
ust | +0.017 |
exciting | +0.016 |
all | +0.016 |
unexpected | +0.016 |
Neg logit contributions | |
kettle | -0.022 |
Stacy | -0.021 |
kit | -0.021 |
sy | -0.020 |
te | -0.020 |
Token | that |
Token ID | 326 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ust | +0.002 |
adventure | +0.002 |
ight | +0.002 |
all | +0.002 |
eternity | +0.002 |
Neg logit contributions | |
Stacy | -0.003 |
kit | -0.003 |
kettle | -0.003 |
sy | -0.003 |
te | -0.003 |
Token | organizing |
Token ID | 16924 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Stacy | +0.031 |
kit | +0.031 |
kettle | +0.029 |
sy | +0.028 |
violet | +0.027 |
Neg logit contributions | |
ust | -0.036 |
ight | -0.033 |
adventure | -0.033 |
eternity | -0.032 |
all | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
Stacy | +0.046 |
kit | +0.044 |
kettle | +0.044 |
violet | +0.043 |
sy | +0.042 |
Neg logit contributions | |
ust | -0.040 |
adventure | -0.038 |
ight | -0.037 |
unexpected | -0.035 |
anymore | -0.035 |
Token | learning |
Token ID | 4673 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
adventure | +0.014 |
ust | +0.014 |
happening | +0.013 |
all | +0.013 |
ight | +0.013 |
Neg logit contributions | |
Stacy | -0.017 |
kettle | -0.016 |
kit | -0.016 |
piping | -0.015 |
te | -0.015 |
Token | new |
Token ID | 649 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
ust | +0.010 |
adventure | +0.009 |
ight | +0.009 |
eternity | +0.008 |
all | +0.008 |
Neg logit contributions | |
Stacy | -0.014 |
kit | -0.014 |
kettle | -0.013 |
sy | -0.013 |
violet | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
kit | +0.028 |
Stacy | +0.026 |
sy | +0.026 |
kettle | +0.025 |
tin | +0.024 |
Neg logit contributions | |
ust | -0.028 |
ight | -0.025 |
all | -0.024 |
adventure | -0.024 |
eternity | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
ust | +0.005 |
adventure | +0.005 |
ight | +0.005 |
all | +0.004 |
unexpected | +0.004 |
Neg logit contributions | |
kit | -0.006 |
Stacy | -0.005 |
kettle | -0.005 |
sy | -0.005 |
Grac | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
ust | +0.002 |
adventure | +0.002 |
ight | +0.002 |
eternity | +0.002 |
all | +0.002 |
Neg logit contributions | |
Stacy | -0.003 |
kit | -0.003 |
kettle | -0.003 |
sy | -0.003 |
Grac | -0.003 |
Token | best |
Token ID | 1266 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Stacy | +0.030 |
kit | +0.029 |
kettle | +0.026 |
Grac | +0.026 |
sy | +0.026 |
Neg logit contributions | |
ust | -0.037 |
adventure | -0.035 |
ight | -0.035 |
eternity | -0.033 |
all | -0.032 |
Token | cake |
Token ID | 12187 |
Feature activation | +6.31e-03 |
Pos logit contributions | |
Stacy | +0.024 |
kit | +0.024 |
kettle | +0.022 |
sy | +0.021 |
tin | +0.021 |
Neg logit contributions | |
ust | -0.037 |
ight | -0.034 |
adventure | -0.034 |
eternity | -0.033 |
all | -0.032 |
Token | ever |
Token ID | 1683 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
Stacy | +0.014 |
kit | +0.014 |
kettle | +0.013 |
sy | +0.013 |
Grac | +0.013 |
Neg logit contributions | |
ust | -0.007 |
ight | -0.006 |
adventure | -0.006 |
eternity | -0.006 |
all | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +8.96e-03 |
Pos logit contributions | |
ust | +0.082 |
eternity | +0.071 |
uct | +0.070 |
ight | +0.070 |
iver | +0.069 |
Neg logit contributions | |
kit | -0.071 |
coloring | -0.066 |
kettle | -0.066 |
shone | -0.065 |
tin | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
kit | +0.017 |
Stacy | +0.016 |
sy | +0.015 |
kettle | +0.015 |
tin | +0.015 |
Neg logit contributions | |
ust | -0.013 |
ight | -0.012 |
all | -0.012 |
adventure | -0.012 |
eternity | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
ust | +0.008 |
ight | +0.007 |
adventure | +0.007 |
eternity | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
Stacy | -0.010 |
kit | -0.009 |
kettle | -0.009 |
violet | -0.009 |
te | -0.009 |
Token | They |
Token ID | 2990 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ust | +0.006 |
ight | +0.005 |
adventure | +0.005 |
eternity | +0.005 |
all | +0.005 |
Neg logit contributions | |
Stacy | -0.007 |
kit | -0.006 |
kettle | -0.006 |
sy | -0.006 |
Grac | -0.006 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
kit | +0.042 |
Stacy | +0.041 |
kettle | +0.038 |
sy | +0.038 |
Did | +0.036 |
Neg logit contributions | |
ust | -0.045 |
adventure | -0.042 |
ight | -0.042 |
eternity | -0.040 |
all | -0.039 |
Token | it |
Token ID | 340 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
kit | +0.074 |
Stacy | +0.073 |
sy | +0.071 |
kettle | +0.070 |
violet | +0.069 |
Neg logit contributions | |
adventure | -0.054 |
ust | -0.052 |
eternity | -0.049 |
ight | -0.049 |
anymore | -0.048 |
Token | angrily |
Token ID | 34425 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ust | +0.045 |
ight | +0.042 |
adventure | +0.041 |
eternity | +0.041 |
all | +0.040 |
Neg logit contributions | |
Stacy | -0.032 |
kit | -0.031 |
kettle | -0.029 |
sy | -0.028 |
te | -0.028 |
Token | grow |
Token ID | 1663 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ust | +0.040 |
ight | +0.037 |
adventure | +0.036 |
eternity | +0.035 |
all | +0.035 |
Neg logit contributions | |
Stacy | -0.029 |
kit | -0.029 |
kettle | -0.026 |
sy | -0.025 |
tin | -0.025 |
Token | led |
Token ID | 992 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ust | +0.026 |
adventure | +0.024 |
eternity | +0.023 |
uct | +0.022 |
all | +0.022 |
Neg logit contributions | |
Stacy | -0.030 |
kit | -0.029 |
kettle | -0.029 |
tin | -0.028 |
te | -0.028 |
Token | at |
Token ID | 379 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ust | +0.044 |
uct | +0.042 |
ight | +0.040 |
iver | +0.038 |
all | +0.038 |
Neg logit contributions | |
kit | -0.035 |
tin | -0.034 |
Stacy | -0.032 |
bottle | -0.032 |
shone | -0.031 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
ust | +0.046 |
ight | +0.041 |
uct | +0.038 |
iver | +0.037 |
all | +0.037 |
Neg logit contributions | |
Stacy | -0.040 |
kit | -0.039 |
kettle | -0.036 |
Grac | -0.036 |
Elsa | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
ust | +0.041 |
ight | +0.036 |
adventure | +0.035 |
eternity | +0.034 |
all | +0.032 |
Neg logit contributions | |
Stacy | -0.063 |
kit | -0.063 |
kettle | -0.058 |
sy | -0.057 |
Elsa | -0.057 |
Token | Dave |
Token ID | 9935 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ust | +0.027 |
adventure | +0.026 |
ight | +0.024 |
eternity | +0.024 |
all | +0.023 |
Neg logit contributions | |
Stacy | -0.033 |
kit | -0.033 |
kettle | -0.031 |
violet | -0.030 |
sy | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
ust | +0.048 |
ight | +0.043 |
adventure | +0.042 |
eternity | +0.039 |
all | +0.039 |
Neg logit contributions | |
Stacy | -0.070 |
kit | -0.070 |
kettle | -0.066 |
violet | -0.065 |
sy | -0.064 |
Token | |
Token ID | 220 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
ust | +0.015 |
ight | +0.014 |
adventure | +0.014 |
eternity | +0.014 |
all | +0.013 |
Neg logit contributions | |
Stacy | -0.014 |
kit | -0.014 |
kettle | -0.013 |
Grac | -0.012 |
sy | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
Stacy | +0.013 |
kit | +0.012 |
Did | +0.011 |
Grac | +0.011 |
kettle | +0.011 |
Neg logit contributions | |
ust | -0.019 |
adventure | -0.018 |
ight | -0.017 |
eternity | -0.017 |
unexpected | -0.016 |
Token | played |
Token ID | 2826 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
kit | +0.013 |
Stacy | +0.013 |
kettle | +0.012 |
sy | +0.012 |
piping | +0.012 |
Neg logit contributions | |
ust | -0.012 |
adventure | -0.011 |
ight | -0.011 |
eternity | -0.010 |
all | -0.010 |
Token | together |
Token ID | 1978 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
ust | +0.022 |
ight | +0.020 |
adventure | +0.019 |
eternity | +0.019 |
all | +0.019 |
Neg logit contributions | |
kit | -0.017 |
Stacy | -0.017 |
kettle | -0.016 |
te | -0.015 |
Grac | -0.015 |
Token | every |
Token ID | 790 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
Stacy | +0.013 |
kit | +0.013 |
kettle | +0.012 |
te | +0.012 |
tin | +0.011 |
Neg logit contributions | |
ust | -0.011 |
ight | -0.010 |
adventure | -0.009 |
eternity | -0.009 |
all | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ust | +0.025 |
ight | +0.023 |
adventure | +0.022 |
eternity | +0.022 |
all | +0.021 |
Neg logit contributions | |
Stacy | -0.026 |
kit | -0.026 |
kettle | -0.024 |
te | -0.023 |
violet | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Stacy | +0.076 |
kit | +0.075 |
kettle | +0.070 |
te | +0.070 |
Elsa | +0.070 |
Neg logit contributions | |
ust | -0.048 |
ight | -0.042 |
adventure | -0.040 |
eternity | -0.039 |
uct | -0.037 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ust | +0.028 |
adventure | +0.026 |
ight | +0.026 |
eternity | +0.026 |
all | +0.025 |
Neg logit contributions | |
kit | -0.028 |
Stacy | -0.027 |
kettle | -0.025 |
sy | -0.025 |
tin | -0.025 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.33e-03 |
Pos logit contributions | |
ust | +0.074 |
ight | +0.066 |
eternity | +0.064 |
adventure | +0.064 |
rated | +0.062 |
Neg logit contributions | |
kit | -0.038 |
Stacy | -0.038 |
Elsa | -0.032 |
Did | -0.032 |
Grac | -0.032 |
Token | upon |
Token ID | 2402 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
Stacy | +0.007 |
kit | +0.006 |
Grac | +0.006 |
kettle | +0.006 |
Elsa | +0.006 |
Neg logit contributions | |
ust | -0.007 |
eternity | -0.007 |
ight | -0.007 |
adventure | -0.007 |
ach | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ust | +0.088 |
eternity | +0.082 |
ight | +0.082 |
ach | +0.080 |
uct | +0.080 |
Neg logit contributions | |
Stacy | -0.040 |
kit | -0.038 |
Elsa | -0.036 |
brush | -0.034 |
piping | -0.033 |
Token | time |
Token ID | 640 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
brush | +0.018 |
Stacy | +0.018 |
te | +0.018 |
piping | +0.017 |
kit | +0.017 |
Neg logit contributions | |
happening | -0.017 |
uct | -0.017 |
all | -0.017 |
ized | -0.017 |
ust | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
Stacy | +0.010 |
Grac | +0.010 |
kit | +0.009 |
Did | +0.009 |
Elsa | +0.008 |
Neg logit contributions | |
ust | -0.023 |
uct | -0.022 |
eternity | -0.022 |
rated | -0.022 |
ight | -0.021 |
Token | As |
Token ID | 1722 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ust | +0.047 |
ight | +0.043 |
adventure | +0.042 |
eternity | +0.041 |
all | +0.040 |
Neg logit contributions | |
Stacy | -0.057 |
kit | -0.056 |
kettle | -0.053 |
sy | -0.051 |
Grac | -0.051 |
Token | they |
Token ID | 484 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
adventure | +0.016 |
anymore | +0.014 |
ust | +0.014 |
all | +0.014 |
eternity | +0.014 |
Neg logit contributions | |
kit | -0.019 |
sy | -0.018 |
Stacy | -0.018 |
clipboard | -0.017 |
Did | -0.017 |
Token | sailed |
Token ID | 33835 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ust | +0.016 |
ight | +0.015 |
adventure | +0.014 |
eternity | +0.014 |
all | +0.014 |
Neg logit contributions | |
Stacy | -0.010 |
kit | -0.010 |
kettle | -0.010 |
tin | -0.009 |
sy | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ust | +0.037 |
adventure | +0.033 |
ight | +0.033 |
eternity | +0.032 |
all | +0.031 |
Neg logit contributions | |
Stacy | -0.047 |
kit | -0.047 |
kettle | -0.044 |
sy | -0.043 |
violet | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
Stacy | +0.020 |
kit | +0.020 |
kettle | +0.019 |
sy | +0.019 |
Did | +0.018 |
Neg logit contributions | |
ust | -0.013 |
adventure | -0.013 |
ight | -0.012 |
eternity | -0.012 |
all | -0.011 |
Token | ship |
Token ID | 4074 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
ust | +0.039 |
ight | +0.034 |
uct | +0.033 |
all | +0.033 |
eternity | +0.031 |
Neg logit contributions | |
kettle | -0.024 |
kit | -0.022 |
printer | -0.022 |
tin | -0.021 |
te | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -6.91e-03 |
Pos logit contributions | |
ust | +0.049 |
ight | +0.045 |
adventure | +0.044 |
eternity | +0.043 |
all | +0.042 |
Neg logit contributions | |
Stacy | -0.050 |
kit | -0.050 |
kettle | -0.046 |
sy | -0.044 |
tin | -0.044 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
anymore | +0.010 |
adventure | +0.009 |
eternity | +0.009 |
behind | +0.009 |
ust | +0.009 |
Neg logit contributions | |
kit | -0.012 |
sy | -0.012 |
Stacy | -0.012 |
piping | -0.011 |
violet | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
Stacy | +0.018 |
kit | +0.018 |
kettle | +0.016 |
sy | +0.016 |
tin | +0.016 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.022 |
adventure | -0.021 |
eternity | -0.021 |
all | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ust | +0.031 |
adventure | +0.030 |
ight | +0.028 |
eternity | +0.027 |
all | +0.027 |
Neg logit contributions | |
Stacy | -0.044 |
kit | -0.043 |
kettle | -0.041 |
sy | -0.040 |
violet | -0.039 |
Token | group |
Token ID | 1448 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
adventure | +0.013 |
ust | +0.013 |
unexpected | +0.012 |
ight | +0.012 |
eternity | +0.011 |
Neg logit contributions | |
Stacy | -0.024 |
kit | -0.023 |
Did | -0.022 |
Elsa | -0.021 |
Grac | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
Stacy | +0.058 |
kit | +0.057 |
kettle | +0.054 |
sy | +0.054 |
violet | +0.052 |
Neg logit contributions | |
ust | -0.041 |
adventure | -0.039 |
ight | -0.038 |
eternity | -0.037 |
all | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
ust | +0.019 |
ight | +0.017 |
adventure | +0.017 |
eternity | +0.016 |
all | +0.016 |
Neg logit contributions | |
Stacy | -0.028 |
kit | -0.027 |
kettle | -0.026 |
sy | -0.025 |
violet | -0.025 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
ust | +0.059 |
ight | +0.055 |
adventure | +0.054 |
eternity | +0.053 |
all | +0.052 |
Neg logit contributions | |
Stacy | -0.045 |
kit | -0.044 |
kettle | -0.041 |
sy | -0.039 |
te | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ust | +0.069 |
ight | +0.063 |
adventure | +0.060 |
eternity | +0.060 |
all | +0.058 |
Neg logit contributions | |
Stacy | -0.071 |
kit | -0.071 |
kettle | -0.066 |
sy | -0.063 |
tin | -0.063 |
Token | watch |
Token ID | 2342 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ust | +0.056 |
adventure | +0.052 |
ight | +0.051 |
eternity | +0.049 |
all | +0.048 |
Neg logit contributions | |
Stacy | -0.057 |
kit | -0.056 |
kettle | -0.052 |
sy | -0.050 |
violet | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
ust | +0.026 |
ight | +0.024 |
uct | +0.021 |
eternity | +0.021 |
rated | +0.021 |
Neg logit contributions | |
Stacy | -0.022 |
kit | -0.021 |
kettle | -0.020 |
tin | -0.019 |
te | -0.019 |
Token | cartoon |
Token ID | 16251 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
ust | +0.053 |
adventure | +0.050 |
ight | +0.049 |
eternity | +0.047 |
all | +0.046 |
Neg logit contributions | |
Stacy | -0.058 |
kit | -0.057 |
kettle | -0.052 |
sy | -0.051 |
Grac | -0.051 |
Token | on |
Token ID | 319 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
Stacy | +0.005 |
kit | +0.005 |
kettle | +0.004 |
Grac | +0.004 |
piping | +0.004 |
Neg logit contributions | |
ust | -0.003 |
adventure | -0.003 |
ight | -0.003 |
eternity | -0.003 |
all | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
ust | +0.048 |
ight | +0.043 |
adventure | +0.038 |
eternity | +0.038 |
uct | +0.038 |
Neg logit contributions | |
Stacy | -0.044 |
kit | -0.042 |
kettle | -0.039 |
Elsa | -0.039 |
tin | -0.038 |
Token | laptop |
Token ID | 13224 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ust | +0.123 |
ight | +0.115 |
eternity | +0.109 |
all | +0.108 |
adventure | +0.106 |
Neg logit contributions | |
Stacy | -0.084 |
kit | -0.084 |
kettle | -0.077 |
te | -0.073 |
sy | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
kit | +0.029 |
Stacy | +0.028 |
kettle | +0.027 |
tin | +0.026 |
te | +0.026 |
Neg logit contributions | |
ust | -0.018 |
ight | -0.015 |
adventure | -0.014 |
eternity | -0.014 |
all | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
kit | +0.018 |
Stacy | +0.018 |
kettle | +0.016 |
violet | +0.016 |
sy | +0.016 |
Neg logit contributions | |
ust | -0.020 |
ight | -0.018 |
adventure | -0.018 |
eternity | -0.017 |
all | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
kit | +0.067 |
Stacy | +0.067 |
kettle | +0.064 |
violet | +0.061 |
tin | +0.061 |
Neg logit contributions | |
ust | -0.054 |
adventure | -0.050 |
ight | -0.049 |
eternity | -0.047 |
all | -0.047 |
Token | Jon |
Token ID | 5966 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
ust | +0.011 |
ight | +0.010 |
adventure | +0.010 |
all | +0.010 |
eternity | +0.010 |
Neg logit contributions | |
kit | -0.011 |
Stacy | -0.011 |
kettle | -0.010 |
tin | -0.010 |
sy | -0.010 |
Token | ny |
Token ID | 3281 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
ust | +0.117 |
adventure | +0.107 |
eternity | +0.105 |
ight | +0.105 |
unexpected | +0.100 |
Neg logit contributions | |
kit | -0.120 |
Stacy | -0.120 |
kettle | -0.105 |
tin | -0.103 |
sy | -0.103 |
Token | couldn |
Token ID | 3521 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
Stacy | +0.066 |
kit | +0.066 |
kettle | +0.062 |
sy | +0.059 |
piping | +0.059 |
Neg logit contributions | |
ust | -0.069 |
adventure | -0.065 |
ight | -0.065 |
eternity | -0.061 |
all | -0.061 |
Token | â |
Token ID | 22940 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
ust | +0.093 |
ight | +0.086 |
adventure | +0.086 |
eternity | +0.083 |
urious | +0.081 |
Neg logit contributions | |
Stacy | -0.043 |
kit | -0.042 |
sy | -0.036 |
Grac | -0.035 |
kettle | -0.035 |
Token | € |
Token ID | 26391 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ust | +0.138 |
adventure | +0.122 |
ight | +0.122 |
anymore | +0.116 |
eternity | +0.114 |
Neg logit contributions | |
kit | -0.162 |
Stacy | -0.156 |
brush | -0.139 |
tin | -0.138 |
sy | -0.137 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ust | +0.043 |
ight | +0.040 |
adventure | +0.039 |
eternity | +0.038 |
unexpected | +0.037 |
Neg logit contributions | |
kit | -0.041 |
Stacy | -0.041 |
Did | -0.037 |
kettle | -0.036 |
throat | -0.036 |
Token | t |
Token ID | 83 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
adventure | +0.028 |
ust | +0.027 |
eternity | +0.026 |
unexpected | +0.026 |
urious | +0.025 |
Neg logit contributions | |
kit | -0.020 |
Stacy | -0.020 |
Did | -0.018 |
Grac | -0.018 |
kettle | -0.017 |
Token | believe |
Token ID | 1975 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
ust | +0.128 |
ight | +0.118 |
uct | +0.111 |
urious | +0.111 |
adventure | +0.111 |
Neg logit contributions | |
Stacy | -0.120 |
kit | -0.113 |
Grac | -0.108 |
brush | -0.108 |
kettle | -0.105 |
Token | it |
Token ID | 340 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
Stacy | +0.025 |
kit | +0.023 |
Grac | +0.023 |
Elsa | +0.022 |
sy | +0.022 |
Neg logit contributions | |
ust | -0.024 |
ight | -0.023 |
adventure | -0.022 |
eternity | -0.021 |
urious | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -8.99e-04 |
Pos logit contributions | |
ust | +0.011 |
adventure | +0.011 |
ight | +0.010 |
eternity | +0.010 |
all | +0.010 |
Neg logit contributions | |
Stacy | -0.017 |
kit | -0.017 |
kettle | -0.016 |
sy | -0.016 |
piping | -0.016 |
Token | plane |
Token ID | 6614 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ust | +0.002 |
ight | +0.002 |
eternity | +0.002 |
all | +0.002 |
adventure | +0.002 |
Neg logit contributions | |
kit | -0.001 |
Stacy | -0.001 |
kettle | -0.001 |
sy | -0.001 |
te | -0.001 |
Token | flew |
Token ID | 13112 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
ust | +0.057 |
eternity | +0.051 |
ight | +0.051 |
adventure | +0.050 |
all | +0.050 |
Neg logit contributions | |
kit | -0.028 |
Stacy | -0.026 |
kettle | -0.025 |
te | -0.024 |
bottle | -0.023 |
Token | up |
Token ID | 510 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
ust | +0.061 |
eternity | +0.059 |
adventure | +0.054 |
uct | +0.054 |
ight | +0.053 |
Neg logit contributions | |
kit | -0.058 |
Stacy | -0.056 |
tin | -0.054 |
bottle | -0.053 |
violet | -0.052 |
Token | so |
Token ID | 523 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ust | +0.010 |
ight | +0.009 |
adventure | +0.008 |
eternity | +0.008 |
uct | +0.008 |
Neg logit contributions | |
kit | -0.010 |
Stacy | -0.010 |
tin | -0.009 |
kettle | -0.009 |
te | -0.009 |
Token | high |
Token ID | 1029 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
Stacy | +0.023 |
kit | +0.022 |
kettle | +0.020 |
Grac | +0.020 |
Elsa | +0.020 |
Neg logit contributions | |
ust | -0.019 |
ight | -0.017 |
adventure | -0.017 |
eternity | -0.016 |
all | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
ust | +0.168 |
ight | +0.149 |
adventure | +0.137 |
urious | +0.134 |
uct | +0.134 |
Neg logit contributions | |
Stacy | -0.150 |
kit | -0.148 |
tin | -0.136 |
kettle | -0.135 |
te | -0.134 |
Token | It |
Token ID | 632 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ust | +0.012 |
ight | +0.011 |
adventure | +0.011 |
eternity | +0.011 |
all | +0.010 |
Neg logit contributions | |
Stacy | -0.008 |
kit | -0.008 |
kettle | -0.007 |
sy | -0.007 |
Grac | -0.007 |
Token | flew |
Token ID | 13112 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ust | +0.030 |
ight | +0.028 |
eternity | +0.027 |
adventure | +0.027 |
all | +0.027 |
Neg logit contributions | |
Stacy | -0.019 |
kit | -0.019 |
kettle | -0.018 |
te | -0.017 |
tin | -0.017 |
Token | higher |
Token ID | 2440 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ust | +0.052 |
eternity | +0.046 |
ight | +0.045 |
adventure | +0.044 |
uct | +0.044 |
Neg logit contributions | |
Stacy | -0.052 |
kit | -0.052 |
tin | -0.049 |
violet | -0.048 |
kettle | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
ust | +0.033 |
ight | +0.029 |
uct | +0.028 |
eternity | +0.027 |
adventure | +0.027 |
Neg logit contributions | |
Stacy | -0.038 |
kit | -0.037 |
tin | -0.036 |
violet | -0.035 |
kettle | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
Stacy | +0.028 |
kit | +0.027 |
kettle | +0.026 |
Elsa | +0.025 |
te | +0.025 |
Neg logit contributions | |
ust | -0.033 |
adventure | -0.030 |
ight | -0.030 |
eternity | -0.030 |
ach | -0.029 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
Stacy | +0.005 |
kit | +0.005 |
Did | +0.004 |
Grac | +0.004 |
kettle | +0.004 |
Neg logit contributions | |
adventure | -0.004 |
ust | -0.004 |
ight | -0.003 |
eternity | -0.003 |
unexpected | -0.003 |
Token | who |
Token ID | 508 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
ust | +0.042 |
adventure | +0.040 |
ight | +0.039 |
eternity | +0.038 |
all | +0.037 |
Neg logit contributions | |
Stacy | -0.044 |
kit | -0.041 |
kettle | -0.038 |
Elsa | -0.038 |
Grac | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
Stacy | +0.066 |
kit | +0.065 |
kettle | +0.060 |
violet | +0.057 |
sy | +0.057 |
Neg logit contributions | |
ust | -0.075 |
ight | -0.071 |
adventure | -0.070 |
eternity | -0.067 |
all | -0.066 |
Token | seen |
Token ID | 1775 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
Stacy | +0.065 |
kit | +0.063 |
kettle | +0.060 |
Grac | +0.057 |
sy | +0.057 |
Neg logit contributions | |
ust | -0.048 |
adventure | -0.044 |
ight | -0.044 |
all | -0.040 |
eternity | -0.040 |
Token | him |
Token ID | 683 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
ust | +0.044 |
ight | +0.040 |
adventure | +0.039 |
eternity | +0.038 |
all | +0.037 |
Neg logit contributions | |
Stacy | -0.048 |
kit | -0.048 |
kettle | -0.044 |
sy | -0.043 |
Grac | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ust | +0.139 |
ight | +0.124 |
eternity | +0.118 |
uct | +0.115 |
rated | +0.114 |
Neg logit contributions | |
kit | -0.166 |
Stacy | -0.159 |
brush | -0.151 |
bottle | -0.149 |
sewing | -0.148 |
Token | The |
Token ID | 383 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
ust | +0.023 |
ight | +0.021 |
adventure | +0.021 |
eternity | +0.020 |
all | +0.020 |
Neg logit contributions | |
Stacy | -0.021 |
kit | -0.021 |
kettle | -0.020 |
sy | -0.019 |
tin | -0.019 |
Token | bird |
Token ID | 6512 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
ust | +0.003 |
ight | +0.002 |
adventure | +0.002 |
eternity | +0.002 |
all | +0.002 |
Neg logit contributions | |
Stacy | -0.002 |
kit | -0.002 |
kettle | -0.002 |
sy | -0.002 |
te | -0.002 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
ust | +0.008 |
ight | +0.007 |
adventure | +0.007 |
eternity | +0.007 |
all | +0.007 |
Neg logit contributions | |
Stacy | -0.007 |
kit | -0.007 |
kettle | -0.006 |
sy | -0.006 |
Grac | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ust | +0.077 |
ight | +0.070 |
eternity | +0.065 |
uct | +0.064 |
iver | +0.063 |
Neg logit contributions | |
kit | -0.062 |
Stacy | -0.061 |
kettle | -0.055 |
Elsa | -0.054 |
Grac | -0.053 |
Token | Jack |
Token ID | 3619 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ust | +0.003 |
adventure | +0.003 |
ight | +0.003 |
eternity | +0.003 |
all | +0.003 |
Neg logit contributions | |
kit | -0.005 |
Stacy | -0.005 |
kettle | -0.004 |
sy | -0.004 |
violet | -0.004 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
ust | +0.059 |
ight | +0.054 |
adventure | +0.053 |
eternity | +0.053 |
all | +0.051 |
Neg logit contributions | |
Stacy | -0.046 |
kit | -0.045 |
kettle | -0.042 |
te | -0.040 |
sy | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ust | +0.067 |
ight | +0.061 |
eternity | +0.057 |
adventure | +0.056 |
all | +0.055 |
Neg logit contributions | |
kit | -0.062 |
Stacy | -0.061 |
kettle | -0.056 |
sy | -0.054 |
tin | -0.054 |
Token | climb |
Token ID | 12080 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
ust | +0.058 |
ight | +0.053 |
adventure | +0.053 |
eternity | +0.051 |
all | +0.050 |
Neg logit contributions | |
Stacy | -0.052 |
kit | -0.052 |
kettle | -0.048 |
sy | -0.046 |
Grac | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ust | +0.134 |
ight | +0.120 |
uct | +0.110 |
urious | +0.110 |
eternity | +0.106 |
Neg logit contributions | |
kit | -0.081 |
Stacy | -0.077 |
tin | -0.072 |
bottle | -0.070 |
Grac | -0.068 |
Token | high |
Token ID | 1029 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
ust | +0.043 |
ight | +0.040 |
eternity | +0.038 |
adventure | +0.037 |
all | +0.037 |
Neg logit contributions | |
Stacy | -0.043 |
kit | -0.042 |
kettle | -0.040 |
tin | -0.039 |
violet | -0.038 |
Token | mountain |
Token ID | 8598 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ust | +0.154 |
ight | +0.139 |
eternity | +0.129 |
all | +0.128 |
uct | +0.126 |
Neg logit contributions | |
kit | -0.143 |
Stacy | -0.142 |
tin | -0.134 |
kettle | -0.132 |
violet | -0.129 |
Token | by |
Token ID | 416 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
ust | +0.066 |
ight | +0.058 |
uct | +0.054 |
eternity | +0.053 |
end | +0.052 |
Neg logit contributions | |
kit | -0.085 |
Stacy | -0.079 |
tin | -0.078 |
kettle | -0.076 |
te | -0.075 |
Token | himself |
Token ID | 2241 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ust | +0.049 |
ight | +0.041 |
uct | +0.036 |
adventure | +0.034 |
ax | +0.034 |
Neg logit contributions | |
Stacy | -0.065 |
kit | -0.062 |
tin | -0.059 |
Grac | -0.058 |
violet | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
ust | +0.054 |
ight | +0.050 |
eternity | +0.049 |
uct | +0.048 |
adventure | +0.047 |
Neg logit contributions | |
kit | -0.071 |
Stacy | -0.071 |
tin | -0.066 |
drawer | -0.065 |
bottle | -0.063 |
Token | Jim |
Token ID | 5395 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
ust | +0.013 |
ight | +0.012 |
adventure | +0.011 |
eternity | +0.011 |
all | +0.011 |
Neg logit contributions | |
Stacy | -0.012 |
kit | -0.012 |
kettle | -0.011 |
sy | -0.011 |
Grac | -0.010 |
Token | time |
Token ID | 640 |
Feature activation | +5.98e-03 |
Pos logit contributions | |
Stacy | +0.006 |
brush | +0.006 |
kettle | +0.006 |
te | +0.006 |
piping | +0.006 |
Neg logit contributions | |
ized | -0.006 |
uted | -0.006 |
ust | -0.006 |
happening | -0.006 |
uct | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
Stacy | +0.007 |
Grac | +0.007 |
kit | +0.007 |
Did | +0.006 |
kettle | +0.006 |
Neg logit contributions | |
ust | -0.013 |
ight | -0.012 |
uct | -0.012 |
rated | -0.012 |
eternity | -0.012 |
Token | lived |
Token ID | 5615 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
Stacy | +0.022 |
kit | +0.021 |
Grac | +0.019 |
kettle | +0.018 |
Did | +0.018 |
Neg logit contributions | |
ust | -0.049 |
ight | -0.045 |
eternity | -0.044 |
adventure | -0.043 |
all | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ust | +0.077 |
eternity | +0.072 |
rated | +0.071 |
ight | +0.070 |
adventure | +0.069 |
Neg logit contributions | |
Stacy | -0.057 |
kit | -0.057 |
Grac | -0.052 |
kettle | -0.052 |
Elsa | -0.051 |
Token | little |
Token ID | 1310 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
ust | +0.023 |
adventure | +0.021 |
ight | +0.021 |
eternity | +0.020 |
all | +0.019 |
Neg logit contributions | |
Stacy | -0.031 |
kit | -0.031 |
kettle | -0.029 |
sy | -0.028 |
Grac | -0.028 |
Token | rac |
Token ID | 3444 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
kit | +0.006 |
Stacy | +0.006 |
kettle | +0.005 |
Did | +0.005 |
sy | +0.005 |
Neg logit contributions | |
ust | -0.007 |
adventure | -0.007 |
ight | -0.007 |
eternity | -0.007 |
unexpected | -0.007 |
Token | coon |
Token ID | 20912 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ust | +0.150 |
uct | +0.128 |
ight | +0.126 |
urious | +0.126 |
eternity | +0.123 |
Neg logit contributions | |
kit | -0.155 |
Stacy | -0.147 |
kettle | -0.142 |
te | -0.137 |
sy | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ust | +0.029 |
adventure | +0.028 |
ight | +0.027 |
eternity | +0.027 |
all | +0.026 |
Neg logit contributions | |
Stacy | -0.017 |
kit | -0.016 |
kettle | -0.014 |
piping | -0.014 |
sy | -0.014 |
Token | It |
Token ID | 632 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ust | +0.021 |
adventure | +0.020 |
ight | +0.020 |
eternity | +0.019 |
all | +0.019 |
Neg logit contributions | |
Stacy | -0.020 |
kit | -0.019 |
kettle | -0.018 |
sy | -0.017 |
violet | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ust | +0.040 |
adventure | +0.039 |
ight | +0.037 |
all | +0.036 |
eternity | +0.035 |
Neg logit contributions | |
kit | -0.040 |
Stacy | -0.039 |
kettle | -0.036 |
piping | -0.035 |
sy | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
ust | +0.019 |
adventure | +0.019 |
ight | +0.017 |
all | +0.017 |
eternity | +0.016 |
Neg logit contributions | |
Stacy | -0.029 |
kit | -0.028 |
kettle | -0.026 |
piping | -0.026 |
sy | -0.026 |