Token | and |
Token ID | 290 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
Buster | +0.218 |
Kenny | +0.215 |
Hanna | +0.212 |
Cindy | +0.210 |
pup | +0.209 |
Neg logit contributions | |
ide | -0.212 |
castle | -0.207 |
ull | -0.197 |
room | -0.193 |
structures | -0.189 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Buster | +0.045 |
Kenny | +0.044 |
Hanna | +0.044 |
pup | +0.044 |
Hannah | +0.044 |
Neg logit contributions | |
castle | -0.047 |
ide | -0.047 |
ull | -0.044 |
structures | -0.043 |
room | -0.043 |
Token | other |
Token ID | 584 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Buster | +0.013 |
pup | +0.013 |
Hanna | +0.012 |
F | +0.012 |
Cindy | +0.012 |
Neg logit contributions | |
ide | -0.014 |
castle | -0.014 |
ull | -0.014 |
room | -0.013 |
structures | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Buster | +0.118 |
Kenny | +0.117 |
pup | +0.116 |
Hanna | +0.116 |
Cindy | +0.115 |
Neg logit contributions | |
castle | -0.121 |
ide | -0.121 |
ull | -0.114 |
room | -0.112 |
structures | -0.111 |
Token | called |
Token ID | 1444 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Buster | +0.060 |
Kenny | +0.059 |
Hanna | +0.059 |
pup | +0.059 |
Cindy | +0.058 |
Neg logit contributions | |
castle | -0.075 |
ide | -0.075 |
ull | -0.071 |
room | -0.070 |
structures | -0.069 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Buster | +0.155 |
Kenny | +0.153 |
pup | +0.152 |
Hanna | +0.151 |
Kel | +0.148 |
Neg logit contributions | |
ide | -0.167 |
castle | -0.164 |
ull | -0.156 |
room | -0.155 |
structures | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Buster | +0.867 |
Kenny | +0.860 |
Hanna | +0.853 |
pup | +0.840 |
Cindy | +0.838 |
Neg logit contributions | |
ide | -0.806 |
castle | -0.787 |
ull | -0.743 |
room | -0.730 |
structures | -0.723 |
Token | One |
Token ID | 1881 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
training | +0.054 |
hesitation | +0.052 |
reins | +0.051 |
buck | +0.051 |
uster | +0.051 |
Neg logit contributions | |
ide | -0.033 |
room | -0.028 |
structures | -0.026 |
ull | -0.024 |
salad | -0.024 |
Token | day |
Token ID | 1110 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Buster | +0.079 |
pup | +0.078 |
Kenny | +0.077 |
Hanna | +0.077 |
F | +0.076 |
Neg logit contributions | |
castle | -0.114 |
ide | -0.113 |
ull | -0.106 |
structures | -0.106 |
room | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ide | +0.033 |
room | +0.028 |
salad | +0.026 |
ull | +0.026 |
ics | +0.026 |
Neg logit contributions | |
uster | -0.056 |
reins | -0.055 |
training | -0.051 |
pup | -0.051 |
Buster | -0.051 |
Token | they |
Token ID | 484 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
uster | +0.056 |
reins | +0.054 |
training | +0.054 |
hesitation | +0.053 |
buck | +0.051 |
Neg logit contributions | |
ide | -0.043 |
salad | -0.036 |
room | -0.036 |
castle | -0.034 |
structures | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Buster | +0.015 |
Kenny | +0.015 |
pup | +0.015 |
F | +0.015 |
Hannah | +0.015 |
Neg logit contributions | |
castle | -0.020 |
ide | -0.019 |
structures | -0.019 |
room | -0.018 |
salad | -0.018 |
Token | Tommy |
Token ID | 19919 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Buster | +0.010 |
Kenny | +0.010 |
Hanna | +0.010 |
pup | +0.010 |
Hannah | +0.010 |
Neg logit contributions | |
castle | -0.009 |
ide | -0.009 |
ull | -0.008 |
room | -0.008 |
structures | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Buster | +0.332 |
pup | +0.331 |
F | +0.318 |
Kenny | +0.317 |
Hannah | +0.314 |
Neg logit contributions | |
castle | -0.559 |
ide | -0.532 |
structures | -0.527 |
room | -0.511 |
ull | -0.500 |
Token | Jeffrey |
Token ID | 19627 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Buster | +0.009 |
Kenny | +0.009 |
F | +0.009 |
Hanna | +0.009 |
pup | +0.009 |
Neg logit contributions | |
castle | -0.011 |
structures | -0.010 |
ide | -0.010 |
room | -0.010 |
ull | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Buster | +0.072 |
Kenny | +0.071 |
Hanna | +0.070 |
Cindy | +0.069 |
uster | +0.069 |
Neg logit contributions | |
ide | -0.064 |
castle | -0.062 |
ull | -0.061 |
room | -0.058 |
structures | -0.057 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
Buster | +0.009 |
Kenny | +0.009 |
Cindy | +0.009 |
Hanna | +0.009 |
Hannah | +0.009 |
Neg logit contributions | |
castle | -0.010 |
ide | -0.010 |
structures | -0.009 |
room | -0.009 |
ull | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
Buster | +0.876 |
Kenny | +0.867 |
Hanna | +0.864 |
pup | +0.851 |
Hannah | +0.848 |
Neg logit contributions | |
ide | -0.772 |
castle | -0.746 |
ull | -0.718 |
room | -0.703 |
structures | -0.694 |
Token | They |
Token ID | 1119 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
castle | +0.004 |
ide | +0.004 |
ull | +0.004 |
room | +0.003 |
structures | +0.003 |
Neg logit contributions | |
Buster | -0.006 |
Kenny | -0.006 |
pup | -0.006 |
Hanna | -0.006 |
Cindy | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
castle | +0.011 |
ide | +0.011 |
structures | +0.010 |
ull | +0.010 |
room | +0.010 |
Neg logit contributions | |
Buster | -0.012 |
F | -0.012 |
Cindy | -0.012 |
Hanna | -0.011 |
pup | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
castle | +0.135 |
ide | +0.135 |
ull | +0.126 |
room | +0.124 |
structures | +0.123 |
Neg logit contributions | |
Buster | -0.104 |
Kenny | -0.102 |
Cindy | -0.101 |
F | -0.101 |
Hanna | -0.101 |
Token | so |
Token ID | 523 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
castle | +0.124 |
ide | +0.123 |
ull | +0.115 |
room | +0.115 |
structures | +0.114 |
Neg logit contributions | |
Buster | -0.086 |
F | -0.085 |
Hanna | -0.085 |
Cindy | -0.084 |
Hannah | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Buster | +0.077 |
Hanna | +0.076 |
Kenny | +0.075 |
Kel | +0.074 |
uster | +0.074 |
Neg logit contributions | |
castle | -0.048 |
ide | -0.047 |
structures | -0.044 |
room | -0.043 |
nation | -0.040 |
Token | From |
Token ID | 3574 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
buck | +0.037 |
pup | +0.036 |
Buster | +0.036 |
hesitation | +0.036 |
training | +0.036 |
Neg logit contributions | |
ide | -0.036 |
room | -0.034 |
castle | -0.034 |
ull | -0.033 |
structures | -0.033 |
Token | then |
Token ID | 788 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
uster | +0.066 |
reins | +0.061 |
training | +0.057 |
Michael | +0.056 |
Hanna | +0.056 |
Neg logit contributions | |
castle | -0.050 |
ide | -0.048 |
ics | -0.045 |
nation | -0.044 |
ull | -0.043 |
Token | on |
Token ID | 319 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
uster | +0.303 |
Hanna | +0.293 |
Hank | +0.292 |
Hannah | +0.289 |
Kel | +0.286 |
Neg logit contributions | |
room | -0.235 |
ide | -0.215 |
anish | -0.204 |
castle | -0.203 |
ics | -0.200 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
uster | +0.183 |
reins | +0.176 |
buck | +0.172 |
Buster | +0.170 |
pup | +0.170 |
Neg logit contributions | |
ide | -0.133 |
castle | -0.125 |
structures | -0.120 |
room | -0.118 |
salad | -0.112 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
uster | +0.031 |
Buster | +0.030 |
Kenny | +0.030 |
pup | +0.030 |
Matthew | +0.030 |
Neg logit contributions | |
ide | -0.030 |
castle | -0.030 |
room | -0.028 |
structures | -0.028 |
ull | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
Kenny | +0.895 |
uster | +0.895 |
Buster | +0.891 |
hesitation | +0.876 |
Kel | +0.874 |
Neg logit contributions | |
castle | -0.715 |
ide | -0.714 |
room | -0.676 |
ull | -0.657 |
structures | -0.614 |
Token | determined |
Token ID | 5295 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
uster | +0.061 |
Kenny | +0.060 |
Buster | +0.060 |
pup | +0.059 |
luggage | +0.058 |
Neg logit contributions | |
castle | -0.048 |
ide | -0.047 |
ull | -0.046 |
room | -0.043 |
ics | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Kenny | +0.226 |
Buster | +0.225 |
Hanna | +0.222 |
Kel | +0.220 |
uster | +0.220 |
Neg logit contributions | |
castle | -0.193 |
ide | -0.190 |
ull | -0.175 |
structures | -0.171 |
room | -0.169 |
Token | always |
Token ID | 1464 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Kenny | +0.012 |
Hanna | +0.012 |
Buster | +0.012 |
Kel | +0.011 |
Hannah | +0.011 |
Neg logit contributions | |
castle | -0.010 |
ide | -0.009 |
ull | -0.009 |
room | -0.009 |
structures | -0.008 |
Token | succeed |
Token ID | 6758 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
uster | +0.028 |
Kenny | +0.028 |
Kel | +0.028 |
Hanna | +0.028 |
Buster | +0.027 |
Neg logit contributions | |
castle | -0.021 |
ide | -0.020 |
room | -0.019 |
ull | -0.018 |
structures | -0.018 |
Token | With |
Token ID | 3152 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ide | +0.042 |
castle | +0.041 |
ull | +0.040 |
room | +0.039 |
structures | +0.039 |
Neg logit contributions | |
Buster | -0.033 |
Kenny | -0.033 |
pup | -0.032 |
Hanna | -0.032 |
Cindy | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
salad | +0.074 |
ide | +0.073 |
castle | +0.068 |
ull | +0.067 |
room | +0.066 |
Neg logit contributions | |
uster | -0.117 |
Matthew | -0.108 |
Eleanor | -0.108 |
Hanna | -0.108 |
Kel | -0.108 |
Token | coat |
Token ID | 13209 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
castle | +0.067 |
salad | +0.063 |
tower | +0.060 |
ull | +0.060 |
structures | +0.059 |
Neg logit contributions | |
Kenny | -0.073 |
Matthew | -0.072 |
Buster | -0.072 |
Kel | -0.071 |
Hank | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Hanna | +0.493 |
Hank | +0.490 |
Buster | +0.489 |
Matthew | +0.486 |
Hannah | +0.486 |
Neg logit contributions | |
castle | -0.445 |
ide | -0.426 |
room | -0.413 |
ull | -0.394 |
ics | -0.388 |
Token | , |
Token ID | 11 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Buster | +0.156 |
Kenny | +0.154 |
pup | +0.154 |
uster | +0.153 |
Hanna | +0.153 |
Neg logit contributions | |
ide | -0.148 |
castle | -0.146 |
room | -0.138 |
ull | -0.136 |
structures | -0.134 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.92e+00 |
Pos logit contributions | |
uster | +0.023 |
Buster | +0.022 |
training | +0.022 |
Matthew | +0.022 |
Kenny | +0.022 |
Neg logit contributions | |
ide | -0.022 |
castle | -0.022 |
structures | -0.020 |
room | -0.020 |
ull | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Buster | +0.832 |
Kenny | +0.826 |
pup | +0.811 |
Hanna | +0.807 |
Cindy | +0.805 |
Neg logit contributions | |
castle | -0.800 |
ide | -0.798 |
ull | -0.744 |
room | -0.741 |
structures | -0.714 |
Token | a |
Token ID | 257 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
uster | +0.247 |
Buster | +0.244 |
Kenny | +0.243 |
pup | +0.237 |
Kel | +0.234 |
Neg logit contributions | |
castle | -0.227 |
ide | -0.222 |
ull | -0.214 |
room | -0.209 |
salad | -0.206 |
Token | wonderful |
Token ID | 7932 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
uster | +0.025 |
Kel | +0.024 |
Kenny | +0.024 |
F | +0.024 |
Buster | +0.024 |
Neg logit contributions | |
castle | -0.025 |
salad | -0.024 |
ide | -0.023 |
nation | -0.023 |
tower | -0.023 |
Token | day |
Token ID | 1110 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
uster | +0.263 |
Buster | +0.263 |
Hanna | +0.261 |
Kenny | +0.260 |
F | +0.256 |
Neg logit contributions | |
castle | -0.279 |
ide | -0.269 |
ull | -0.260 |
room | -0.248 |
salad | -0.246 |
Token | in |
Token ID | 287 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ide | +0.043 |
castle | +0.043 |
room | +0.039 |
ull | +0.038 |
salad | +0.036 |
Neg logit contributions | |
Kenny | -0.068 |
Kel | -0.068 |
Eleanor | -0.068 |
Hanna | -0.067 |
Michael | -0.067 |
Token | eat |
Token ID | 4483 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
uster | +0.004 |
Buster | +0.004 |
Kenny | +0.004 |
Kel | +0.004 |
pup | +0.004 |
Neg logit contributions | |
castle | -0.003 |
ide | -0.003 |
room | -0.003 |
ull | -0.003 |
ics | -0.003 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ide | +0.203 |
castle | +0.199 |
salad | +0.189 |
structures | +0.187 |
ull | +0.187 |
Neg logit contributions | |
Buster | -0.206 |
uster | -0.205 |
Kenny | -0.204 |
Hanna | -0.204 |
Kel | -0.202 |
Token | of |
Token ID | 286 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ide | +0.103 |
castle | +0.094 |
salad | +0.090 |
structures | +0.090 |
ull | +0.087 |
Neg logit contributions | |
Buster | -0.124 |
Hanna | -0.122 |
Kenny | -0.122 |
Kel | -0.122 |
Matthew | -0.121 |
Token | food |
Token ID | 2057 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
uster | +0.060 |
Buster | +0.058 |
Kenny | +0.058 |
Hanna | +0.058 |
Kel | +0.057 |
Neg logit contributions | |
salad | -0.045 |
ide | -0.045 |
structures | -0.044 |
castle | -0.044 |
ull | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ide | +0.015 |
castle | +0.015 |
ull | +0.014 |
room | +0.014 |
structures | +0.014 |
Neg logit contributions | |
Buster | -0.014 |
Kenny | -0.014 |
Hanna | -0.014 |
pup | -0.014 |
Cindy | -0.013 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
Buster | +0.017 |
Kenny | +0.017 |
pup | +0.017 |
Hanna | +0.017 |
Hannah | +0.017 |
Neg logit contributions | |
ide | -0.017 |
castle | -0.017 |
ull | -0.016 |
room | -0.015 |
structures | -0.015 |
Token | just |
Token ID | 655 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Buster | +0.806 |
Kenny | +0.801 |
Hanna | +0.786 |
uster | +0.785 |
pup | +0.784 |
Neg logit contributions | |
ide | -0.820 |
castle | -0.804 |
ull | -0.751 |
room | -0.744 |
structures | -0.724 |
Token | wanted |
Token ID | 2227 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
Buster | +0.111 |
Kenny | +0.110 |
Hanna | +0.109 |
pup | +0.108 |
uster | +0.108 |
Neg logit contributions | |
ide | -0.097 |
castle | -0.097 |
ull | -0.091 |
room | -0.087 |
structures | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
ide | +0.059 |
salad | +0.058 |
ull | +0.054 |
castle | +0.054 |
structures | +0.053 |
Neg logit contributions | |
uster | -0.079 |
Kel | -0.075 |
Kenny | -0.074 |
Buster | -0.074 |
Haley | -0.073 |
Token | be |
Token ID | 307 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Buster | +0.004 |
Kenny | +0.004 |
pup | +0.004 |
Hanna | +0.004 |
Hannah | +0.004 |
Neg logit contributions | |
ide | -0.004 |
castle | -0.004 |
ull | -0.004 |
room | -0.004 |
structures | -0.004 |
Token | silly |
Token ID | 14397 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Buster | +0.019 |
pup | +0.018 |
Hanna | +0.018 |
Hannah | +0.018 |
Cindy | +0.018 |
Neg logit contributions | |
ide | -0.025 |
castle | -0.024 |
structures | -0.023 |
room | -0.023 |
ull | -0.023 |
Token | As |
Token ID | 1081 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Michael | +0.009 |
hesitation | +0.009 |
training | +0.009 |
buck | +0.009 |
Kenny | +0.009 |
Neg logit contributions | |
room | -0.010 |
ide | -0.009 |
tub | -0.009 |
salad | -0.008 |
structures | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
reins | +0.145 |
uster | +0.136 |
brakes | +0.132 |
leaf | +0.128 |
hesitation | +0.128 |
Neg logit contributions | |
ide | -0.038 |
ics | -0.025 |
salad | -0.024 |
nation | -0.024 |
room | -0.021 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ide | +0.028 |
castle | +0.026 |
room | +0.025 |
ill | +0.022 |
salad | +0.021 |
Neg logit contributions | |
reins | -0.042 |
Buster | -0.042 |
uster | -0.042 |
pup | -0.042 |
Matthew | -0.041 |
Token | around |
Token ID | 1088 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Michael | +0.145 |
Tyler | +0.141 |
hesitation | +0.140 |
reins | +0.139 |
Matthew | +0.138 |
Neg logit contributions | |
castle | -0.076 |
ide | -0.075 |
room | -0.068 |
structure | -0.063 |
structures | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
reins | +0.176 |
uster | +0.175 |
Matthew | +0.171 |
Buster | +0.170 |
Michael | +0.166 |
Neg logit contributions | |
ide | -0.117 |
room | -0.114 |
castle | -0.107 |
structures | -0.101 |
nation | -0.100 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
reins | +0.013 |
training | +0.011 |
saddle | +0.011 |
uster | +0.011 |
Michael | +0.011 |
Neg logit contributions | |
ide | -0.021 |
salad | -0.020 |
room | -0.019 |
kins | -0.019 |
ics | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Buster | +0.872 |
Kenny | +0.865 |
Kel | +0.854 |
uster | +0.854 |
Hanna | +0.848 |
Neg logit contributions | |
castle | -0.745 |
ide | -0.737 |
room | -0.677 |
ull | -0.663 |
structures | -0.647 |
Token | eyes |
Token ID | 2951 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
castle | +0.084 |
ide | +0.075 |
salad | +0.074 |
structures | +0.072 |
room | +0.071 |
Neg logit contributions | |
Kel | -0.096 |
ha | -0.095 |
Michael | -0.095 |
Buster | -0.095 |
Kenny | -0.094 |
Token | lit |
Token ID | 6578 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
Buster | +0.004 |
Kenny | +0.004 |
pup | +0.004 |
Hanna | +0.003 |
Hannah | +0.003 |
Neg logit contributions | |
ide | -0.003 |
castle | -0.003 |
ull | -0.003 |
room | -0.002 |
structures | -0.002 |
Token | up |
Token ID | 510 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ide | +0.052 |
castle | +0.049 |
structures | +0.046 |
ull | +0.045 |
room | +0.045 |
Neg logit contributions | |
uster | -0.068 |
Buster | -0.067 |
Michael | -0.067 |
hesitation | -0.065 |
Kenny | -0.065 |
Token | as |
Token ID | 355 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ide | +0.012 |
castle | +0.012 |
structures | +0.011 |
ull | +0.011 |
room | +0.011 |
Neg logit contributions | |
Buster | -0.014 |
Kenny | -0.014 |
Hanna | -0.014 |
uster | -0.014 |
Michael | -0.014 |
Token | much |
Token ID | 881 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
castle | +0.043 |
ide | +0.041 |
room | +0.040 |
ull | +0.040 |
structures | +0.040 |
Neg logit contributions | |
Buster | -0.030 |
Hanna | -0.029 |
pup | -0.029 |
Kenny | -0.029 |
F | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ide | +0.041 |
castle | +0.039 |
structures | +0.037 |
salad | +0.036 |
ull | +0.036 |
Neg logit contributions | |
Buster | -0.055 |
Kenny | -0.055 |
Kel | -0.055 |
Hanna | -0.054 |
Michael | -0.054 |
Token | One |
Token ID | 1881 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
Kenny | +0.025 |
Matthew | +0.025 |
Michael | +0.025 |
training | +0.025 |
hesitation | +0.025 |
Neg logit contributions | |
ide | -0.022 |
room | -0.020 |
salad | -0.019 |
structures | -0.018 |
castle | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
Buster | +0.067 |
pup | +0.066 |
Kenny | +0.065 |
Hanna | +0.065 |
Cindy | +0.064 |
Neg logit contributions | |
castle | -0.094 |
ide | -0.093 |
ull | -0.088 |
structures | -0.088 |
room | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
ide | +0.028 |
room | +0.025 |
salad | +0.023 |
ics | +0.020 |
castle | +0.020 |
Neg logit contributions | |
reins | -0.073 |
uster | -0.073 |
Michael | -0.070 |
Kenny | -0.070 |
Buster | -0.070 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.87e+00 |
Pos logit contributions | |
reins | +0.045 |
Michael | +0.045 |
hesitation | +0.045 |
grizz | +0.044 |
Kenny | +0.044 |
Neg logit contributions | |
ide | -0.018 |
salad | -0.018 |
room | -0.016 |
kins | -0.014 |
ectar | -0.013 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
pup | +0.769 |
Buster | +0.755 |
Hanna | +0.753 |
Hannah | +0.744 |
F | +0.738 |
Neg logit contributions | |
castle | -0.876 |
ide | -0.872 |
structures | -0.831 |
ull | -0.817 |
room | -0.795 |
Token | to |
Token ID | 284 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
ide | +0.057 |
castle | +0.057 |
ull | +0.055 |
structures | +0.054 |
salad | +0.054 |
Neg logit contributions | |
Buster | -0.061 |
Kenny | -0.060 |
uster | -0.060 |
Hanna | -0.060 |
pup | -0.059 |
Token | go |
Token ID | 467 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Buster | +0.007 |
pup | +0.007 |
F | +0.007 |
Cindy | +0.007 |
Hannah | +0.007 |
Neg logit contributions | |
ide | -0.009 |
castle | -0.009 |
structures | -0.008 |
ull | -0.008 |
room | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
castle | +0.134 |
salad | +0.123 |
ull | +0.122 |
ide | +0.122 |
room | +0.117 |
Neg logit contributions | |
Michael | -0.185 |
Kel | -0.179 |
Hannah | -0.177 |
uster | -0.175 |
Haley | -0.175 |
Token | a |
Token ID | 257 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
uster | +0.083 |
ging | +0.072 |
Hank | +0.071 |
Michael | +0.071 |
Kenny | +0.071 |
Neg logit contributions | |
salad | -0.031 |
structures | -0.028 |
dragons | -0.028 |
ics | -0.026 |
pie | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Buster | +0.071 |
Kenny | +0.070 |
pup | +0.070 |
Hanna | +0.070 |
Hannah | +0.069 |
Neg logit contributions | |
ide | -0.075 |
castle | -0.075 |
ull | -0.071 |
room | -0.070 |
structures | -0.069 |
Token | a |
Token ID | 257 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Buster | +0.034 |
Kenny | +0.033 |
Hanna | +0.033 |
pup | +0.032 |
Hannah | +0.032 |
Neg logit contributions | |
ide | -0.041 |
castle | -0.040 |
ull | -0.039 |
room | -0.039 |
structures | -0.038 |
Token | little |
Token ID | 1310 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Buster | +0.020 |
Kenny | +0.020 |
Hanna | +0.019 |
Kel | +0.019 |
Cindy | +0.019 |
Neg logit contributions | |
ide | -0.022 |
castle | -0.022 |
ull | -0.021 |
room | -0.020 |
structures | -0.020 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Kenny | +0.010 |
Buster | +0.010 |
hesitation | +0.010 |
Hanna | +0.010 |
training | +0.010 |
Neg logit contributions | |
castle | -0.009 |
ide | -0.009 |
ull | -0.009 |
salad | -0.009 |
room | -0.009 |
Token | named |
Token ID | 3706 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Buster | +0.032 |
Kenny | +0.032 |
Hanna | +0.031 |
pup | +0.031 |
Hannah | +0.031 |
Neg logit contributions | |
ide | -0.033 |
castle | -0.033 |
ull | -0.031 |
room | -0.030 |
structures | -0.030 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.87e+00 |
Pos logit contributions | |
Buster | +0.104 |
Kenny | +0.103 |
Hanna | +0.103 |
Hannah | +0.102 |
pup | +0.102 |
Neg logit contributions | |
castle | -0.096 |
ide | -0.094 |
ull | -0.089 |
structures | -0.087 |
room | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Buster | +0.841 |
Kenny | +0.831 |
Hanna | +0.821 |
pup | +0.818 |
Cindy | +0.811 |
Neg logit contributions | |
ide | -0.799 |
castle | -0.783 |
ull | -0.747 |
room | -0.730 |
structures | -0.720 |
Token | She |
Token ID | 1375 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
hesitation | +0.015 |
training | +0.015 |
reins | +0.015 |
Michael | +0.015 |
Matthew | +0.015 |
Neg logit contributions | |
ide | -0.006 |
room | -0.005 |
salad | -0.004 |
ill | -0.004 |
structures | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
castle | +0.024 |
ide | +0.023 |
ull | +0.022 |
structures | +0.022 |
room | +0.022 |
Neg logit contributions | |
Buster | -0.027 |
Kenny | -0.027 |
pup | -0.027 |
Hanna | -0.027 |
Hannah | -0.027 |
Token | three |
Token ID | 1115 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Buster | +0.038 |
Kenny | +0.038 |
uster | +0.037 |
Hanna | +0.037 |
pup | +0.037 |
Neg logit contributions | |
ide | -0.042 |
castle | -0.042 |
ull | -0.040 |
room | -0.040 |
structures | -0.039 |
Token | years |
Token ID | 812 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
pup | +0.122 |
Buster | +0.120 |
Kenny | +0.119 |
Hanna | +0.117 |
F | +0.117 |
Neg logit contributions | |
castle | -0.257 |
ide | -0.251 |
ull | -0.244 |
room | -0.240 |
structures | -0.237 |
Token | big |
Token ID | 1263 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
uster | +0.035 |
Buster | +0.035 |
Kenny | +0.035 |
Kel | +0.034 |
Hanna | +0.034 |
Neg logit contributions | |
castle | -0.032 |
ide | -0.030 |
ull | -0.029 |
salad | -0.029 |
structures | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
castle | +0.049 |
ide | +0.045 |
salad | +0.044 |
structures | +0.043 |
ull | +0.043 |
Neg logit contributions | |
Hanna | -0.058 |
uster | -0.057 |
Buster | -0.057 |
Kenny | -0.057 |
Kel | -0.056 |
Token | hairy |
Token ID | 43873 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
uster | +0.038 |
Kenny | +0.037 |
Hanna | +0.036 |
Haley | +0.036 |
Buster | +0.036 |
Neg logit contributions | |
salad | -0.028 |
castle | -0.028 |
ull | -0.027 |
structure | -0.026 |
tower | -0.026 |
Token | cat |
Token ID | 3797 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
Buster | +0.162 |
Kenny | +0.161 |
Hanna | +0.161 |
Hannah | +0.157 |
Kel | +0.157 |
Neg logit contributions | |
castle | -0.164 |
ide | -0.160 |
ull | -0.153 |
room | -0.150 |
structures | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
ide | +0.072 |
castle | +0.071 |
ull | +0.067 |
room | +0.067 |
structures | +0.066 |
Neg logit contributions | |
Buster | -0.075 |
Hanna | -0.075 |
Kenny | -0.074 |
pup | -0.073 |
uster | -0.073 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
training | +0.036 |
hesitation | +0.036 |
Kenny | +0.036 |
Matthew | +0.035 |
Michael | +0.035 |
Neg logit contributions | |
ide | -0.019 |
salad | -0.019 |
room | -0.019 |
castle | -0.017 |
structures | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
Buster | +0.711 |
Kenny | +0.706 |
F | +0.700 |
pup | +0.697 |
Cindy | +0.693 |
Neg logit contributions | |
castle | -0.933 |
ide | -0.906 |
ull | -0.872 |
structures | -0.867 |
room | -0.860 |
Token | so |
Token ID | 523 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Buster | +0.048 |
Kenny | +0.047 |
Hanna | +0.047 |
pup | +0.047 |
Hannah | +0.046 |
Neg logit contributions | |
ide | -0.056 |
castle | -0.056 |
ull | -0.053 |
room | -0.052 |
structures | -0.052 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
castle | +0.077 |
structures | +0.072 |
ide | +0.071 |
room | +0.069 |
ull | +0.068 |
Neg logit contributions | |
F | -0.042 |
Cindy | -0.041 |
Kel | -0.040 |
Kenny | -0.040 |
pup | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
ide | +0.033 |
castle | +0.032 |
ull | +0.030 |
structures | +0.030 |
room | +0.029 |
Neg logit contributions | |
Buster | -0.030 |
Hanna | -0.030 |
Kenny | -0.029 |
uster | -0.029 |
pup | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
hesitation | +0.038 |
training | +0.038 |
Kenny | +0.037 |
Michael | +0.037 |
Matthew | +0.037 |
Neg logit contributions | |
ide | -0.019 |
room | -0.018 |
castle | -0.017 |
structures | -0.017 |
salad | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Buster | +0.006 |
Kenny | +0.006 |
Hanna | +0.006 |
pup | +0.006 |
Hannah | +0.006 |
Neg logit contributions | |
ide | -0.006 |
castle | -0.006 |
ull | -0.005 |
structures | -0.005 |
room | -0.005 |
Token | After |
Token ID | 2293 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
training | +0.023 |
buck | +0.023 |
Buster | +0.022 |
uster | +0.022 |
pup | +0.022 |
Neg logit contributions | |
ide | -0.017 |
room | -0.016 |
structures | -0.016 |
castle | -0.015 |
ull | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
uster | +0.173 |
reins | +0.156 |
pup | +0.152 |
Buster | +0.152 |
Michael | +0.151 |
Neg logit contributions | |
ide | -0.118 |
salad | -0.117 |
castle | -0.117 |
structures | -0.116 |
ull | -0.112 |
Token | while |
Token ID | 981 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Kel | +0.030 |
Kenny | +0.030 |
Hanna | +0.030 |
uster | +0.030 |
Buster | +0.029 |
Neg logit contributions | |
ide | -0.033 |
castle | -0.032 |
salad | -0.031 |
ull | -0.030 |
structures | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ide | +0.070 |
castle | +0.064 |
room | +0.061 |
ull | +0.060 |
nation | +0.058 |
Neg logit contributions | |
uster | -0.132 |
reins | -0.129 |
Matthew | -0.125 |
buck | -0.123 |
Buster | -0.123 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
uster | +0.032 |
reins | +0.030 |
training | +0.029 |
Buster | +0.029 |
buck | +0.028 |
Neg logit contributions | |
ide | -0.021 |
castle | -0.019 |
structures | -0.018 |
room | -0.018 |
salad | -0.018 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Buster | +0.763 |
Kenny | +0.754 |
Hanna | +0.746 |
pup | +0.742 |
Kel | +0.734 |
Neg logit contributions | |
castle | -0.859 |
ide | -0.853 |
ull | -0.807 |
room | -0.792 |
structures | -0.783 |
Token | that |
Token ID | 326 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ide | +0.072 |
castle | +0.066 |
salad | +0.061 |
ull | +0.060 |
ics | +0.060 |
Neg logit contributions | |
uster | -0.113 |
reins | -0.110 |
Michael | -0.103 |
training | -0.102 |
Tyler | -0.099 |
Token | she |
Token ID | 673 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
uster | +0.100 |
Buster | +0.096 |
Kenny | +0.095 |
Hanna | +0.094 |
reins | +0.093 |
Neg logit contributions | |
ide | -0.095 |
castle | -0.092 |
ull | -0.088 |
structures | -0.087 |
room | -0.086 |
Token | always |
Token ID | 1464 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
uster | +0.008 |
Buster | +0.008 |
Hanna | +0.008 |
Kenny | +0.008 |
Kel | +0.008 |
Neg logit contributions | |
ide | -0.008 |
castle | -0.008 |
ull | -0.007 |
room | -0.007 |
structures | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
uster | +0.014 |
Kenny | +0.014 |
Buster | +0.014 |
Hanna | +0.014 |
Kel | +0.014 |
Neg logit contributions | |
castle | -0.012 |
ide | -0.012 |
ull | -0.012 |
room | -0.011 |
salad | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Buster | +0.040 |
Kenny | +0.039 |
pup | +0.039 |
Hanna | +0.039 |
Hannah | +0.039 |
Neg logit contributions | |
ide | -0.042 |
castle | -0.042 |
ull | -0.040 |
room | -0.039 |
structures | -0.039 |
Token | shining |
Token ID | 22751 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Buster | +0.048 |
Kenny | +0.047 |
pup | +0.047 |
Hanna | +0.046 |
uster | +0.046 |
Neg logit contributions | |
ide | -0.061 |
castle | -0.060 |
ull | -0.057 |
room | -0.056 |
structures | -0.056 |
Token | so |
Token ID | 523 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
Buster | +0.108 |
Kenny | +0.106 |
pup | +0.105 |
Hanna | +0.105 |
Cindy | +0.104 |
Neg logit contributions | |
castle | -0.120 |
ide | -0.120 |
ull | -0.113 |
room | -0.111 |
structures | -0.111 |
Token | brightly |
Token ID | 35254 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ide | +0.054 |
castle | +0.052 |
ull | +0.049 |
salad | +0.049 |
structures | +0.047 |
Neg logit contributions | |
uster | -0.058 |
Buster | -0.057 |
pup | -0.057 |
reins | -0.057 |
Kenny | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Buster | +0.038 |
uster | +0.037 |
pup | +0.037 |
Kenny | +0.037 |
Hanna | +0.036 |
Neg logit contributions | |
castle | -0.031 |
ide | -0.031 |
ull | -0.028 |
room | -0.026 |
structures | -0.026 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
hesitation | +0.026 |
Michael | +0.026 |
Matthew | +0.026 |
training | +0.025 |
ha | +0.025 |
Neg logit contributions | |
room | -0.023 |
ide | -0.023 |
salad | -0.022 |
structures | -0.021 |
tub | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Buster | +0.812 |
Kenny | +0.801 |
pup | +0.800 |
Hanna | +0.799 |
Hannah | +0.790 |
Neg logit contributions | |
castle | -0.811 |
ide | -0.808 |
ull | -0.763 |
structures | -0.751 |
room | -0.747 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
castle | +0.074 |
ide | +0.070 |
room | +0.067 |
structures | +0.066 |
ull | +0.065 |
Neg logit contributions | |
Buster | -0.097 |
Hanna | -0.094 |
Kenny | -0.094 |
Kel | -0.094 |
Cindy | -0.093 |
Token | said |
Token ID | 531 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
Buster | +0.039 |
Kenny | +0.038 |
pup | +0.038 |
Hanna | +0.038 |
Kel | +0.037 |
Neg logit contributions | |
ide | -0.038 |
castle | -0.038 |
ull | -0.036 |
room | -0.035 |
structures | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
uster | +0.075 |
Buster | +0.074 |
Kenny | +0.074 |
reins | +0.072 |
pup | +0.072 |
Neg logit contributions | |
ide | -0.058 |
ull | -0.057 |
castle | -0.057 |
salad | -0.055 |
room | -0.054 |
Token | " |
Token ID | 366 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
uster | +0.049 |
luggage | +0.048 |
reins | +0.048 |
training | +0.048 |
buck | +0.047 |
Neg logit contributions | |
ide | -0.019 |
ull | -0.018 |
room | -0.016 |
castle | -0.016 |
salad | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
uster | +0.031 |
training | +0.028 |
luggage | +0.028 |
buck | +0.027 |
reins | +0.027 |
Neg logit contributions | |
ide | -0.026 |
room | -0.022 |
castle | -0.021 |
ics | -0.021 |
ull | -0.021 |
Token | other |
Token ID | 584 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
uster | +0.002 |
Hanna | +0.002 |
Matthew | +0.002 |
Michael | +0.002 |
Haley | +0.002 |
Neg logit contributions | |
structures | -0.001 |
ide | -0.001 |
castle | -0.001 |
room | -0.001 |
nation | -0.001 |
Token | animals |
Token ID | 4695 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
uster | +0.138 |
Hanna | +0.133 |
Buster | +0.131 |
Matthew | +0.131 |
Hannah | +0.130 |
Neg logit contributions | |
ide | -0.101 |
castle | -0.092 |
structures | -0.092 |
room | -0.090 |
ull | -0.086 |
Token | then |
Token ID | 788 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Buster | +0.007 |
Kenny | +0.007 |
Hanna | +0.007 |
pup | +0.007 |
Hannah | +0.007 |
Neg logit contributions | |
ide | -0.007 |
castle | -0.007 |
ull | -0.006 |
room | -0.006 |
structures | -0.006 |
Token | showed |
Token ID | 3751 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
Buster | +0.286 |
Kenny | +0.283 |
Hanna | +0.282 |
uster | +0.280 |
pup | +0.279 |
Neg logit contributions | |
castle | -0.265 |
ide | -0.262 |
ull | -0.248 |
structures | -0.241 |
room | -0.240 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
ide | +0.073 |
room | +0.066 |
structures | +0.065 |
ull | +0.063 |
castle | +0.061 |
Neg logit contributions | |
uster | -0.090 |
Buster | -0.088 |
training | -0.087 |
Matthew | -0.087 |
buck | -0.087 |
Token | around |
Token ID | 1088 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Buster | +0.854 |
Kenny | +0.847 |
Hanna | +0.840 |
uster | +0.830 |
pup | +0.828 |
Neg logit contributions | |
ide | -0.772 |
castle | -0.751 |
structures | -0.711 |
ull | -0.708 |
room | -0.692 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
Buster | +0.147 |
uster | +0.145 |
Hanna | +0.145 |
Kenny | +0.144 |
pup | +0.142 |
Neg logit contributions | |
ide | -0.144 |
castle | -0.139 |
room | -0.132 |
ull | -0.132 |
structures | -0.132 |
Token | jungle |
Token ID | 20712 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
ide | +0.000 |
castle | +0.000 |
ull | +0.000 |
room | +0.000 |
structures | +0.000 |
Neg logit contributions | |
Buster | -0.000 |
Kenny | -0.000 |
pup | -0.000 |
Hanna | -0.000 |
Cindy | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
castle | +0.269 |
ull | +0.267 |
ide | +0.267 |
room | +0.254 |
salad | +0.246 |
Neg logit contributions | |
Kenny | -0.215 |
pup | -0.214 |
Buster | -0.211 |
F | -0.211 |
buck | -0.204 |
Token | teaching |
Token ID | 7743 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
Buster | +0.026 |
Kenny | +0.025 |
pup | +0.025 |
Hanna | +0.025 |
Hannah | +0.025 |
Neg logit contributions | |
castle | -0.030 |
ide | -0.030 |
ull | -0.028 |
room | -0.028 |
structures | -0.028 |
Token | ate |
Token ID | 15063 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Kel | +0.070 |
Kenny | +0.070 |
uster | +0.069 |
Buster | +0.069 |
Cindy | +0.068 |
Neg logit contributions | |
ide | -0.049 |
castle | -0.047 |
room | -0.042 |
ull | -0.042 |
salad | -0.040 |
Token | loads |
Token ID | 15989 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ide | +0.240 |
castle | +0.240 |
ull | +0.226 |
room | +0.222 |
structures | +0.221 |
Neg logit contributions | |
Buster | -0.237 |
Kenny | -0.234 |
pup | -0.232 |
Hanna | -0.232 |
Hannah | -0.229 |
Token | of |
Token ID | 286 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
Buster | +0.189 |
Kenny | +0.188 |
Hanna | +0.187 |
pup | +0.185 |
Kel | +0.182 |
Neg logit contributions | |
ide | -0.196 |
castle | -0.190 |
ull | -0.180 |
room | -0.178 |
structures | -0.177 |
Token | food |
Token ID | 2057 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
uster | +0.061 |
Kenny | +0.059 |
Buster | +0.059 |
Hanna | +0.058 |
pup | +0.058 |
Neg logit contributions | |
salad | -0.044 |
ide | -0.042 |
structures | -0.041 |
castle | -0.041 |
ull | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
castle | +0.020 |
ide | +0.020 |
ull | +0.019 |
structures | +0.019 |
room | +0.019 |
Neg logit contributions | |
Buster | -0.017 |
Kenny | -0.017 |
pup | -0.017 |
Hanna | -0.017 |
Hannah | -0.017 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
Buster | +0.025 |
Kenny | +0.025 |
Hanna | +0.025 |
pup | +0.024 |
uster | +0.024 |
Neg logit contributions | |
castle | -0.025 |
ide | -0.025 |
ull | -0.023 |
structures | -0.023 |
room | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Buster | +0.813 |
Kenny | +0.803 |
Hanna | +0.794 |
pup | +0.793 |
Cindy | +0.784 |
Neg logit contributions | |
ide | -0.806 |
castle | -0.803 |
ull | -0.752 |
room | -0.743 |
structures | -0.731 |
Token | being |
Token ID | 852 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Buster | +0.042 |
Kenny | +0.042 |
Hanna | +0.041 |
pup | +0.041 |
Hannah | +0.041 |
Neg logit contributions | |
ide | -0.048 |
castle | -0.048 |
ull | -0.046 |
structures | -0.045 |
room | -0.045 |
Token | crazy |
Token ID | 7165 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
castle | +0.033 |
ide | +0.033 |
ull | +0.032 |
room | +0.031 |
structures | +0.030 |
Neg logit contributions | |
Buster | -0.029 |
Kenny | -0.029 |
pup | -0.028 |
Hanna | -0.028 |
Kel | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ide | +0.038 |
castle | +0.037 |
structures | +0.034 |
room | +0.034 |
ull | +0.033 |
Neg logit contributions | |
Kel | -0.047 |
Hanna | -0.047 |
Buster | -0.047 |
Kenny | -0.046 |
Haley | -0.046 |
Token | The |
Token ID | 383 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
uster | +0.021 |
Kel | +0.021 |
Buster | +0.021 |
hesitation | +0.021 |
Hanna | +0.021 |
Neg logit contributions | |
ide | -0.020 |
castle | -0.019 |
room | -0.019 |
structures | -0.019 |
salad | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Kenny | +0.055 |
F | +0.053 |
Kel | +0.051 |
Buster | +0.051 |
pup | +0.051 |
Neg logit contributions | |
castle | -0.100 |
structures | -0.094 |
ide | -0.092 |
salad | -0.092 |
ull | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Buster | +0.027 |
pup | +0.027 |
Hanna | +0.027 |
Kenny | +0.027 |
Cindy | +0.027 |
Neg logit contributions | |
castle | -0.049 |
ide | -0.047 |
structures | -0.045 |
ull | -0.045 |
room | -0.044 |
Token | little |
Token ID | 1310 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Buster | +0.023 |
pup | +0.023 |
Kenny | +0.023 |
Hanna | +0.023 |
Hannah | +0.022 |
Neg logit contributions | |
ide | -0.030 |
castle | -0.030 |
ull | -0.028 |
structures | -0.028 |
room | -0.028 |
Token | girl |
Token ID | 2576 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Buster | +0.022 |
Kenny | +0.022 |
Hanna | +0.022 |
Kel | +0.022 |
Hannah | +0.022 |
Neg logit contributions | |
castle | -0.024 |
ide | -0.024 |
ull | -0.023 |
room | -0.023 |
structures | -0.022 |
Token | called |
Token ID | 1444 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Buster | +0.038 |
pup | +0.038 |
Hanna | +0.038 |
Kenny | +0.038 |
F | +0.037 |
Neg logit contributions | |
castle | -0.048 |
ide | -0.047 |
structures | -0.044 |
ull | -0.044 |
room | -0.043 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
Buster | +0.166 |
Kenny | +0.164 |
pup | +0.163 |
Hanna | +0.162 |
Cindy | +0.159 |
Neg logit contributions | |
ide | -0.129 |
castle | -0.126 |
ull | -0.118 |
room | -0.118 |
structures | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Buster | +0.753 |
pup | +0.746 |
Hanna | +0.740 |
Kenny | +0.739 |
F | +0.733 |
Neg logit contributions | |
castle | -0.882 |
ide | -0.859 |
structures | -0.816 |
ull | -0.815 |
room | -0.801 |
Token | She |
Token ID | 1375 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
hesitation | +0.030 |
Michael | +0.029 |
training | +0.029 |
Matthew | +0.029 |
Kenny | +0.029 |
Neg logit contributions | |
ide | -0.011 |
room | -0.010 |
salad | -0.008 |
ectar | -0.007 |
ill | -0.006 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
castle | +0.022 |
ide | +0.021 |
structures | +0.020 |
ull | +0.020 |
room | +0.020 |
Neg logit contributions | |
Buster | -0.019 |
Hanna | -0.019 |
pup | -0.019 |
Kenny | -0.019 |
F | -0.019 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ide | +0.021 |
castle | +0.021 |
ull | +0.020 |
room | +0.020 |
structures | +0.019 |
Neg logit contributions | |
Buster | -0.015 |
pup | -0.015 |
Kenny | -0.015 |
Cindy | -0.015 |
Hanna | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Buster | +0.009 |
pup | +0.009 |
F | +0.009 |
Hanna | +0.009 |
Kenny | +0.009 |
Neg logit contributions | |
castle | -0.012 |
ide | -0.012 |
ull | -0.011 |
structures | -0.011 |
room | -0.011 |
Token | dad |
Token ID | 9955 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Buster | +0.025 |
pup | +0.024 |
Hanna | +0.024 |
Kenny | +0.024 |
Hannah | +0.024 |
Neg logit contributions | |
ide | -0.026 |
castle | -0.026 |
ull | -0.025 |
structures | -0.024 |
room | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ide | +0.027 |
castle | +0.024 |
room | +0.023 |
structures | +0.022 |
salad | +0.022 |
Neg logit contributions | |
Buster | -0.042 |
Kenny | -0.042 |
uster | -0.041 |
Hanna | -0.041 |
Michael | -0.041 |
Token | Every |
Token ID | 3887 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
hesitation | +0.025 |
reins | +0.025 |
training | +0.025 |
ha | +0.025 |
Matthew | +0.025 |
Neg logit contributions | |
ide | -0.014 |
room | -0.012 |
salad | -0.010 |
tub | -0.010 |
structures | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
Buster | +0.020 |
Kenny | +0.020 |
Hanna | +0.019 |
Kel | +0.019 |
Cindy | +0.019 |
Neg logit contributions | |
ide | -0.025 |
castle | -0.025 |
ull | -0.024 |
room | -0.023 |
structures | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
ide | +0.032 |
room | +0.029 |
ap | +0.024 |
salad | +0.023 |
ics | +0.023 |
Neg logit contributions | |
reins | -0.087 |
uster | -0.081 |
Kenny | -0.080 |
Michael | -0.080 |
grizz | -0.080 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
reins | +0.044 |
uster | +0.043 |
grizz | +0.043 |
Michael | +0.042 |
ha | +0.042 |
Neg logit contributions | |
ide | -0.024 |
salad | -0.023 |
room | -0.020 |
castle | -0.019 |
ics | -0.018 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Buster | +0.759 |
Hanna | +0.754 |
pup | +0.751 |
Hannah | +0.741 |
Kenny | +0.734 |
Neg logit contributions | |
castle | -0.856 |
ide | -0.851 |
ull | -0.813 |
structures | -0.805 |
room | -0.785 |
Token | to |
Token ID | 284 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
ide | +0.020 |
castle | +0.020 |
ull | +0.019 |
room | +0.019 |
structures | +0.019 |
Neg logit contributions | |
Buster | -0.017 |
Kenny | -0.017 |
pup | -0.016 |
Hanna | -0.016 |
Hannah | -0.016 |
Token | play |
Token ID | 711 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Buster | +0.006 |
pup | +0.006 |
Hanna | +0.006 |
Kenny | +0.006 |
Hannah | +0.006 |
Neg logit contributions | |
ide | -0.007 |
castle | -0.007 |
ull | -0.006 |
structures | -0.006 |
room | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
pup | +0.036 |
Buster | +0.036 |
Hannah | +0.035 |
Kenny | +0.034 |
Hanna | +0.034 |
Neg logit contributions | |
castle | -0.047 |
ull | -0.046 |
ide | -0.045 |
structures | -0.042 |
pulp | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
castle | +0.040 |
ide | +0.040 |
ull | +0.038 |
room | +0.037 |
structures | +0.037 |
Neg logit contributions | |
Buster | -0.029 |
Kenny | -0.029 |
Hanna | -0.029 |
Hannah | -0.028 |
pup | -0.028 |
Token | try |
Token ID | 1949 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
castle | +0.070 |
ide | +0.069 |
room | +0.065 |
ull | +0.063 |
structures | +0.063 |
Neg logit contributions | |
Buster | -0.079 |
Kenny | -0.077 |
Hanna | -0.077 |
Michael | -0.077 |
uster | -0.076 |
Token | on |
Token ID | 319 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Buster | +0.125 |
Kenny | +0.124 |
uster | +0.123 |
Hanna | +0.123 |
Michael | +0.122 |
Neg logit contributions | |
castle | -0.103 |
ide | -0.102 |
ull | -0.096 |
structures | -0.093 |
room | -0.093 |
Token | everything |
Token ID | 2279 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
uster | +0.180 |
Michael | +0.170 |
reins | +0.170 |
Hanna | +0.169 |
Buster | +0.168 |
Neg logit contributions | |
castle | -0.122 |
ide | -0.120 |
structures | -0.115 |
room | -0.114 |
salad | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ide | +0.103 |
castle | +0.100 |
room | +0.092 |
structures | +0.091 |
ull | +0.088 |
Neg logit contributions | |
Buster | -0.119 |
pup | -0.116 |
uster | -0.116 |
Hanna | -0.115 |
Matthew | -0.115 |
Token | Soon |
Token ID | 15894 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
buck | +0.018 |
hesitation | +0.017 |
Michael | +0.017 |
Kenny | +0.017 |
training | +0.017 |
Neg logit contributions | |
room | -0.018 |
ide | -0.017 |
salad | -0.016 |
structures | -0.015 |
castle | -0.015 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
ide | +0.007 |
salad | +0.006 |
room | +0.006 |
castle | +0.006 |
ics | +0.006 |
Neg logit contributions | |
reins | -0.014 |
uster | -0.013 |
Michael | -0.013 |
Matthew | -0.013 |
leaf | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
Buster | +0.826 |
Kenny | +0.814 |
Hanna | +0.811 |
Cindy | +0.803 |
pup | +0.801 |
Neg logit contributions | |
castle | -0.799 |
ide | -0.786 |
room | -0.738 |
ull | -0.733 |
structures | -0.705 |
Token | so |
Token ID | 523 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
Buster | +0.051 |
Kenny | +0.050 |
pup | +0.050 |
Kel | +0.049 |
Hanna | +0.049 |
Neg logit contributions | |
castle | -0.049 |
ide | -0.046 |
ull | -0.045 |
room | -0.043 |
structures | -0.042 |
Token | pleased |
Token ID | 10607 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ide | +0.060 |
castle | +0.059 |
ull | +0.056 |
structures | +0.055 |
room | +0.055 |
Neg logit contributions | |
Buster | -0.049 |
Kenny | -0.049 |
pup | -0.048 |
Hanna | -0.048 |
Hannah | -0.048 |
Token | with |
Token ID | 351 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
castle | +0.081 |
ide | +0.081 |
ull | +0.075 |
room | +0.073 |
structures | +0.073 |
Neg logit contributions | |
Buster | -0.093 |
Hanna | -0.092 |
Kenny | -0.091 |
uster | -0.091 |
pup | -0.089 |
Token | her |
Token ID | 607 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
ide | +0.070 |
salad | +0.064 |
structures | +0.063 |
ull | +0.062 |
room | +0.060 |
Neg logit contributions | |
reins | -0.156 |
uster | -0.155 |
ha | -0.155 |
Taxi | -0.154 |
Michael | -0.152 |
Token | box |
Token ID | 3091 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Kenny | +0.029 |
Buster | +0.029 |
Kel | +0.029 |
Hanna | +0.029 |
uster | +0.029 |
Neg logit contributions | |
castle | -0.026 |
salad | -0.024 |
ide | -0.024 |
ull | -0.023 |
structures | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
castle | +0.130 |
ide | +0.129 |
ull | +0.120 |
room | +0.119 |
structures | +0.116 |
Neg logit contributions | |
Buster | -0.137 |
Kenny | -0.134 |
Hanna | -0.134 |
pup | -0.133 |
Cindy | -0.132 |
Token | her |
Token ID | 607 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
ide | +0.032 |
room | +0.029 |
structures | +0.028 |
salad | +0.027 |
ull | +0.026 |
Neg logit contributions | |
uster | -0.054 |
Buster | -0.053 |
Kenny | -0.050 |
Matthew | -0.050 |
pup | -0.050 |
Token | room |
Token ID | 2119 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
ide | +0.065 |
castle | +0.064 |
ull | +0.062 |
structures | +0.058 |
room | +0.058 |
Neg logit contributions | |
Buster | -0.082 |
pup | -0.082 |
Kenny | -0.081 |
Hanna | -0.080 |
Hannah | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ide | +0.084 |
castle | +0.083 |
ull | +0.080 |
structures | +0.078 |
room | +0.077 |
Neg logit contributions | |
Buster | -0.074 |
Kenny | -0.073 |
pup | -0.073 |
Hanna | -0.072 |
Hannah | -0.072 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
hesitation | +0.025 |
training | +0.024 |
Michael | +0.023 |
Kenny | +0.023 |
Matthew | +0.023 |
Neg logit contributions | |
room | -0.009 |
ide | -0.009 |
salad | -0.009 |
ectar | -0.007 |
ics | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Buster | +0.728 |
Kenny | +0.726 |
pup | +0.721 |
Hanna | +0.718 |
Hannah | +0.715 |
Neg logit contributions | |
castle | -0.896 |
ide | -0.880 |
ull | -0.843 |
structures | -0.834 |
room | -0.820 |
Token | so |
Token ID | 523 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
Buster | +0.039 |
Kenny | +0.039 |
pup | +0.039 |
Hanna | +0.038 |
Hannah | +0.038 |
Neg logit contributions | |
ide | -0.049 |
castle | -0.049 |
ull | -0.046 |
room | -0.046 |
structures | -0.046 |
Token | excited |
Token ID | 6568 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
ide | +0.092 |
castle | +0.091 |
structures | +0.087 |
ull | +0.085 |
room | +0.084 |
Neg logit contributions | |
buck | -0.040 |
Hannah | -0.038 |
F | -0.038 |
Cindy | -0.036 |
Kel | -0.036 |
Token | ! |
Token ID | 0 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
ide | +0.042 |
castle | +0.041 |
ull | +0.038 |
structures | +0.038 |
room | +0.037 |
Neg logit contributions | |
Buster | -0.040 |
Hanna | -0.039 |
Kenny | -0.039 |
uster | -0.039 |
pup | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
hesitation | +0.094 |
training | +0.091 |
reins | +0.087 |
buck | +0.086 |
luggage | +0.086 |
Neg logit contributions | |
ide | -0.036 |
room | -0.035 |
salad | -0.029 |
structures | -0.029 |
castle | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
buck | +0.026 |
training | +0.026 |
Michael | +0.025 |
hesitation | +0.025 |
Matthew | +0.024 |
Neg logit contributions | |
ide | -0.020 |
room | -0.019 |
salad | -0.018 |
structures | -0.018 |
castle | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
castle | +0.013 |
ide | +0.013 |
ull | +0.013 |
room | +0.012 |
structures | +0.012 |
Neg logit contributions | |
Buster | -0.014 |
Kenny | -0.014 |
pup | -0.014 |
Hanna | -0.014 |
Cindy | -0.013 |
Token | all |
Token ID | 477 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
castle | +0.112 |
ide | +0.112 |
ull | +0.106 |
structures | +0.104 |
room | +0.104 |
Neg logit contributions | |
Buster | -0.103 |
Kenny | -0.102 |
pup | -0.101 |
Hanna | -0.101 |
Hannah | -0.100 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ide | +0.104 |
castle | +0.104 |
ull | +0.099 |
room | +0.097 |
structures | +0.097 |
Neg logit contributions | |
Buster | -0.090 |
Kenny | -0.088 |
pup | -0.088 |
Hanna | -0.088 |
Hannah | -0.086 |
Token | at |
Token ID | 379 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ide | +0.014 |
castle | +0.014 |
ull | +0.014 |
structures | +0.013 |
room | +0.013 |
Neg logit contributions | |
Buster | -0.014 |
Hanna | -0.014 |
Kenny | -0.014 |
Hannah | -0.014 |
pup | -0.014 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
ide | +0.118 |
castle | +0.115 |
ull | +0.109 |
structures | +0.109 |
room | +0.108 |
Neg logit contributions | |
Buster | -0.118 |
Hanna | -0.117 |
uster | -0.116 |
pup | -0.116 |
Kenny | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Buster | +0.828 |
Kenny | +0.819 |
Hanna | +0.816 |
pup | +0.806 |
Cindy | +0.802 |
Neg logit contributions | |
ide | -0.801 |
castle | -0.787 |
ull | -0.728 |
room | -0.724 |
structures | -0.723 |
Token | the |
Token ID | 262 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
Buster | +0.029 |
Kenny | +0.028 |
pup | +0.028 |
Hanna | +0.028 |
Hannah | +0.028 |
Neg logit contributions | |
castle | -0.031 |
ide | -0.031 |
ull | -0.029 |
room | -0.029 |
structures | -0.028 |
Token | leader |
Token ID | 3554 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
uster | +0.004 |
Hanna | +0.004 |
Buster | +0.004 |
Hannah | +0.004 |
Haley | +0.004 |
Neg logit contributions | |
castle | -0.004 |
ide | -0.004 |
structures | -0.004 |
ull | -0.004 |
room | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
ide | +0.142 |
castle | +0.141 |
ull | +0.133 |
room | +0.130 |
structures | +0.128 |
Neg logit contributions | |
Buster | -0.145 |
Kenny | -0.142 |
Hanna | -0.142 |
pup | -0.140 |
Cindy | -0.139 |
Token | the |
Token ID | 262 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
uster | +0.076 |
Michael | +0.071 |
Matthew | +0.071 |
buck | +0.071 |
Kel | +0.070 |
Neg logit contributions | |
ide | -0.045 |
room | -0.040 |
structures | -0.040 |
ull | -0.039 |
salad | -0.039 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Kenny | +0.009 |
Buster | +0.008 |
Hanna | +0.008 |
Kel | +0.008 |
Matthew | +0.008 |
Neg logit contributions | |
castle | -0.009 |
ide | -0.008 |
ull | -0.008 |
room | -0.008 |
salad | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
Buster | +0.035 |
pup | +0.034 |
Kenny | +0.034 |
Hanna | +0.034 |
Hannah | +0.034 |
Neg logit contributions | |
castle | -0.039 |
ide | -0.038 |
ull | -0.036 |
structures | -0.036 |
room | -0.035 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
F | +0.002 |
Hanna | +0.002 |
Hannah | +0.002 |
Cindy | +0.002 |
pup | +0.002 |
Neg logit contributions | |
castle | -0.003 |
ull | -0.003 |
ide | -0.003 |
structures | -0.003 |
ics | -0.002 |
Token | name |
Token ID | 1438 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
castle | +0.098 |
ide | +0.097 |
room | +0.093 |
ull | +0.092 |
structures | +0.091 |
Neg logit contributions | |
Buster | -0.082 |
Kenny | -0.080 |
Hanna | -0.079 |
Cindy | -0.077 |
Kel | -0.077 |
Token | was |
Token ID | 373 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
pup | +0.214 |
Buster | +0.214 |
Kenny | +0.214 |
Hanna | +0.211 |
F | +0.210 |
Neg logit contributions | |
castle | -0.304 |
ide | -0.300 |
structures | -0.286 |
ull | -0.282 |
room | -0.274 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
Buster | +0.048 |
Kenny | +0.047 |
Hanna | +0.047 |
pup | +0.047 |
Hannah | +0.047 |
Neg logit contributions | |
castle | -0.046 |
ide | -0.046 |
ull | -0.043 |
room | -0.042 |
structures | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
Buster | +0.788 |
Kenny | +0.776 |
pup | +0.775 |
Hanna | +0.773 |
Hannah | +0.763 |
Neg logit contributions | |
castle | -0.838 |
ide | -0.831 |
ull | -0.787 |
structures | -0.773 |
room | -0.771 |
Token | She |
Token ID | 1375 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
hesitation | +0.010 |
reins | +0.010 |
training | +0.010 |
Michael | +0.010 |
Matthew | +0.010 |
Neg logit contributions | |
ide | -0.004 |
room | -0.003 |
salad | -0.003 |
ectar | -0.002 |
ill | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
castle | +0.019 |
ide | +0.019 |
ull | +0.017 |
structures | +0.017 |
room | +0.017 |
Neg logit contributions | |
Buster | -0.023 |
Kenny | -0.022 |
Hanna | -0.022 |
pup | -0.022 |
Hannah | -0.022 |
Token | three |
Token ID | 1115 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Buster | +0.046 |
Kenny | +0.045 |
pup | +0.044 |
Hanna | +0.044 |
uster | +0.044 |
Neg logit contributions | |
ide | -0.053 |
castle | -0.052 |
ull | -0.050 |
room | -0.050 |
structures | -0.049 |
Token | years |
Token ID | 812 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Buster | +0.123 |
pup | +0.122 |
Kenny | +0.121 |
Hanna | +0.120 |
Hannah | +0.118 |
Neg logit contributions | |
castle | -0.262 |
ide | -0.260 |
ull | -0.250 |
room | -0.246 |
structures | -0.244 |
Token | was |
Token ID | 373 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Buster | +0.054 |
Kenny | +0.053 |
Hanna | +0.053 |
Hannah | +0.053 |
Cindy | +0.053 |
Neg logit contributions | |
castle | -0.058 |
ide | -0.056 |
structures | -0.055 |
ull | -0.054 |
room | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Buster | +0.025 |
Hanna | +0.025 |
Cindy | +0.024 |
pup | +0.024 |
Hannah | +0.024 |
Neg logit contributions | |
castle | -0.047 |
ide | -0.046 |
structures | -0.044 |
room | -0.043 |
ull | -0.043 |
Token | little |
Token ID | 1310 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Buster | +0.018 |
Kenny | +0.017 |
pup | +0.017 |
Hanna | +0.017 |
Hannah | +0.017 |
Neg logit contributions | |
ide | -0.020 |
castle | -0.020 |
ull | -0.019 |
room | -0.019 |
structures | -0.019 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Buster | +0.012 |
Kenny | +0.012 |
Hanna | +0.012 |
Kel | +0.012 |
Hannah | +0.012 |
Neg logit contributions | |
castle | -0.013 |
ide | -0.012 |
ull | -0.012 |
structures | -0.012 |
room | -0.012 |
Token | named |
Token ID | 3706 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Kenny | +0.035 |
Buster | +0.035 |
uster | +0.035 |
Kel | +0.034 |
Hanna | +0.034 |
Neg logit contributions | |
ide | -0.028 |
castle | -0.028 |
ull | -0.026 |
room | -0.025 |
structures | -0.024 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +9.82e+00 |
Pos logit contributions | |
Buster | +0.103 |
pup | +0.102 |
Kenny | +0.101 |
Hanna | +0.099 |
uster | +0.099 |
Neg logit contributions | |
ide | -0.092 |
castle | -0.088 |
room | -0.084 |
ull | -0.083 |
structures | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Kenny | +0.930 |
Buster | +0.927 |
uster | +0.916 |
training | +0.915 |
hesitation | +0.913 |
Neg logit contributions | |
ide | -0.705 |
castle | -0.648 |
ull | -0.630 |
room | -0.617 |
structures | -0.568 |
Token | She |
Token ID | 1375 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
hesitation | +0.013 |
reins | +0.013 |
training | +0.013 |
buck | +0.013 |
Matthew | +0.012 |
Neg logit contributions | |
ide | -0.005 |
room | -0.004 |
ill | -0.003 |
ectar | -0.003 |
ackers | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ide | +0.022 |
castle | +0.021 |
ull | +0.020 |
room | +0.020 |
structures | +0.019 |
Neg logit contributions | |
Buster | -0.025 |
Kenny | -0.025 |
uster | -0.025 |
pup | -0.025 |
Hanna | -0.025 |
Token | three |
Token ID | 1115 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Buster | +0.046 |
uster | +0.046 |
Kenny | +0.045 |
Matthew | +0.045 |
pup | +0.045 |
Neg logit contributions | |
ide | -0.049 |
castle | -0.048 |
room | -0.047 |
ull | -0.047 |
structures | -0.045 |
Token | years |
Token ID | 812 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Buster | +0.136 |
Kenny | +0.132 |
Hanna | +0.131 |
pup | +0.130 |
Cindy | +0.128 |
Neg logit contributions | |
ide | -0.246 |
castle | -0.244 |
ull | -0.233 |
structures | -0.231 |
room | -0.230 |
Token | She |
Token ID | 1375 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Buster | +0.008 |
pup | +0.008 |
Kenny | +0.008 |
Hanna | +0.007 |
Matthew | +0.007 |
Neg logit contributions | |
ide | -0.007 |
castle | -0.007 |
room | -0.006 |
structures | -0.006 |
ull | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ide | +0.023 |
castle | +0.023 |
ull | +0.022 |
structures | +0.022 |
room | +0.022 |
Neg logit contributions | |
Buster | -0.021 |
Kenny | -0.021 |
Hanna | -0.021 |
pup | -0.021 |
Hannah | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Buster | +0.051 |
Hannah | +0.051 |
Cindy | +0.051 |
Hanna | +0.051 |
pup | +0.050 |
Neg logit contributions | |
ide | -0.074 |
castle | -0.074 |
ull | -0.070 |
structures | -0.070 |
room | -0.069 |
Token | " |
Token ID | 366 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Kenny | +0.025 |
Buster | +0.025 |
pup | +0.025 |
Hanna | +0.024 |
Kel | +0.024 |
Neg logit contributions | |
ide | -0.022 |
castle | -0.022 |
ull | -0.021 |
room | -0.021 |
structures | -0.020 |
Token | V |
Token ID | 53 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ide | +0.078 |
room | +0.076 |
castle | +0.075 |
ull | +0.072 |
anish | +0.067 |
Neg logit contributions | |
Buster | -0.076 |
Kenny | -0.074 |
Kel | -0.071 |
hesitation | -0.070 |
uster | -0.070 |
Token | anish |
Token ID | 7115 |
Feature activation | -8.77e+00 |
Pos logit contributions | |
pup | +0.340 |
Hannah | +0.339 |
Kenny | +0.337 |
Buster | +0.337 |
Hanna | +0.336 |
Neg logit contributions | |
castle | -0.097 |
ide | -0.091 |
structures | -0.086 |
ull | -0.084 |
salad | -0.077 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
ide | +0.736 |
room | +0.690 |
castle | +0.666 |
ull | +0.620 |
ics | +0.600 |
Neg logit contributions | |
Buster | -0.743 |
buck | -0.724 |
Kenny | -0.724 |
luggage | -0.724 |
Kel | -0.710 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
castle | +0.065 |
ide | +0.065 |
ull | +0.061 |
structures | +0.060 |
room | +0.060 |
Neg logit contributions | |
Buster | -0.057 |
Kenny | -0.057 |
Hanna | -0.056 |
pup | -0.056 |
Hannah | -0.055 |
Token | then |
Token ID | 788 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Hannah | +0.023 |
Hanna | +0.023 |
Cindy | +0.023 |
F | +0.023 |
Kenny | +0.022 |
Neg logit contributions | |
ide | -0.031 |
castle | -0.030 |
ull | -0.030 |
structures | -0.029 |
room | -0.028 |
Token | waited |
Token ID | 13488 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Buster | +0.262 |
pup | +0.255 |
Kenny | +0.254 |
uster | +0.254 |
Hanna | +0.251 |
Neg logit contributions | |
castle | -0.273 |
ide | -0.269 |
ull | -0.252 |
room | -0.252 |
structures | -0.250 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ide | +0.034 |
castle | +0.034 |
ull | +0.031 |
room | +0.031 |
structures | +0.031 |
Neg logit contributions | |
Buster | -0.032 |
Kenny | -0.031 |
pup | -0.031 |
Hanna | -0.031 |
Kel | -0.030 |
Token | something |
Token ID | 1223 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
castle | +0.093 |
ide | +0.092 |
ull | +0.088 |
room | +0.086 |
structures | +0.086 |
Neg logit contributions | |
Buster | -0.075 |
Kenny | -0.074 |
pup | -0.074 |
Hanna | -0.074 |
Hannah | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Buster | +0.046 |
Hanna | +0.045 |
Kenny | +0.045 |
pup | +0.045 |
Hannah | +0.045 |
Neg logit contributions | |
castle | -0.044 |
ide | -0.043 |
ull | -0.042 |
room | -0.041 |
structures | -0.040 |
Token | say |
Token ID | 910 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Buster | +0.018 |
Kenny | +0.018 |
Hanna | +0.018 |
pup | +0.018 |
Hannah | +0.018 |
Neg logit contributions | |
castle | -0.018 |
ide | -0.017 |
ull | -0.016 |
structures | -0.016 |
room | -0.016 |
Token | ' |
Token ID | 705 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
Buster | +0.079 |
Kenny | +0.077 |
pup | +0.077 |
uster | +0.077 |
Kel | +0.076 |
Neg logit contributions | |
castle | -0.101 |
ide | -0.100 |
ull | -0.095 |
structures | -0.095 |
room | -0.095 |
Token | v |
Token ID | 85 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
Buster | +0.068 |
Kenny | +0.066 |
Hanna | +0.065 |
Hannah | +0.065 |
uster | +0.065 |
Neg logit contributions | |
ide | -0.071 |
castle | -0.068 |
room | -0.067 |
ull | -0.066 |
structures | -0.061 |
Token | anish |
Token ID | 7115 |
Feature activation | -8.72e+00 |
Pos logit contributions | |
castle | +0.051 |
ide | +0.048 |
structures | +0.048 |
salad | +0.046 |
ull | +0.043 |
Neg logit contributions | |
pup | -0.079 |
Buster | -0.078 |
Hannah | -0.078 |
Kenny | -0.076 |
Hanna | -0.076 |
Token | !' |
Token ID | 13679 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
ide | +0.744 |
room | +0.682 |
castle | +0.669 |
ull | +0.646 |
ics | +0.619 |
Neg logit contributions | |
Kenny | -0.731 |
Buster | -0.719 |
Kel | -0.707 |
buck | -0.700 |
pup | -0.693 |
Token | and |
Token ID | 290 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ide | +0.051 |
castle | +0.049 |
room | +0.049 |
ull | +0.047 |
structures | +0.047 |
Neg logit contributions | |
Buster | -0.063 |
Kenny | -0.063 |
Kel | -0.061 |
Matthew | -0.060 |
Hanna | -0.060 |
Token | then |
Token ID | 788 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Buster | +0.015 |
Kenny | +0.015 |
pup | +0.015 |
Hanna | +0.015 |
uster | +0.015 |
Neg logit contributions | |
castle | -0.023 |
ide | -0.023 |
structures | -0.021 |
ull | -0.021 |
room | -0.021 |
Token | come |
Token ID | 1282 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Buster | +0.261 |
uster | +0.256 |
Kenny | +0.255 |
pup | +0.255 |
Matthew | +0.253 |
Neg logit contributions | |
castle | -0.275 |
ide | -0.270 |
ull | -0.252 |
room | -0.251 |
structures | -0.250 |
Token | out |
Token ID | 503 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
castle | +0.041 |
ide | +0.040 |
ull | +0.039 |
room | +0.039 |
structures | +0.036 |
Neg logit contributions | |
hesitation | -0.045 |
Buster | -0.044 |
Matthew | -0.044 |
Hanna | -0.044 |
Michael | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Buster | +0.119 |
pup | +0.118 |
Kenny | +0.118 |
F | +0.117 |
Hanna | +0.115 |
Neg logit contributions | |
castle | -0.154 |
ide | -0.152 |
ull | -0.149 |
structures | -0.143 |
room | -0.140 |
Token | said |
Token ID | 531 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
buck | +0.009 |
Kenny | +0.009 |
Buster | +0.009 |
F | +0.009 |
pup | +0.009 |
Neg logit contributions | |
ide | -0.015 |
castle | -0.014 |
room | -0.013 |
ull | -0.013 |
structures | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
F | +0.038 |
Kenny | +0.037 |
Buster | +0.036 |
Cindy | +0.036 |
Hannah | +0.035 |
Neg logit contributions | |
ide | -0.072 |
castle | -0.070 |
room | -0.066 |
structures | -0.066 |
ull | -0.066 |
Token | " |
Token ID | 366 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
Buster | +0.017 |
Kenny | +0.016 |
Hanna | +0.016 |
pup | +0.016 |
Hannah | +0.016 |
Neg logit contributions | |
ide | -0.013 |
castle | -0.013 |
ull | -0.013 |
room | -0.012 |
structures | -0.012 |
Token | V |
Token ID | 53 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
castle | +0.106 |
ide | +0.105 |
ull | +0.101 |
structures | +0.100 |
room | +0.098 |
Neg logit contributions | |
Buster | -0.059 |
Kenny | -0.058 |
pup | -0.058 |
Hanna | -0.058 |
Cindy | -0.057 |
Token | anish |
Token ID | 7115 |
Feature activation | -8.71e+00 |
Pos logit contributions | |
pup | +0.324 |
Michael | +0.319 |
Kenny | +0.318 |
F | +0.315 |
Hannah | +0.315 |
Neg logit contributions | |
pulp | -0.094 |
salad | -0.080 |
castle | -0.079 |
structures | -0.075 |
pole | -0.066 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
castle | +0.843 |
ide | +0.816 |
ull | +0.805 |
structures | +0.789 |
salad | +0.769 |
Neg logit contributions | |
Kenny | -0.613 |
F | -0.601 |
Buster | -0.600 |
pup | -0.593 |
Hannah | -0.589 |
Token | The |
Token ID | 383 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
castle | +0.093 |
ide | +0.090 |
nation | +0.086 |
structures | +0.085 |
ull | +0.085 |
Neg logit contributions | |
F | -0.043 |
Kenny | -0.042 |
Buster | -0.039 |
buck | -0.037 |
Hank | -0.037 |
Token | toy |
Token ID | 13373 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ide | +0.054 |
castle | +0.054 |
ull | +0.051 |
room | +0.050 |
structures | +0.050 |
Neg logit contributions | |
Buster | -0.047 |
Kenny | -0.046 |
pup | -0.046 |
Hanna | -0.046 |
Hannah | -0.045 |
Token | car |
Token ID | 1097 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
pup | +0.039 |
Buster | +0.038 |
Kenny | +0.038 |
F | +0.038 |
buck | +0.038 |
Neg logit contributions | |
ide | -0.046 |
castle | -0.044 |
ull | -0.042 |
structures | -0.040 |
room | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
buck | +0.114 |
Kenny | +0.109 |
F | +0.108 |
pup | +0.107 |
Buster | +0.105 |
Neg logit contributions | |
ide | -0.162 |
castle | -0.157 |
ull | -0.152 |
salad | -0.148 |
structures | -0.148 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
pup | +0.100 |
F | +0.097 |
Buster | +0.097 |
Kenny | +0.096 |
buck | +0.094 |
Neg logit contributions | |
castle | -0.146 |
ull | -0.146 |
ide | -0.144 |
structures | -0.139 |
room | -0.135 |
Token | said |
Token ID | 531 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Buster | +0.015 |
Kenny | +0.015 |
pup | +0.014 |
F | +0.014 |
Hanna | +0.014 |
Neg logit contributions | |
ide | -0.020 |
castle | -0.020 |
ull | -0.019 |
room | -0.019 |
structures | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Buster | +0.041 |
Kenny | +0.041 |
F | +0.041 |
Cindy | +0.040 |
pup | +0.040 |
Neg logit contributions | |
ide | -0.060 |
castle | -0.059 |
room | -0.056 |
structures | -0.055 |
ull | -0.055 |
Token | " |
Token ID | 366 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Buster | +0.021 |
pup | +0.020 |
Hanna | +0.020 |
Kenny | +0.020 |
uster | +0.020 |
Neg logit contributions | |
castle | -0.014 |
ide | -0.014 |
ull | -0.013 |
room | -0.013 |
structures | -0.013 |
Token | V |
Token ID | 53 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ide | +0.106 |
castle | +0.103 |
ull | +0.101 |
room | +0.100 |
structures | +0.095 |
Neg logit contributions | |
Buster | -0.068 |
Kenny | -0.066 |
Hanna | -0.064 |
Hannah | -0.064 |
hesitation | -0.064 |
Token | anish |
Token ID | 7115 |
Feature activation | -8.66e+00 |
Pos logit contributions | |
Michael | +0.343 |
Hannah | +0.341 |
pup | +0.339 |
Kenny | +0.338 |
uster | +0.334 |
Neg logit contributions | |
castle | -0.072 |
pulp | -0.070 |
salad | -0.067 |
structures | -0.064 |
ull | -0.060 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ide | +0.769 |
castle | +0.751 |
room | +0.721 |
ull | +0.707 |
structures | +0.692 |
Neg logit contributions | |
Buster | -0.676 |
Hanna | -0.662 |
pup | -0.658 |
Kenny | -0.655 |
Cindy | -0.649 |
Token | The |
Token ID | 383 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
ide | +0.069 |
castle | +0.069 |
ull | +0.065 |
structures | +0.064 |
room | +0.063 |
Neg logit contributions | |
Buster | -0.057 |
Kenny | -0.057 |
F | -0.055 |
pup | -0.055 |
Cindy | -0.055 |
Token | couch |
Token ID | 18507 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
salad | +0.039 |
structures | +0.038 |
room | +0.038 |
ide | +0.038 |
castle | +0.038 |
Neg logit contributions | |
uster | -0.059 |
Matthew | -0.058 |
Buster | -0.057 |
Hank | -0.057 |
Kenny | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
pup | +0.101 |
Kenny | +0.100 |
buck | +0.099 |
F | +0.099 |
Hannah | +0.095 |
Neg logit contributions | |
ide | -0.142 |
castle | -0.140 |
ull | -0.138 |
structures | -0.136 |
room | -0.132 |
Token | gone |
Token ID | 3750 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Buster | +0.038 |
Kenny | +0.037 |
pup | +0.037 |
Hanna | +0.037 |
Hannah | +0.037 |
Neg logit contributions | |
castle | -0.041 |
ide | -0.041 |
ull | -0.039 |
room | -0.038 |
structures | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Buster | +0.079 |
Kenny | +0.078 |
Hanna | +0.078 |
pup | +0.077 |
Hannah | +0.077 |
Neg logit contributions | |
ide | -0.096 |
castle | -0.096 |
ull | -0.091 |
room | -0.089 |
structures | -0.089 |
Token | said |
Token ID | 531 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
Buster | +0.012 |
Kenny | +0.012 |
buck | +0.012 |
pup | +0.012 |
F | +0.011 |
Neg logit contributions | |
ide | -0.016 |
castle | -0.016 |
room | -0.015 |
ull | -0.015 |
structures | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
F | +0.042 |
Kenny | +0.042 |
Buster | +0.042 |
Cindy | +0.041 |
Hanna | +0.040 |
Neg logit contributions | |
ide | -0.073 |
castle | -0.071 |
room | -0.067 |
ull | -0.066 |
structures | -0.066 |
Token | " |
Token ID | 366 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
Buster | +0.019 |
pup | +0.019 |
Hanna | +0.019 |
Kenny | +0.019 |
Hannah | +0.019 |
Neg logit contributions | |
ide | -0.015 |
castle | -0.015 |
ull | -0.014 |
structures | -0.014 |
room | -0.014 |
Token | V |
Token ID | 53 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ide | +0.099 |
castle | +0.098 |
ull | +0.094 |
room | +0.093 |
structures | +0.092 |
Neg logit contributions | |
Buster | -0.061 |
Kenny | -0.060 |
pup | -0.060 |
Hanna | -0.060 |
Hannah | -0.059 |
Token | anish |
Token ID | 7115 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
pup | +0.343 |
Kenny | +0.340 |
Michael | +0.339 |
F | +0.335 |
Peggy | +0.328 |
Neg logit contributions | |
pulp | -0.088 |
salad | -0.074 |
castle | -0.071 |
structures | -0.070 |
ull | -0.063 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
castle | +0.815 |
ide | +0.794 |
ull | +0.776 |
structures | +0.762 |
salad | +0.741 |
Neg logit contributions | |
Kenny | -0.619 |
Buster | -0.614 |
pup | -0.605 |
F | -0.605 |
Hannah | -0.600 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ide | +0.075 |
castle | +0.074 |
ull | +0.072 |
structures | +0.067 |
ics | +0.066 |
Neg logit contributions | |
Kenny | -0.049 |
F | -0.049 |
buck | -0.047 |
Buster | -0.047 |
pup | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Buster | +0.044 |
Hanna | +0.044 |
pup | +0.043 |
Kenny | +0.043 |
Hannah | +0.043 |
Neg logit contributions | |
castle | -0.044 |
ide | -0.043 |
ull | -0.041 |
room | -0.041 |
structures | -0.041 |
Token | his |
Token ID | 465 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
Buster | +0.016 |
Hanna | +0.016 |
Kenny | +0.016 |
pup | +0.015 |
uster | +0.015 |
Neg logit contributions | |
castle | -0.019 |
ide | -0.018 |
ull | -0.018 |
room | -0.018 |
structures | -0.018 |
Token | toy |
Token ID | 13373 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
castle | +0.074 |
ide | +0.073 |
ull | +0.069 |
structures | +0.068 |
room | +0.068 |
Neg logit contributions | |
Buster | -0.075 |
Kenny | -0.074 |
Hanna | -0.074 |
Cindy | -0.073 |
Hannah | -0.073 |
Token | magic |
Token ID | 5536 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
castle | +0.007 |
salad | +0.006 |
ull | +0.006 |
structures | +0.006 |
nation | +0.006 |
Neg logit contributions | |
Kenny | -0.008 |
Kel | -0.008 |
Buster | -0.007 |
Kathy | -0.007 |
uster | -0.007 |
Token | word |
Token ID | 1573 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
castle | +0.077 |
ull | +0.073 |
ide | +0.072 |
room | +0.069 |
structures | +0.069 |
Neg logit contributions | |
Buster | -0.081 |
Cindy | -0.081 |
Kenny | -0.080 |
Matthew | -0.080 |
Hanna | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
castle | +0.042 |
ide | +0.042 |
ull | +0.040 |
room | +0.039 |
structures | +0.039 |
Neg logit contributions | |
Buster | -0.042 |
Hanna | -0.042 |
Cindy | -0.041 |
uster | -0.041 |
pup | -0.041 |
Token | " |
Token ID | 366 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
Buster | +0.022 |
Kenny | +0.022 |
Hanna | +0.022 |
pup | +0.021 |
Hannah | +0.021 |
Neg logit contributions | |
castle | -0.019 |
ide | -0.019 |
ull | -0.018 |
room | -0.017 |
structures | -0.017 |
Token | V |
Token ID | 53 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ide | +0.094 |
castle | +0.093 |
ull | +0.089 |
room | +0.088 |
structures | +0.086 |
Neg logit contributions | |
Buster | -0.072 |
Kenny | -0.070 |
Hanna | -0.070 |
pup | -0.070 |
Hannah | -0.069 |
Token | anish |
Token ID | 7115 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
pup | +0.306 |
Hannah | +0.303 |
Hank | +0.299 |
Matthew | +0.298 |
F | +0.296 |
Neg logit contributions | |
structures | -0.123 |
castle | -0.119 |
ide | -0.118 |
salad | -0.115 |
pulp | -0.113 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
ide | +0.725 |
castle | +0.709 |
room | +0.676 |
ull | +0.667 |
structures | +0.649 |
Neg logit contributions | |
Buster | -0.705 |
Kenny | -0.692 |
pup | -0.691 |
Hanna | -0.690 |
Cindy | -0.680 |
Token | When |
Token ID | 1649 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ide | +0.065 |
castle | +0.064 |
ull | +0.061 |
structures | +0.060 |
room | +0.059 |
Neg logit contributions | |
Buster | -0.055 |
Kenny | -0.054 |
pup | -0.053 |
F | -0.053 |
Hannah | -0.053 |
Token | he |
Token ID | 339 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
uster | +0.048 |
reins | +0.045 |
Matthew | +0.044 |
pup | +0.043 |
Hanna | +0.043 |
Neg logit contributions | |
castle | -0.033 |
salad | -0.030 |
structures | -0.030 |
ull | -0.029 |
tower | -0.029 |
Token | opened |
Token ID | 4721 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Buster | +0.058 |
Kenny | +0.058 |
Hanna | +0.057 |
pup | +0.057 |
Hannah | +0.057 |
Neg logit contributions | |
ide | -0.077 |
castle | -0.077 |
structures | -0.074 |
ull | -0.072 |
room | -0.071 |
Token | his |
Token ID | 465 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
castle | +0.079 |
ide | +0.078 |
structures | +0.073 |
ull | +0.072 |
salad | +0.071 |
Neg logit contributions | |
pup | -0.110 |
uster | -0.108 |
Hanna | -0.108 |
Buster | -0.106 |
reins | -0.106 |
Token | They |
Token ID | 1119 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
ide | +0.007 |
castle | +0.007 |
ull | +0.007 |
room | +0.007 |
structures | +0.007 |
Neg logit contributions | |
Buster | -0.012 |
Kenny | -0.011 |
pup | -0.011 |
Hanna | -0.011 |
Hannah | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
ide | +0.030 |
castle | +0.030 |
ull | +0.028 |
structures | +0.028 |
room | +0.028 |
Neg logit contributions | |
Buster | -0.025 |
buck | -0.025 |
Kenny | -0.025 |
Hanna | -0.025 |
F | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Buster | +0.047 |
Kenny | +0.047 |
pup | +0.046 |
Hanna | +0.046 |
uster | +0.045 |
Neg logit contributions | |
castle | -0.053 |
ide | -0.053 |
ull | -0.050 |
structures | -0.049 |
room | -0.049 |
Token | " |
Token ID | 366 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
Buster | +0.013 |
Kenny | +0.013 |
pup | +0.013 |
Hanna | +0.013 |
Hannah | +0.012 |
Neg logit contributions | |
castle | -0.012 |
ide | -0.012 |
ull | -0.011 |
room | -0.011 |
structures | -0.011 |
Token | V |
Token ID | 53 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ide | +0.090 |
castle | +0.088 |
room | +0.086 |
ull | +0.084 |
structures | +0.081 |
Neg logit contributions | |
Buster | -0.075 |
Kenny | -0.073 |
Hanna | -0.071 |
pup | -0.071 |
Hannah | -0.071 |
Token | anish |
Token ID | 7115 |
Feature activation | -8.56e+00 |
Pos logit contributions | |
pup | +0.356 |
Michael | +0.349 |
Kenny | +0.347 |
F | +0.346 |
Hannah | +0.343 |
Neg logit contributions | |
salad | -0.094 |
pulp | -0.089 |
castle | -0.088 |
ull | -0.072 |
structures | -0.070 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
ide | +0.731 |
castle | +0.707 |
room | +0.679 |
ull | +0.662 |
structures | +0.645 |
Neg logit contributions | |
Buster | -0.703 |
Kenny | -0.686 |
pup | -0.686 |
Hanna | -0.683 |
Cindy | -0.677 |
Token | each |
Token ID | 1123 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ide | +0.064 |
castle | +0.064 |
ull | +0.060 |
room | +0.059 |
structures | +0.059 |
Neg logit contributions | |
Buster | -0.063 |
Kenny | -0.062 |
pup | -0.062 |
Hanna | -0.062 |
Cindy | -0.061 |
Token | time |
Token ID | 640 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ide | +0.141 |
castle | +0.141 |
ull | +0.134 |
room | +0.132 |
structures | +0.131 |
Neg logit contributions | |
Buster | -0.115 |
Kenny | -0.113 |
Hanna | -0.112 |
pup | -0.112 |
Cindy | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
uster | +0.025 |
Buster | +0.024 |
Hanna | +0.024 |
pup | +0.024 |
Matthew | +0.024 |
Neg logit contributions | |
ide | -0.021 |
room | -0.020 |
castle | -0.020 |
ull | -0.019 |
ics | -0.018 |
Token | All |
Token ID | 1439 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Buster | +0.002 |
pup | +0.002 |
Kenny | +0.002 |
Hanna | +0.002 |
Kel | +0.002 |
Neg logit contributions | |
ide | -0.001 |
castle | -0.001 |
room | -0.001 |
ull | -0.001 |
structures | -0.001 |
Token | flew |
Token ID | 13112 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ide | +0.321 |
castle | +0.316 |
structures | +0.299 |
ull | +0.298 |
room | +0.295 |
Neg logit contributions | |
Buster | -0.332 |
pup | -0.326 |
Kenny | -0.326 |
Hanna | -0.324 |
F | -0.322 |
Token | away |
Token ID | 1497 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
castle | +0.310 |
ide | +0.309 |
ull | +0.300 |
structures | +0.285 |
room | +0.284 |
Neg logit contributions | |
Hanna | -0.290 |
Buster | -0.288 |
Kenny | -0.287 |
Michael | -0.285 |
Haley | -0.283 |
Token | to |
Token ID | 284 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Buster | +0.077 |
pup | +0.076 |
Kenny | +0.076 |
F | +0.076 |
Cindy | +0.075 |
Neg logit contributions | |
ide | -0.091 |
castle | -0.091 |
ull | -0.087 |
room | -0.087 |
structures | -0.085 |
Token | eat |
Token ID | 4483 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ide | +0.014 |
castle | +0.013 |
room | +0.013 |
ull | +0.013 |
structures | +0.012 |
Neg logit contributions | |
Buster | -0.010 |
F | -0.010 |
Cindy | -0.010 |
pup | -0.010 |
Kenny | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
castle | +0.269 |
ide | +0.267 |
ull | +0.255 |
room | +0.252 |
structures | +0.247 |
Neg logit contributions | |
Buster | -0.179 |
pup | -0.176 |
Hannah | -0.176 |
Cindy | -0.175 |
F | -0.175 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
ide | +0.015 |
room | +0.014 |
ull | +0.013 |
castle | +0.013 |
ics | +0.012 |
Neg logit contributions | |
pup | -0.027 |
hesitation | -0.025 |
Buster | -0.025 |
Hannah | -0.025 |
training | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
ull | +0.846 |
room | +0.828 |
ide | +0.816 |
structures | +0.809 |
castle | +0.801 |
Neg logit contributions | |
F | -0.471 |
pup | -0.468 |
Hannah | -0.458 |
Buster | -0.455 |
Cindy | -0.443 |
Token | And |
Token ID | 843 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Buster | +0.006 |
Kenny | +0.006 |
pup | +0.006 |
Hanna | +0.006 |
Cindy | +0.006 |
Neg logit contributions | |
castle | -0.008 |
ide | -0.008 |
ull | -0.007 |
structures | -0.007 |
room | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
castle | +0.147 |
ide | +0.147 |
ull | +0.139 |
room | +0.136 |
structures | +0.136 |
Neg logit contributions | |
Buster | -0.129 |
Kenny | -0.127 |
Hanna | -0.127 |
pup | -0.126 |
Hannah | -0.124 |
Token | all |
Token ID | 477 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
castle | +0.043 |
structures | +0.042 |
ide | +0.041 |
room | +0.040 |
ull | +0.039 |
Neg logit contributions | |
Buster | -0.042 |
F | -0.041 |
Kenny | -0.041 |
Cindy | -0.040 |
Hanna | -0.040 |
Token | lived |
Token ID | 5615 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
castle | +0.112 |
structures | +0.107 |
room | +0.105 |
ide | +0.105 |
ull | +0.096 |
Neg logit contributions | |
F | -0.127 |
Buster | -0.126 |
Kenny | -0.124 |
Kel | -0.124 |
Hanna | -0.123 |
Token | or |
Token ID | 393 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ull | +0.014 |
ide | +0.014 |
castle | +0.014 |
structures | +0.013 |
room | +0.013 |
Neg logit contributions | |
Hannah | -0.008 |
F | -0.008 |
Buster | -0.008 |
pup | -0.008 |
Cindy | -0.008 |
Token | putting |
Token ID | 5137 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
ide | +0.132 |
castle | +0.130 |
ull | +0.123 |
room | +0.122 |
structures | +0.116 |
Neg logit contributions | |
Buster | -0.144 |
pup | -0.142 |
Kenny | -0.141 |
Hanna | -0.141 |
Hannah | -0.141 |
Token | on |
Token ID | 319 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Buster | +0.052 |
Kenny | +0.052 |
Hanna | +0.052 |
pup | +0.051 |
Haley | +0.051 |
Neg logit contributions | |
castle | -0.054 |
ide | -0.054 |
structures | -0.052 |
ull | -0.052 |
room | -0.051 |
Token | fish |
Token ID | 5916 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Buster | +0.156 |
Kenny | +0.154 |
pup | +0.153 |
Hanna | +0.153 |
Hannah | +0.151 |
Neg logit contributions | |
castle | -0.143 |
ide | -0.143 |
ull | -0.134 |
room | -0.131 |
structures | -0.131 |
Token | or |
Token ID | 393 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
castle | +0.138 |
ull | +0.133 |
ide | +0.132 |
structures | +0.127 |
room | +0.124 |
Neg logit contributions | |
pup | -0.081 |
F | -0.078 |
Buster | -0.076 |
buck | -0.075 |
luggage | -0.074 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
ide | +0.125 |
castle | +0.124 |
ull | +0.117 |
room | +0.114 |
structures | +0.113 |
Neg logit contributions | |
Buster | -0.149 |
Kenny | -0.146 |
pup | -0.146 |
Hanna | -0.146 |
Hannah | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
ull | +0.813 |
castle | +0.786 |
ide | +0.783 |
structures | +0.761 |
room | +0.747 |
Neg logit contributions | |
pup | -0.518 |
F | -0.517 |
Hannah | -0.515 |
buck | -0.515 |
Buster | -0.514 |
Token | He |
Token ID | 679 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
castle | +0.005 |
ide | +0.005 |
ull | +0.005 |
ics | +0.005 |
structures | +0.005 |
Neg logit contributions | |
Kenny | -0.004 |
F | -0.004 |
Buster | -0.004 |
Hank | -0.004 |
Cindy | -0.004 |
Token | explains |
Token ID | 6688 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Buster | +0.006 |
Kenny | +0.006 |
pup | +0.006 |
Hanna | +0.006 |
Hannah | +0.006 |
Neg logit contributions | |
ide | -0.006 |
castle | -0.006 |
ull | -0.006 |
room | -0.006 |
structures | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
Buster | +0.030 |
Kenny | +0.029 |
Hanna | +0.029 |
pup | +0.029 |
Hannah | +0.029 |
Neg logit contributions | |
castle | -0.042 |
ide | -0.042 |
ull | -0.040 |
structures | -0.039 |
room | -0.039 |
Token | oranges |
Token ID | 48389 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Buster | +0.076 |
F | +0.075 |
Kenny | +0.075 |
pup | +0.074 |
Hannah | +0.074 |
Neg logit contributions | |
ide | -0.089 |
castle | -0.088 |
room | -0.082 |
ull | -0.081 |
structures | -0.080 |
Token | pieces |
Token ID | 5207 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ide | +0.011 |
room | +0.011 |
ull | +0.010 |
castle | +0.010 |
ics | +0.009 |
Neg logit contributions | |
pup | -0.014 |
luggage | -0.014 |
hesitation | -0.013 |
Hannah | -0.013 |
Buster | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
castle | +0.207 |
structures | +0.199 |
ull | +0.199 |
ide | +0.199 |
room | +0.196 |
Neg logit contributions | |
Buster | -0.125 |
Hannah | -0.123 |
Kenny | -0.120 |
pup | -0.119 |
Hanna | -0.119 |
Token | got |
Token ID | 1392 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Buster | +0.013 |
Kenny | +0.013 |
buck | +0.012 |
Hannah | +0.012 |
Cindy | +0.012 |
Neg logit contributions | |
ide | -0.019 |
castle | -0.018 |
room | -0.018 |
ull | -0.018 |
structures | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ide | +0.038 |
castle | +0.038 |
ull | +0.036 |
room | +0.036 |
structures | +0.035 |
Neg logit contributions | |
Buster | -0.026 |
Kenny | -0.026 |
Hanna | -0.026 |
pup | -0.026 |
Hannah | -0.026 |
Token | new |
Token ID | 649 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
pup | +0.015 |
Buster | +0.015 |
Hannah | +0.015 |
Hanna | +0.015 |
Cindy | +0.015 |
Neg logit contributions | |
ide | -0.021 |
castle | -0.021 |
room | -0.020 |
structures | -0.020 |
ull | -0.020 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.31e+00 |
Pos logit contributions | |
pup | +0.065 |
luggage | +0.063 |
hesitation | +0.062 |
ahead | +0.061 |
Hannah | +0.060 |
Neg logit contributions | |
ide | -0.044 |
room | -0.043 |
ics | -0.040 |
castle | -0.038 |
ull | -0.037 |
Token | for |
Token ID | 329 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
ide | +0.815 |
ull | +0.798 |
structures | +0.796 |
castle | +0.783 |
room | +0.775 |
Neg logit contributions | |
pup | -0.525 |
Buster | -0.517 |
Hannah | -0.512 |
Hanna | -0.499 |
buck | -0.497 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Hannah | +0.035 |
Cindy | +0.035 |
Buster | +0.035 |
Hanna | +0.034 |
Kenny | +0.034 |
Neg logit contributions | |
castle | -0.049 |
ide | -0.047 |
ull | -0.045 |
room | -0.044 |
structures | -0.044 |
Token | family |
Token ID | 1641 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ide | +0.017 |
castle | +0.017 |
ull | +0.016 |
room | +0.016 |
structures | +0.015 |
Neg logit contributions | |
pup | -0.014 |
Buster | -0.014 |
Hannah | -0.014 |
Hanna | -0.014 |
Kenny | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Buster | +0.022 |
Kenny | +0.022 |
pup | +0.022 |
Hanna | +0.022 |
Hannah | +0.021 |
Neg logit contributions | |
castle | -0.024 |
ide | -0.024 |
ull | -0.022 |
room | -0.022 |
structures | -0.022 |
Token | The |
Token ID | 383 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Kenny | +0.014 |
Buster | +0.014 |
Hannah | +0.013 |
Cindy | +0.013 |
F | +0.013 |
Neg logit contributions | |
castle | -0.019 |
ide | -0.018 |
ull | -0.017 |
structures | -0.017 |
room | -0.017 |
Token | fridge |
Token ID | 25772 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
castle | +0.046 |
ide | +0.043 |
structures | +0.042 |
salad | +0.042 |
ull | +0.041 |
Neg logit contributions | |
Kenny | -0.051 |
Buster | -0.051 |
Kel | -0.050 |
uster | -0.050 |
Hanna | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ull | +0.325 |
ide | +0.324 |
castle | +0.323 |
structures | +0.322 |
room | +0.300 |
Neg logit contributions | |
pup | -0.228 |
Buster | -0.227 |
F | -0.225 |
Hanna | -0.224 |
Hannah | -0.223 |
Token | picked |
Token ID | 6497 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
Buster | +0.011 |
Kenny | +0.011 |
Hanna | +0.011 |
pup | +0.011 |
Hannah | +0.011 |
Neg logit contributions | |
ide | -0.013 |
castle | -0.013 |
ull | -0.012 |
room | -0.012 |
structures | -0.012 |
Token | out |
Token ID | 503 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Buster | +0.070 |
uster | +0.069 |
Kenny | +0.069 |
hesitation | +0.069 |
Hanna | +0.068 |
Neg logit contributions | |
ide | -0.075 |
castle | -0.074 |
ull | -0.072 |
salad | -0.072 |
structures | -0.071 |
Token | some |
Token ID | 617 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
ide | +0.157 |
castle | +0.152 |
structures | +0.147 |
ull | +0.147 |
salad | +0.145 |
Neg logit contributions | |
Buster | -0.171 |
uster | -0.171 |
Kenny | -0.168 |
Hanna | -0.167 |
pup | -0.167 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
Buster | +0.074 |
Kenny | +0.074 |
Michael | +0.073 |
Matthew | +0.073 |
Haley | +0.073 |
Neg logit contributions | |
salad | -0.055 |
ide | -0.051 |
castle | -0.051 |
structures | -0.050 |
ull | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ide | +0.735 |
castle | +0.729 |
ull | +0.707 |
room | +0.694 |
structures | +0.693 |
Neg logit contributions | |
Buster | -0.613 |
pup | -0.607 |
Hanna | -0.601 |
Kenny | -0.601 |
Hannah | -0.599 |
Token | He |
Token ID | 679 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Buster | +0.014 |
Kenny | +0.014 |
Hanna | +0.014 |
pup | +0.014 |
Hannah | +0.013 |
Neg logit contributions | |
castle | -0.015 |
ide | -0.015 |
ull | -0.014 |
room | -0.014 |
structures | -0.014 |
Token | took |
Token ID | 1718 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
buck | +0.008 |
F | +0.007 |
Hannah | +0.007 |
Kenny | +0.007 |
pup | +0.007 |
Neg logit contributions | |
ide | -0.011 |
castle | -0.011 |
room | -0.011 |
structures | -0.011 |
ull | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
ide | +0.133 |
castle | +0.133 |
ull | +0.125 |
room | +0.124 |
structures | +0.123 |
Neg logit contributions | |
Buster | -0.093 |
Kenny | -0.091 |
pup | -0.091 |
Hanna | -0.091 |
Hannah | -0.089 |
Token | to |
Token ID | 284 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
pup | +0.040 |
Buster | +0.040 |
Kenny | +0.038 |
F | +0.037 |
training | +0.037 |
Neg logit contributions | |
ide | -0.071 |
castle | -0.071 |
ull | -0.069 |
structures | -0.068 |
room | -0.068 |
Token | him |
Token ID | 683 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ide | +0.021 |
ull | +0.021 |
salad | +0.020 |
castle | +0.020 |
room | +0.019 |
Neg logit contributions | |
uster | -0.026 |
Matthew | -0.025 |
Michael | -0.025 |
Char | -0.025 |
buck | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
castle | +0.037 |
ide | +0.037 |
ull | +0.036 |
structures | +0.035 |
salad | +0.034 |
Neg logit contributions | |
Buster | -0.032 |
Kenny | -0.032 |
Hanna | -0.031 |
Kel | -0.031 |
pup | -0.031 |
Token | big |
Token ID | 1263 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
Kel | +0.006 |
Kenny | +0.006 |
Hanna | +0.006 |
Buster | +0.006 |
Haley | +0.006 |
Neg logit contributions | |
salad | -0.005 |
castle | -0.005 |
ull | -0.005 |
ide | -0.005 |
pie | -0.005 |
Token | bowl |
Token ID | 9396 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
castle | +0.076 |
salad | +0.074 |
ull | +0.073 |
ide | +0.071 |
room | +0.069 |
Neg logit contributions | |
Kel | -0.071 |
Hanna | -0.071 |
Kenny | -0.071 |
Buster | -0.070 |
Haley | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ide | +0.313 |
castle | +0.311 |
structures | +0.302 |
ull | +0.296 |
room | +0.291 |
Neg logit contributions | |
Buster | -0.240 |
pup | -0.237 |
Kenny | -0.234 |
F | -0.232 |
Hanna | -0.231 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
Buster | +0.046 |
Kenny | +0.046 |
uster | +0.046 |
Hanna | +0.046 |
pup | +0.046 |
Neg logit contributions | |
salad | -0.036 |
castle | -0.036 |
ide | -0.035 |
ull | -0.034 |
structures | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ide | +0.778 |
ull | +0.755 |
castle | +0.753 |
structures | +0.751 |
room | +0.743 |
Neg logit contributions | |
pup | -0.549 |
Buster | -0.546 |
F | -0.541 |
Hannah | -0.537 |
Hanna | -0.531 |
Token | Max |
Token ID | 5436 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Buster | +0.018 |
pup | +0.018 |
Hanna | +0.018 |
Kenny | +0.018 |
Kel | +0.017 |
Neg logit contributions | |
ide | -0.017 |
castle | -0.017 |
ull | -0.016 |
room | -0.016 |
structures | -0.016 |
Token | ate |
Token ID | 15063 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Buster | +0.037 |
pup | +0.036 |
F | +0.036 |
Kenny | +0.036 |
Hannah | +0.036 |
Neg logit contributions | |
castle | -0.051 |
ide | -0.049 |
ull | -0.049 |
room | -0.048 |
structures | -0.047 |
Token | it |
Token ID | 340 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
castle | +0.308 |
ide | +0.303 |
ull | +0.292 |
room | +0.289 |
structures | +0.280 |
Neg logit contributions | |
Buster | -0.196 |
Hannah | -0.192 |
F | -0.190 |
Cindy | -0.190 |
Kenny | -0.189 |
Token | all |
Token ID | 477 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Buster | +0.040 |
F | +0.040 |
Kenny | +0.039 |
pup | +0.039 |
Hannah | +0.038 |
Neg logit contributions | |
ull | -0.069 |
castle | -0.069 |
structures | -0.066 |
ide | -0.065 |
room | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ide | +0.034 |
castle | +0.034 |
structures | +0.032 |
room | +0.032 |
ull | +0.032 |
Neg logit contributions | |
Buster | -0.046 |
Kenny | -0.045 |
Hanna | -0.045 |
Kel | -0.044 |
Cindy | -0.044 |
Token | It |
Token ID | 632 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
ide | +0.002 |
castle | +0.002 |
ull | +0.001 |
room | +0.001 |
structures | +0.001 |
Neg logit contributions | |
Buster | -0.001 |
Kenny | -0.001 |
pup | -0.001 |
Hanna | -0.001 |
Cindy | -0.001 |
Token | will |
Token ID | 481 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
F | +0.041 |
Buster | +0.040 |
Hanna | +0.040 |
buck | +0.040 |
Hannah | +0.040 |
Neg logit contributions | |
ide | -0.070 |
castle | -0.070 |
room | -0.066 |
ull | -0.065 |
structures | -0.063 |
Token | make |
Token ID | 787 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Buster | +0.123 |
Hanna | +0.121 |
Kenny | +0.120 |
pup | +0.120 |
Cindy | +0.120 |
Neg logit contributions | |
ide | -0.106 |
castle | -0.106 |
ull | -0.099 |
room | -0.097 |
structures | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
castle | +0.173 |
ide | +0.168 |
ull | +0.156 |
room | +0.154 |
structures | +0.150 |
Neg logit contributions | |
F | -0.106 |
Hanna | -0.105 |
Hannah | -0.105 |
Buster | -0.105 |
Cindy | -0.103 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
pup | +0.005 |
Buster | +0.005 |
Hanna | +0.005 |
Hannah | +0.005 |
Cindy | +0.005 |
Neg logit contributions | |
ide | -0.005 |
castle | -0.004 |
ull | -0.004 |
room | -0.004 |
structures | -0.004 |
Token | taste |
Token ID | 6938 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ull | +0.840 |
ide | +0.823 |
room | +0.814 |
structures | +0.780 |
castle | +0.774 |
Neg logit contributions | |
buck | -0.467 |
Hanna | -0.438 |
ahead | -0.433 |
luggage | -0.426 |
F | -0.423 |
Token | bad |
Token ID | 2089 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
castle | +0.199 |
ide | +0.194 |
room | +0.190 |
structures | +0.187 |
ull | +0.186 |
Neg logit contributions | |
Hanna | -0.095 |
F | -0.094 |
Hannah | -0.094 |
Buster | -0.092 |
Cindy | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
pup | +0.002 |
F | +0.002 |
Hannah | +0.002 |
Buster | +0.002 |
Hanna | +0.002 |
Neg logit contributions | |
castle | -0.002 |
ide | -0.002 |
ull | -0.002 |
room | -0.002 |
structures | -0.002 |
Token | We |
Token ID | 775 |
Feature activation | +9.39e-03 |
Pos logit contributions | |
ide | +0.003 |
castle | +0.003 |
ull | +0.003 |
room | +0.003 |
structures | +0.003 |
Neg logit contributions | |
Buster | -0.003 |
Kenny | -0.003 |
pup | -0.003 |
Hanna | -0.003 |
Cindy | -0.002 |
Token | need |
Token ID | 761 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Buster | +0.001 |
Kenny | +0.001 |
Hanna | +0.001 |
pup | +0.001 |
Cindy | +0.001 |
Neg logit contributions | |
ide | -0.001 |
castle | -0.001 |
ull | -0.001 |
room | -0.001 |
structures | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Cindy | +0.015 |
Hannah | +0.015 |
Buster | +0.015 |
Kenny | +0.014 |
F | +0.014 |
Neg logit contributions | |
castle | -0.018 |
ide | -0.018 |
ull | -0.017 |
structures | -0.017 |
room | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ide | +0.067 |
castle | +0.064 |
room | +0.063 |
ull | +0.062 |
ics | +0.059 |
Neg logit contributions | |
pup | -0.046 |
Hannah | -0.044 |
Buster | -0.043 |
hesitation | -0.042 |
Cindy | -0.042 |
Token | understood |
Token ID | 7247 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Kenny | +0.014 |
Buster | +0.013 |
Hannah | +0.013 |
pup | +0.013 |
buck | +0.013 |
Neg logit contributions | |
castle | -0.023 |
ide | -0.022 |
structures | -0.022 |
room | -0.021 |
ull | -0.021 |
Token | why |
Token ID | 1521 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ide | +0.095 |
castle | +0.086 |
ull | +0.084 |
room | +0.082 |
salad | +0.082 |
Neg logit contributions | |
uster | -0.139 |
reins | -0.136 |
Buster | -0.134 |
training | -0.132 |
Hanna | -0.132 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Buster | +0.001 |
pup | +0.001 |
Kenny | +0.001 |
Hanna | +0.001 |
uster | +0.001 |
Neg logit contributions | |
ide | -0.002 |
castle | -0.002 |
ull | -0.002 |
structures | -0.001 |
room | -0.001 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
ide | +0.012 |
room | +0.012 |
castle | +0.011 |
ull | +0.011 |
ics | +0.011 |
Neg logit contributions | |
pup | -0.010 |
Hannah | -0.009 |
luggage | -0.009 |
Cindy | -0.009 |
hesitation | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ide | +0.810 |
castle | +0.791 |
ull | +0.779 |
structures | +0.767 |
room | +0.766 |
Neg logit contributions | |
Kenny | -0.524 |
Buster | -0.524 |
pup | -0.521 |
Hannah | -0.515 |
buck | -0.504 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Buster | +0.031 |
Cindy | +0.031 |
pup | +0.030 |
Hannah | +0.030 |
Kenny | +0.030 |
Neg logit contributions | |
ide | -0.043 |
castle | -0.043 |
room | -0.041 |
structures | -0.040 |
ull | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Buster | +0.075 |
pup | +0.074 |
Kenny | +0.074 |
Hannah | +0.073 |
Cindy | +0.072 |
Neg logit contributions | |
castle | -0.093 |
ide | -0.092 |
ull | -0.088 |
structures | -0.086 |
room | -0.086 |
Token | said |
Token ID | 531 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Buster | +0.015 |
Kenny | +0.015 |
pup | +0.015 |
Hanna | +0.015 |
Hannah | +0.015 |
Neg logit contributions | |
ide | -0.020 |
castle | -0.020 |
ull | -0.019 |
room | -0.019 |
structures | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Buster | +0.046 |
Kenny | +0.046 |
Hanna | +0.045 |
pup | +0.045 |
Hannah | +0.045 |
Neg logit contributions | |
ide | -0.062 |
castle | -0.062 |
ull | -0.058 |
room | -0.058 |
structures | -0.057 |
Token | Now |
Token ID | 2735 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ide | +0.005 |
room | +0.005 |
ull | +0.005 |
castle | +0.005 |
structures | +0.005 |
Neg logit contributions | |
hesitation | -0.005 |
Kenny | -0.005 |
Buster | -0.005 |
buck | -0.005 |
training | -0.005 |
Token | we |
Token ID | 356 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
Buster | +0.193 |
Kenny | +0.190 |
pup | +0.188 |
Hanna | +0.187 |
Cindy | +0.185 |
Neg logit contributions | |
castle | -0.188 |
ide | -0.188 |
ull | -0.175 |
room | -0.173 |
structures | -0.172 |
Token | can |
Token ID | 460 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
castle | +0.077 |
ide | +0.077 |
ull | +0.074 |
room | +0.073 |
structures | +0.072 |
Neg logit contributions | |
Buster | -0.061 |
Kenny | -0.061 |
Hanna | -0.059 |
pup | -0.059 |
Cindy | -0.058 |
Token | finish |
Token ID | 5461 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Buster | +0.123 |
Hanna | +0.122 |
Kenny | +0.121 |
Hannah | +0.121 |
Cindy | +0.120 |
Neg logit contributions | |
ide | -0.145 |
castle | -0.145 |
ull | -0.142 |
structures | -0.140 |
room | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
Buster | +0.016 |
Kenny | +0.016 |
pup | +0.016 |
Hanna | +0.016 |
Kel | +0.015 |
Neg logit contributions | |
castle | -0.015 |
ide | -0.015 |
structures | -0.014 |
ull | -0.014 |
room | -0.014 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
Buster | +0.009 |
Kenny | +0.009 |
uster | +0.009 |
Hanna | +0.009 |
Matthew | +0.009 |
Neg logit contributions | |
castle | -0.007 |
ide | -0.006 |
salad | -0.006 |
structures | -0.006 |
room | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
ull | +0.897 |
structures | +0.817 |
castle | +0.807 |
ide | +0.805 |
room | +0.793 |
Neg logit contributions | |
buck | -0.436 |
ahead | -0.426 |
F | -0.424 |
Hannah | -0.414 |
Hanna | -0.413 |
Token | We |
Token ID | 775 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
castle | +0.003 |
ide | +0.003 |
room | +0.003 |
ull | +0.003 |
structures | +0.003 |
Neg logit contributions | |
Buster | -0.003 |
Kenny | -0.003 |
pup | -0.003 |
Hanna | -0.003 |
Kel | -0.003 |
Token | will |
Token ID | 481 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Buster | +0.005 |
Kenny | +0.005 |
Hanna | +0.005 |
pup | +0.005 |
Matthew | +0.005 |
Neg logit contributions | |
ide | -0.006 |
castle | -0.005 |
ull | -0.005 |
room | -0.005 |
structures | -0.005 |
Token | add |
Token ID | 751 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Buster | +0.118 |
Hanna | +0.117 |
Hannah | +0.116 |
Cindy | +0.116 |
F | +0.115 |
Neg logit contributions | |
ide | -0.126 |
castle | -0.125 |
ull | -0.120 |
structures | -0.118 |
room | -0.114 |
Token | some |
Token ID | 617 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ide | +0.269 |
castle | +0.269 |
ull | +0.255 |
room | +0.251 |
structures | +0.250 |
Neg logit contributions | |
Buster | -0.191 |
Kenny | -0.188 |
pup | -0.186 |
Hanna | -0.186 |
Cindy | -0.184 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ide | +0.013 |
room | +0.012 |
castle | +0.012 |
ull | +0.011 |
structures | +0.011 |
Neg logit contributions | |
pup | -0.012 |
hesitation | -0.011 |
Buster | -0.011 |
luggage | -0.010 |
reins | -0.010 |
Token | picked |
Token ID | 6497 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ide | +0.231 |
castle | +0.230 |
structures | +0.221 |
room | +0.221 |
ull | +0.215 |
Neg logit contributions | |
Buster | -0.196 |
pup | -0.196 |
Kenny | -0.193 |
Hanna | -0.189 |
buck | -0.189 |
Token | up |
Token ID | 510 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Buster | +0.074 |
pup | +0.073 |
Kenny | +0.072 |
Cindy | +0.072 |
F | +0.071 |
Neg logit contributions | |
ide | -0.100 |
castle | -0.100 |
room | -0.092 |
ull | -0.092 |
structures | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ide | +0.022 |
castle | +0.022 |
ull | +0.021 |
room | +0.021 |
structures | +0.020 |
Neg logit contributions | |
Buster | -0.017 |
Kenny | -0.017 |
pup | -0.017 |
Hanna | -0.016 |
Cindy | -0.016 |
Token | tied |
Token ID | 8165 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ide | +0.013 |
castle | +0.012 |
ull | +0.012 |
room | +0.012 |
structures | +0.011 |
Neg logit contributions | |
pup | -0.018 |
Buster | -0.018 |
hesitation | -0.017 |
Hannah | -0.017 |
training | -0.017 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
Buster | +0.118 |
Hanna | +0.117 |
Kenny | +0.117 |
pup | +0.115 |
Hannah | +0.114 |
Neg logit contributions | |
ide | -0.128 |
castle | -0.128 |
ull | -0.121 |
room | -0.119 |
structures | -0.118 |
Token | in |
Token ID | 287 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
ull | +0.820 |
ide | +0.809 |
castle | +0.802 |
room | +0.793 |
structures | +0.792 |
Neg logit contributions | |
pup | -0.503 |
F | -0.494 |
Buster | -0.492 |
Hannah | -0.487 |
Cindy | -0.478 |
Token | its |
Token ID | 663 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
castle | +0.051 |
ide | +0.051 |
ull | +0.047 |
structures | +0.047 |
room | +0.046 |
Neg logit contributions | |
Buster | -0.053 |
Kenny | -0.052 |
pup | -0.052 |
Cindy | -0.051 |
Hannah | -0.051 |
Token | be |
Token ID | 307 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
ide | +0.409 |
castle | +0.379 |
room | +0.372 |
ull | +0.367 |
structures | +0.352 |
Neg logit contributions | |
pup | -0.360 |
Buster | -0.350 |
F | -0.345 |
Cindy | -0.338 |
luggage | -0.337 |
Token | ak |
Token ID | 461 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Buster | +0.006 |
pup | +0.006 |
Hanna | +0.006 |
Kenny | +0.006 |
Hannah | +0.006 |
Neg logit contributions | |
ide | -0.004 |
castle | -0.004 |
structures | -0.004 |
ull | -0.004 |
room | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
castle | +0.138 |
ide | +0.138 |
ull | +0.130 |
room | +0.128 |
structures | +0.127 |
Neg logit contributions | |
Buster | -0.126 |
Kenny | -0.124 |
Hanna | -0.123 |
pup | -0.123 |
Hannah | -0.122 |
Token | a |
Token ID | 257 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Buster | +0.105 |
uster | +0.104 |
Kenny | +0.103 |
Hanna | +0.103 |
pup | +0.102 |
Neg logit contributions | |
ide | -0.097 |
castle | -0.096 |
ull | -0.090 |
room | -0.090 |
salad | -0.090 |
Token | little |
Token ID | 1310 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Kenny | +0.020 |
Buster | +0.020 |
Kel | +0.020 |
Hanna | +0.020 |
Michael | +0.020 |
Neg logit contributions | |
castle | -0.019 |
ide | -0.019 |
salad | -0.019 |
ull | -0.018 |
structures | -0.017 |
Token | bit |
Token ID | 1643 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Buster | +0.016 |
Kenny | +0.016 |
Hanna | +0.016 |
Matthew | +0.016 |
Kel | +0.016 |
Neg logit contributions | |
castle | -0.015 |
salad | -0.015 |
ide | -0.015 |
ull | -0.014 |
structures | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
ide | +0.055 |
castle | +0.049 |
salad | +0.049 |
room | +0.048 |
structures | +0.048 |
Neg logit contributions | |
Buster | -0.077 |
Kenny | -0.075 |
Matthew | -0.075 |
pup | -0.073 |
Kel | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
uster | +0.062 |
Matthew | +0.058 |
Hanna | +0.058 |
Michael | +0.057 |
Thomas | +0.057 |
Neg logit contributions | |
salad | -0.050 |
structures | -0.046 |
pie | -0.045 |
avocado | -0.043 |
castle | -0.041 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
Hanna | +0.000 |
Kenny | +0.000 |
uster | +0.000 |
Matthew | +0.000 |
Buster | +0.000 |
Neg logit contributions | |
salad | -0.000 |
castle | -0.000 |
structures | -0.000 |
pie | -0.000 |
structure | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ull | +0.809 |
castle | +0.796 |
ide | +0.789 |
structures | +0.780 |
room | +0.759 |
Neg logit contributions | |
Hannah | -0.535 |
pup | -0.532 |
Buster | -0.525 |
F | -0.523 |
Hanna | -0.520 |
Token | but |
Token ID | 475 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Buster | +0.029 |
Kenny | +0.029 |
Matthew | +0.028 |
pup | +0.028 |
uster | +0.028 |
Neg logit contributions | |
castle | -0.025 |
ide | -0.024 |
salad | -0.024 |
structures | -0.023 |
room | -0.023 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
uster | +0.070 |
reins | +0.069 |
Matthew | +0.067 |
Buster | +0.066 |
pup | +0.065 |
Neg logit contributions | |
castle | -0.040 |
ide | -0.040 |
salad | -0.037 |
room | -0.035 |
structures | -0.035 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Buster | +0.003 |
Kenny | +0.003 |
Hanna | +0.003 |
pup | +0.003 |
Cindy | +0.003 |
Neg logit contributions | |
ide | -0.003 |
castle | -0.003 |
ull | -0.003 |
room | -0.003 |
structures | -0.003 |
Token | 't |
Token ID | 470 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ide | +0.098 |
castle | +0.094 |
room | +0.092 |
ull | +0.091 |
ics | +0.087 |
Neg logit contributions | |
pup | -0.093 |
Buster | -0.093 |
Hanna | -0.092 |
Kenny | -0.091 |
hesitation | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
ide | +0.037 |
room | +0.034 |
ull | +0.034 |
castle | +0.032 |
structures | +0.031 |
Neg logit contributions | |
pup | -0.050 |
Buster | -0.049 |
hesitation | -0.049 |
uster | -0.049 |
training | -0.048 |
Token | Their |
Token ID | 14574 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
ide | +0.026 |
room | +0.025 |
castle | +0.022 |
structures | +0.021 |
ull | +0.021 |
Neg logit contributions | |
hesitation | -0.061 |
Buster | -0.059 |
pup | -0.059 |
uster | -0.058 |
Cindy | -0.057 |
Token | mother |
Token ID | 2802 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
ide | +0.026 |
castle | +0.026 |
ull | +0.025 |
salad | +0.025 |
structures | +0.024 |
Neg logit contributions | |
uster | -0.039 |
Buster | -0.039 |
Kenny | -0.039 |
Kel | -0.038 |
Cindy | -0.038 |
Token | put |
Token ID | 1234 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Buster | +0.072 |
Kenny | +0.070 |
Hanna | +0.070 |
pup | +0.070 |
Cindy | +0.069 |
Neg logit contributions | |
ide | -0.084 |
castle | -0.083 |
ull | -0.080 |
room | -0.078 |
structures | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Matthew | +0.115 |
Buster | +0.114 |
Kenny | +0.112 |
uster | +0.110 |
pup | +0.110 |
Neg logit contributions | |
room | -0.072 |
ull | -0.069 |
salad | -0.065 |
ide | -0.063 |
castle | -0.063 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
castle | +0.009 |
ide | +0.009 |
salad | +0.009 |
ull | +0.008 |
structures | +0.008 |
Neg logit contributions | |
Kenny | -0.016 |
Buster | -0.016 |
Hanna | -0.016 |
Kel | -0.016 |
Cindy | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ide | +0.861 |
castle | +0.844 |
ull | +0.834 |
structures | +0.834 |
room | +0.824 |
Neg logit contributions | |
pup | -0.467 |
buck | -0.459 |
Buster | -0.455 |
Hannah | -0.451 |
Hanna | -0.448 |
Token | a |
Token ID | 257 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
room | +0.038 |
ide | +0.035 |
ull | +0.035 |
ill | +0.033 |
salad | +0.032 |
Neg logit contributions | |
Buster | -0.057 |
uster | -0.056 |
Matthew | -0.056 |
Kenny | -0.055 |
pup | -0.054 |
Token | pot |
Token ID | 1787 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Buster | +0.019 |
Kenny | +0.018 |
pup | +0.018 |
Hanna | +0.018 |
Cindy | +0.018 |
Neg logit contributions | |
castle | -0.014 |
ide | -0.014 |
ull | -0.013 |
structures | -0.013 |
room | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
castle | +0.276 |
ide | +0.273 |
structures | +0.266 |
ull | +0.261 |
room | +0.251 |
Neg logit contributions | |
Buster | -0.193 |
Hanna | -0.192 |
pup | -0.191 |
Hannah | -0.189 |
buck | -0.188 |
Token | placed |
Token ID | 4624 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Buster | +0.011 |
Kenny | +0.010 |
pup | +0.010 |
Hanna | +0.010 |
Cindy | +0.010 |
Neg logit contributions | |
castle | -0.011 |
ide | -0.011 |
ull | -0.010 |
room | -0.010 |
structures | -0.010 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ide | +0.011 |
castle | +0.011 |
ull | +0.010 |
room | +0.010 |
structures | +0.010 |
Neg logit contributions | |
pup | -0.010 |
Buster | -0.010 |
Hannah | -0.010 |
Hanna | -0.010 |
Cindy | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
castle | +0.001 |
ide | +0.001 |
ull | +0.001 |
structures | +0.001 |
room | +0.001 |
Neg logit contributions | |
Hannah | -0.001 |
pup | -0.001 |
Hanna | -0.001 |
Buster | -0.001 |
Kenny | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
Buster | +0.021 |
Kenny | +0.021 |
Hanna | +0.021 |
Hannah | +0.021 |
Cindy | +0.021 |
Neg logit contributions | |
ide | -0.027 |
castle | -0.027 |
ull | -0.026 |
structures | -0.026 |
room | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
castle | +0.093 |
ide | +0.093 |
ull | +0.088 |
room | +0.086 |
structures | +0.086 |
Neg logit contributions | |
Buster | -0.065 |
Kenny | -0.064 |
Hanna | -0.063 |
pup | -0.063 |
Hannah | -0.063 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ide | +0.009 |
room | +0.008 |
castle | +0.008 |
ull | +0.008 |
ics | +0.008 |
Neg logit contributions | |
pup | -0.011 |
hesitation | -0.011 |
Hannah | -0.011 |
Buster | -0.011 |
luggage | -0.011 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
pup | +0.108 |
luggage | +0.104 |
Hannah | +0.101 |
ahead | +0.101 |
hesitation | +0.101 |
Neg logit contributions | |
ide | -0.058 |
room | -0.055 |
ics | -0.049 |
ectar | -0.046 |
castle | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ide | +0.766 |
castle | +0.749 |
ull | +0.744 |
room | +0.725 |
structures | +0.718 |
Neg logit contributions | |
pup | -0.569 |
Buster | -0.568 |
Hannah | -0.560 |
Kenny | -0.559 |
Hanna | -0.552 |
Token | She |
Token ID | 1375 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Hannah | +0.016 |
Cindy | +0.016 |
Buster | +0.016 |
Kenny | +0.016 |
Hanna | +0.016 |
Neg logit contributions | |
castle | -0.019 |
ide | -0.019 |
ull | -0.018 |
room | -0.017 |
structures | -0.017 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ide | +0.039 |
castle | +0.039 |
structures | +0.037 |
room | +0.037 |
ull | +0.035 |
Neg logit contributions | |
Kenny | -0.024 |
Buster | -0.024 |
Hannah | -0.024 |
pup | -0.024 |
Cindy | -0.023 |
Token | over |
Token ID | 625 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Hanna | +0.030 |
Buster | +0.030 |
hesitation | +0.030 |
Matthew | +0.029 |
Kel | +0.029 |
Neg logit contributions | |
ide | -0.024 |
castle | -0.023 |
structures | -0.022 |
room | -0.022 |
salad | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
Buster | +0.036 |
Hanna | +0.036 |
Kenny | +0.035 |
pup | +0.035 |
uster | +0.035 |
Neg logit contributions | |
ide | -0.032 |
castle | -0.031 |
room | -0.030 |
ull | -0.030 |
structures | -0.029 |
Token | had |
Token ID | 550 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ide | +0.030 |
castle | +0.030 |
ull | +0.029 |
structures | +0.028 |
room | +0.028 |
Neg logit contributions | |
Buster | -0.027 |
Kenny | -0.027 |
Hanna | -0.026 |
pup | -0.026 |
Cindy | -0.026 |
Token | never |
Token ID | 1239 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Buster | +0.205 |
Kenny | +0.201 |
pup | +0.200 |
Hanna | +0.200 |
Hannah | +0.198 |
Neg logit contributions | |
ide | -0.251 |
castle | -0.250 |
ull | -0.236 |
room | -0.232 |
structures | -0.231 |
Token | seen |
Token ID | 1775 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
ide | +0.051 |
castle | +0.050 |
room | +0.048 |
structures | +0.047 |
ull | +0.047 |
Neg logit contributions | |
buck | -0.033 |
training | -0.032 |
hesitation | -0.032 |
pup | -0.032 |
Buster | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Buster | +0.027 |
Hannah | +0.026 |
Cindy | +0.026 |
pup | +0.026 |
Kenny | +0.026 |
Neg logit contributions | |
castle | -0.039 |
ide | -0.038 |
room | -0.036 |
ull | -0.036 |
structures | -0.035 |
Token | broken |
Token ID | 5445 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
pup | +0.022 |
hesitation | +0.021 |
Buster | +0.020 |
Hannah | +0.020 |
Cindy | +0.020 |
Neg logit contributions | |
room | -0.022 |
ide | -0.022 |
ics | -0.022 |
castle | -0.019 |
ull | -0.019 |
Token | salad |
Token ID | 20698 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
pup | +0.092 |
hesitation | +0.086 |
ahead | +0.086 |
luggage | +0.085 |
Hannah | +0.083 |
Neg logit contributions | |
ide | -0.065 |
ics | -0.065 |
room | -0.063 |
structures | -0.056 |
od | -0.056 |
Token | before |
Token ID | 878 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ide | +0.875 |
castle | +0.868 |
ull | +0.857 |
structures | +0.842 |
room | +0.828 |
Neg logit contributions | |
Buster | -0.467 |
pup | -0.466 |
Hannah | -0.459 |
Hanna | -0.455 |
Kenny | -0.453 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Buster | +0.108 |
Kenny | +0.107 |
pup | +0.106 |
Hanna | +0.106 |
Hannah | +0.105 |
Neg logit contributions | |
castle | -0.123 |
ide | -0.123 |
ull | -0.116 |
structures | -0.114 |
room | -0.114 |
Token | She |
Token ID | 1375 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Buster | +0.018 |
Kenny | +0.017 |
Hanna | +0.017 |
pup | +0.017 |
Hannah | +0.017 |
Neg logit contributions | |
castle | -0.022 |
ide | -0.021 |
ull | -0.020 |
structures | -0.020 |
room | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
ide | +0.031 |
castle | +0.031 |
ull | +0.029 |
room | +0.029 |
structures | +0.029 |
Neg logit contributions | |
Buster | -0.025 |
Kenny | -0.024 |
pup | -0.024 |
Hanna | -0.024 |
Hannah | -0.024 |
Token | not |
Token ID | 407 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Buster | +0.042 |
Kenny | +0.042 |
Hanna | +0.042 |
pup | +0.042 |
Hannah | +0.041 |
Neg logit contributions | |
castle | -0.042 |
ide | -0.042 |
ull | -0.040 |
room | -0.039 |
structures | -0.039 |
Token | He |
Token ID | 679 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Hanna | +0.060 |
Kel | +0.060 |
uster | +0.059 |
Haley | +0.057 |
Kenny | +0.056 |
Neg logit contributions | |
structures | -0.045 |
salad | -0.042 |
room | -0.040 |
castle | -0.039 |
ide | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
Buster | +0.018 |
Kenny | +0.017 |
Hanna | +0.017 |
pup | +0.017 |
Cindy | +0.017 |
Neg logit contributions | |
castle | -0.018 |
ide | -0.018 |
ull | -0.017 |
structures | -0.017 |
room | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Buster | +0.054 |
Kenny | +0.054 |
Hanna | +0.053 |
pup | +0.053 |
uster | +0.053 |
Neg logit contributions | |
castle | -0.055 |
ide | -0.054 |
ull | -0.053 |
structures | -0.050 |
room | -0.050 |
Token | very |
Token ID | 845 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Kenny | +0.046 |
Kel | +0.046 |
Buster | +0.045 |
Hanna | +0.045 |
uster | +0.045 |
Neg logit contributions | |
castle | -0.044 |
salad | -0.041 |
ide | -0.041 |
ull | -0.040 |
nation | -0.039 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
castle | +0.045 |
ide | +0.044 |
ull | +0.042 |
structures | +0.041 |
salad | +0.041 |
Neg logit contributions | |
Buster | -0.044 |
Kenny | -0.044 |
Hanna | -0.043 |
pup | -0.043 |
Kel | -0.043 |
Token | puppy |
Token ID | 26188 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
castle | +0.194 |
ide | +0.188 |
ull | +0.181 |
salad | +0.175 |
structures | +0.172 |
Neg logit contributions | |
Kenny | -0.199 |
Buster | -0.199 |
Kel | -0.197 |
Hanna | -0.196 |
uster | -0.194 |
Token | ! |
Token ID | 0 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
uster | +0.502 |
Hanna | +0.502 |
Kel | +0.498 |
Buster | +0.497 |
Kenny | +0.495 |
Neg logit contributions | |
ide | -0.460 |
castle | -0.450 |
ull | -0.420 |
room | -0.418 |
salad | -0.398 |
Token | His |
Token ID | 2399 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
hesitation | +0.072 |
uster | +0.071 |
buck | +0.070 |
training | +0.070 |
luggage | +0.070 |
Neg logit contributions | |
ide | -0.064 |
castle | -0.060 |
room | -0.060 |
ull | -0.059 |
structures | -0.056 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
uster | +0.010 |
ha | +0.010 |
Michael | +0.010 |
Kel | +0.010 |
Hanna | +0.010 |
Neg logit contributions | |
castle | -0.008 |
salad | -0.007 |
room | -0.007 |
ide | -0.007 |
nation | -0.007 |
Token | scrub |
Token ID | 27268 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Buster | +0.013 |
uster | +0.013 |
pup | +0.013 |
Kenny | +0.013 |
Hanna | +0.013 |
Neg logit contributions | |
ide | -0.013 |
castle | -0.013 |
ull | -0.012 |
room | -0.012 |
structures | -0.012 |
Token | bed |
Token ID | 3077 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
hesitation | +0.297 |
reins | +0.284 |
uster | +0.284 |
pup | +0.284 |
luggage | +0.281 |
Neg logit contributions | |
ide | -0.218 |
room | -0.213 |
castle | -0.193 |
ics | -0.192 |
structures | -0.187 |
Token | ." |
Token ID | 526 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ide | +0.011 |
castle | +0.010 |
room | +0.009 |
ull | +0.009 |
salad | +0.009 |
Neg logit contributions | |
hesitation | -0.014 |
buck | -0.013 |
reins | -0.013 |
Hanna | -0.013 |
Kel | -0.013 |
Token | |
Token ID | 220 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
room | +0.089 |
castle | +0.087 |
ull | +0.083 |
ide | +0.083 |
salad | +0.080 |
Neg logit contributions | |
Kel | -0.128 |
reins | -0.125 |
luggage | -0.125 |
hesitation | -0.122 |
buck | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
pup | +0.104 |
Buster | +0.103 |
Hanna | +0.103 |
Kenny | +0.101 |
hesitation | +0.101 |
Neg logit contributions | |
ide | -0.103 |
castle | -0.100 |
ull | -0.097 |
room | -0.097 |
structures | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
room | +0.022 |
ide | +0.021 |
ull | +0.021 |
castle | +0.019 |
structures | +0.017 |
Neg logit contributions | |
luggage | -0.040 |
hesitation | -0.039 |
reins | -0.038 |
Kel | -0.038 |
pup | -0.037 |
Token | The |
Token ID | 464 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
room | +0.025 |
ide | +0.024 |
castle | +0.022 |
ull | +0.022 |
structures | +0.020 |
Neg logit contributions | |
luggage | -0.040 |
hesitation | -0.039 |
Kel | -0.038 |
reins | -0.037 |
Hanna | -0.036 |
Token | policeman |
Token ID | 32166 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
nation | +0.017 |
castle | +0.016 |
ull | +0.016 |
structure | +0.015 |
salad | +0.015 |
Neg logit contributions | |
uster | -0.021 |
Kel | -0.021 |
Kenny | -0.020 |
Hanna | -0.020 |
Kathy | -0.019 |
Token | replied |
Token ID | 8712 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Buster | +0.461 |
uster | +0.461 |
Hanna | +0.456 |
Cindy | +0.443 |
training | +0.442 |
Neg logit contributions | |
ide | -0.455 |
castle | -0.451 |
ull | -0.428 |
room | -0.412 |
salad | -0.387 |
Token | , |
Token ID | 11 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ide | +0.008 |
castle | +0.008 |
ull | +0.008 |
room | +0.008 |
salad | +0.007 |
Neg logit contributions | |
Hanna | -0.010 |
Buster | -0.010 |
Kenny | -0.010 |
reins | -0.010 |
buck | -0.010 |
Token | � |
Token ID | 6184 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
luggage | +0.019 |
uster | +0.019 |
Hanna | +0.019 |
Buster | +0.019 |
pup | +0.019 |
Neg logit contributions | |
castle | -0.012 |
ide | -0.012 |
ull | -0.012 |
room | -0.011 |
salad | -0.011 |
Token | � |
Token ID | 95 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
hesitation | +0.008 |
reins | +0.008 |
training | +0.007 |
luggage | +0.007 |
Hanna | +0.007 |
Neg logit contributions | |
castle | -0.009 |
room | -0.009 |
ide | -0.009 |
structures | -0.008 |
nation | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
hesitation | +0.233 |
Cindy | +0.223 |
Hanna | +0.222 |
Kel | +0.220 |
luggage | +0.220 |
Neg logit contributions | |
room | -0.214 |
castle | -0.203 |
ide | -0.193 |
structures | -0.184 |
ull | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ide | +0.039 |
ull | +0.037 |
room | +0.035 |
castle | +0.034 |
ics | +0.032 |
Neg logit contributions | |
pup | -0.051 |
luggage | -0.050 |
Buster | -0.050 |
uster | -0.049 |
training | -0.049 |
Token | Dave |
Token ID | 27984 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
ide | +0.044 |
castle | +0.041 |
room | +0.039 |
ull | +0.039 |
ics | +0.036 |
Neg logit contributions | |
Kenny | -0.045 |
Buster | -0.045 |
luggage | -0.044 |
pup | -0.044 |
Kel | -0.044 |
Token | got |
Token ID | 1392 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Buster | +0.073 |
Kenny | +0.073 |
Cindy | +0.071 |
Hanna | +0.071 |
Kel | +0.071 |
Neg logit contributions | |
castle | -0.072 |
ide | -0.071 |
ull | -0.069 |
room | -0.066 |
salad | -0.062 |
Token | in |
Token ID | 287 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
salad | +0.011 |
ull | +0.011 |
pie | +0.010 |
castle | +0.010 |
ics | +0.010 |
Neg logit contributions | |
Michael | -0.018 |
Matthew | -0.018 |
uster | -0.018 |
Kenny | -0.018 |
Kathy | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
room | +0.023 |
salad | +0.020 |
castle | +0.018 |
ull | +0.017 |
ide | +0.017 |
Neg logit contributions | |
ha | -0.055 |
uster | -0.055 |
Kel | -0.054 |
Hanna | -0.053 |
Matthew | -0.053 |
Token | kay |
Token ID | 34681 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
castle | +0.009 |
tower | +0.009 |
salad | +0.009 |
nation | +0.009 |
structure | +0.009 |
Neg logit contributions | |
Kathy | -0.013 |
Kenny | -0.013 |
Kel | -0.012 |
Michael | -0.012 |
Eleanor | -0.012 |
Token | ak |
Token ID | 461 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Buster | +0.582 |
Kenny | +0.575 |
Hanna | +0.572 |
pup | +0.572 |
Cindy | +0.569 |
Neg logit contributions | |
castle | -0.357 |
ide | -0.356 |
ull | -0.331 |
room | -0.325 |
structures | -0.318 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ide | +0.122 |
castle | +0.122 |
ull | +0.116 |
structures | +0.113 |
room | +0.113 |
Neg logit contributions | |
Buster | -0.108 |
Kenny | -0.106 |
pup | -0.105 |
Hanna | -0.105 |
Hannah | -0.104 |
Token | padd |
Token ID | 14098 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
uster | +0.009 |
hesitation | +0.009 |
Kenny | +0.009 |
Matthew | +0.009 |
Kel | +0.009 |
Neg logit contributions | |
castle | -0.009 |
ull | -0.008 |
salad | -0.008 |
ide | -0.008 |
room | -0.008 |
Token | led |
Token ID | 992 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Kenny | +0.485 |
Buster | +0.482 |
Haley | +0.478 |
Kel | +0.475 |
Hanna | +0.475 |
Neg logit contributions | |
ide | -0.285 |
castle | -0.265 |
ull | -0.263 |
room | -0.254 |
structures | -0.240 |
Token | off |
Token ID | 572 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ide | +0.132 |
castle | +0.130 |
structures | +0.129 |
ull | +0.121 |
salad | +0.115 |
Neg logit contributions | |
Michael | -0.208 |
Matthew | -0.207 |
uster | -0.206 |
Haley | -0.204 |
Hanna | -0.204 |
Token | Everyone |
Token ID | 16190 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
ide | +0.038 |
room | +0.035 |
ics | +0.034 |
castle | +0.033 |
ull | +0.032 |
Neg logit contributions | |
Kenny | -0.047 |
Kel | -0.047 |
hesitation | -0.047 |
luggage | -0.046 |
uster | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ide | +0.005 |
castle | +0.005 |
ull | +0.005 |
room | +0.005 |
structures | +0.005 |
Neg logit contributions | |
Buster | -0.005 |
Hanna | -0.005 |
uster | -0.005 |
Kenny | -0.005 |
pup | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
Buster | +0.031 |
Kenny | +0.030 |
uster | +0.030 |
pup | +0.030 |
Hanna | +0.030 |
Neg logit contributions | |
ide | -0.031 |
castle | -0.031 |
ull | -0.030 |
room | -0.029 |
structures | -0.028 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
castle | +0.078 |
ide | +0.078 |
structures | +0.073 |
room | +0.073 |
ull | +0.073 |
Neg logit contributions | |
Buster | -0.067 |
Kenny | -0.067 |
pup | -0.066 |
Hanna | -0.066 |
Cindy | -0.066 |
Token | that |
Token ID | 326 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
ide | +0.193 |
castle | +0.190 |
ull | +0.176 |
structures | +0.174 |
room | +0.168 |
Neg logit contributions | |
uster | -0.216 |
Hanna | -0.213 |
Buster | -0.211 |
Eleanor | -0.205 |
Kenny | -0.205 |
Token | Rover |
Token ID | 36718 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
uster | +0.078 |
reins | +0.069 |
Kel | +0.069 |
buck | +0.069 |
training | +0.068 |
Neg logit contributions | |
ide | -0.082 |
castle | -0.075 |
ull | -0.075 |
salad | -0.074 |
ics | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Buster | +0.483 |
Kenny | +0.480 |
Hanna | +0.473 |
uster | +0.473 |
Kel | +0.470 |
Neg logit contributions | |
ide | -0.487 |
castle | -0.485 |
ull | -0.457 |
room | -0.447 |
structures | -0.436 |
Token | his |
Token ID | 465 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
uster | +0.012 |
Hanna | +0.011 |
Hannah | +0.011 |
Kenny | +0.011 |
Matthew | +0.011 |
Neg logit contributions | |
ide | -0.013 |
castle | -0.012 |
structures | -0.012 |
ull | -0.012 |
salad | -0.012 |
Token | owner |
Token ID | 4870 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
castle | +0.081 |
ide | +0.079 |
structures | +0.076 |
room | +0.074 |
ull | +0.074 |
Neg logit contributions | |
Buster | -0.095 |
uster | -0.095 |
Hanna | -0.095 |
Hannah | -0.094 |
Hank | -0.092 |
Token | were |
Token ID | 547 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Buster | +0.143 |
Kenny | +0.142 |
pup | +0.141 |
Hanna | +0.140 |
F | +0.139 |
Neg logit contributions | |
castle | -0.129 |
ide | -0.129 |
ull | -0.121 |
structures | -0.119 |
room | -0.118 |
Token | safe |
Token ID | 3338 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
castle | +0.132 |
ide | +0.131 |
ull | +0.126 |
room | +0.120 |
structures | +0.117 |
Neg logit contributions | |
Buster | -0.127 |
Kenny | -0.126 |
pup | -0.126 |
uster | -0.126 |
Hanna | -0.125 |
Token | adventures |
Token ID | 17545 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
uster | +0.026 |
Hanna | +0.026 |
Hannah | +0.025 |
Buster | +0.025 |
Kenny | +0.025 |
Neg logit contributions | |
ide | -0.028 |
structures | -0.027 |
castle | -0.027 |
salad | -0.025 |
structure | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ide | +0.042 |
castle | +0.041 |
room | +0.038 |
structures | +0.038 |
ull | +0.038 |
Neg logit contributions | |
Buster | -0.047 |
Hanna | -0.047 |
Kenny | -0.047 |
pup | -0.046 |
Cindy | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
hesitation | +0.008 |
training | +0.008 |
buck | +0.008 |
pup | +0.008 |
Buster | +0.008 |
Neg logit contributions | |
ide | -0.008 |
castle | -0.008 |
room | -0.008 |
ull | -0.007 |
structures | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ide | +0.042 |
ull | +0.040 |
room | +0.038 |
castle | +0.038 |
structures | +0.036 |
Neg logit contributions | |
pup | -0.042 |
Buster | -0.042 |
Cindy | -0.042 |
Hanna | -0.042 |
hesitation | -0.041 |
Token | The |
Token ID | 464 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ide | +0.047 |
castle | +0.045 |
room | +0.043 |
ull | +0.043 |
structures | +0.041 |
Neg logit contributions | |
Buster | -0.042 |
Hanna | -0.042 |
Cindy | -0.042 |
pup | -0.042 |
Kenny | -0.042 |
Token | puppy |
Token ID | 26188 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
castle | +0.023 |
salad | +0.023 |
tower | +0.022 |
structure | +0.021 |
nation | +0.021 |
Neg logit contributions | |
Kel | -0.027 |
Kenny | -0.026 |
uster | -0.026 |
Hanna | -0.026 |
Haley | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Buster | +0.464 |
Kenny | +0.457 |
Hanna | +0.456 |
pup | +0.452 |
uster | +0.450 |
Neg logit contributions | |
castle | -0.475 |
ide | -0.475 |
ull | -0.443 |
structures | -0.436 |
room | -0.435 |
Token | so |
Token ID | 523 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
uster | +0.029 |
Buster | +0.029 |
Hanna | +0.029 |
Kenny | +0.029 |
pup | +0.028 |
Neg logit contributions | |
ide | -0.026 |
castle | -0.026 |
ull | -0.025 |
room | -0.024 |
ics | -0.023 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
castle | +0.070 |
ide | +0.070 |
ull | +0.065 |
structures | +0.065 |
room | +0.065 |
Neg logit contributions | |
Buster | -0.070 |
Kenny | -0.069 |
pup | -0.068 |
Hanna | -0.068 |
Cindy | -0.067 |
Token | ! |
Token ID | 0 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
castle | +0.198 |
ide | +0.196 |
ull | +0.184 |
structures | +0.180 |
room | +0.178 |
Neg logit contributions | |
Hanna | -0.190 |
Buster | -0.187 |
uster | -0.186 |
Kenny | -0.182 |
Kel | -0.181 |
Token | He |
Token ID | 679 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
hesitation | +0.062 |
Buster | +0.062 |
Hanna | +0.062 |
training | +0.061 |
buck | +0.061 |
Neg logit contributions | |
ide | -0.052 |
castle | -0.052 |
room | -0.048 |
ull | -0.048 |
structures | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Buster | +0.022 |
Hanna | +0.021 |
Kenny | +0.021 |
pup | +0.021 |
Hannah | +0.021 |
Neg logit contributions | |
ide | -0.028 |
castle | -0.027 |
ull | -0.026 |
structures | -0.026 |
room | -0.025 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
Buster | +0.023 |
Kenny | +0.023 |
Hanna | +0.022 |
uster | +0.022 |
pup | +0.022 |
Neg logit contributions | |
castle | -0.023 |
ide | -0.023 |
ull | -0.022 |
room | -0.022 |
structures | -0.022 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
Buster | +0.006 |
pup | +0.006 |
Hanna | +0.006 |
Kenny | +0.006 |
Hannah | +0.006 |
Neg logit contributions | |
ide | -0.006 |
castle | -0.006 |
ull | -0.006 |
structures | -0.006 |
room | -0.006 |
Token | how |
Token ID | 703 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
ide | +0.073 |
castle | +0.072 |
ull | +0.069 |
structures | +0.068 |
room | +0.068 |
Neg logit contributions | |
Buster | -0.061 |
Hanna | -0.060 |
Kenny | -0.060 |
pup | -0.060 |
uster | -0.060 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ide | +0.246 |
castle | +0.245 |
ull | +0.233 |
room | +0.228 |
structures | +0.227 |
Neg logit contributions | |
Buster | -0.215 |
Kenny | -0.212 |
pup | -0.211 |
Hanna | -0.210 |
Hannah | -0.207 |
Token | Mama |
Token ID | 40084 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ide | +0.196 |
castle | +0.195 |
ull | +0.186 |
structures | +0.182 |
room | +0.179 |
Neg logit contributions | |
Buster | -0.179 |
uster | -0.178 |
Kenny | -0.176 |
Hanna | -0.174 |
pup | -0.171 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
uster | +0.158 |
training | +0.153 |
reins | +0.152 |
Buster | +0.147 |
hesitation | +0.147 |
Neg logit contributions | |
ide | -0.122 |
castle | -0.114 |
ull | -0.110 |
room | -0.105 |
salad | -0.104 |
Token | Papa |
Token ID | 42328 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Buster | +0.019 |
pup | +0.018 |
Cindy | +0.018 |
Kenny | +0.018 |
Hannah | +0.018 |
Neg logit contributions | |
ide | -0.022 |
castle | -0.022 |
room | -0.021 |
ull | -0.021 |
structures | -0.021 |
Token | were |
Token ID | 547 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
uster | +0.189 |
Kenny | +0.180 |
Kel | +0.179 |
Buster | +0.179 |
reins | +0.178 |
Neg logit contributions | |
ide | -0.156 |
castle | -0.148 |
ull | -0.142 |
room | -0.138 |
salad | -0.135 |
Token | together |
Token ID | 1978 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
castle | +0.121 |
ide | +0.120 |
ull | +0.114 |
room | +0.111 |
structures | +0.110 |
Neg logit contributions | |
Buster | -0.116 |
Kenny | -0.115 |
pup | -0.114 |
Hanna | -0.114 |
Hannah | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
castle | +0.282 |
ide | +0.277 |
ull | +0.257 |
salad | +0.250 |
room | +0.248 |
Neg logit contributions | |
Buster | -0.313 |
Kenny | -0.313 |
uster | -0.307 |
Kel | -0.306 |
Hanna | -0.305 |
Token | my |
Token ID | 1820 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
castle | +0.136 |
ide | +0.134 |
structures | +0.131 |
ull | +0.129 |
room | +0.128 |
Neg logit contributions | |
pup | -0.094 |
Buster | -0.094 |
Kenny | -0.094 |
buck | -0.092 |
Hannah | -0.091 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
buck | +0.009 |
pup | +0.009 |
Buster | +0.008 |
Hannah | +0.008 |
Kenny | +0.008 |
Neg logit contributions | |
ide | -0.014 |
structures | -0.014 |
castle | -0.014 |
room | -0.014 |
ull | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
castle | +0.013 |
ide | +0.011 |
ull | +0.011 |
salad | +0.011 |
structures | +0.011 |
Neg logit contributions | |
uster | -0.017 |
Hanna | -0.017 |
Kenny | -0.016 |
Kel | -0.016 |
Michael | -0.016 |
Token | put |
Token ID | 1234 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ide | +0.006 |
castle | +0.006 |
ull | +0.006 |
structures | +0.006 |
room | +0.006 |
Neg logit contributions | |
Buster | -0.005 |
Kenny | -0.005 |
pup | -0.005 |
Hanna | -0.005 |
Cindy | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Michael | +0.117 |
Hanna | +0.115 |
Matthew | +0.115 |
uster | +0.115 |
Kenny | +0.113 |
Neg logit contributions | |
salad | -0.070 |
ull | -0.070 |
castle | -0.070 |
room | -0.065 |
structures | -0.064 |
Token | penny |
Token ID | 26369 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
castle | +0.010 |
ull | +0.009 |
salad | +0.009 |
tower | +0.008 |
ide | +0.008 |
Neg logit contributions | |
Kenny | -0.012 |
Buster | -0.011 |
Hanna | -0.011 |
Michael | -0.011 |
Haley | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Buster | +0.177 |
pup | +0.174 |
Kenny | +0.174 |
Hanna | +0.172 |
Hannah | +0.170 |
Neg logit contributions | |
ide | -0.204 |
castle | -0.204 |
ull | -0.193 |
structures | -0.190 |
room | -0.190 |
Token | his |
Token ID | 465 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
castle | +0.037 |
room | +0.036 |
ide | +0.036 |
ull | +0.036 |
salad | +0.035 |
Neg logit contributions | |
uster | -0.063 |
Hanna | -0.062 |
Kel | -0.061 |
Buster | -0.061 |
Kenny | -0.061 |
Token | small |
Token ID | 1402 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
castle | +0.112 |
ide | +0.109 |
ull | +0.105 |
structures | +0.105 |
room | +0.104 |
Neg logit contributions | |
Buster | -0.055 |
Kenny | -0.055 |
Hanna | -0.053 |
Kel | -0.052 |
Cindy | -0.052 |
Token | pig |
Token ID | 12967 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
castle | +0.050 |
salad | +0.048 |
ide | +0.047 |
structures | +0.046 |
room | +0.046 |
Neg logit contributions | |
Kenny | -0.039 |
Buster | -0.038 |
Hanna | -0.038 |
Kel | -0.038 |
Michael | -0.038 |
Token | gy |
Token ID | 1360 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Buster | +0.276 |
pup | +0.272 |
Kenny | +0.272 |
Hanna | +0.269 |
Cindy | +0.266 |
Neg logit contributions | |
ide | -0.180 |
castle | -0.180 |
ull | -0.168 |
structures | -0.163 |
room | -0.163 |
Token | great |
Token ID | 1049 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Kel | +0.023 |
Kenny | +0.023 |
uster | +0.023 |
Buster | +0.023 |
Hanna | +0.022 |
Neg logit contributions | |
castle | -0.029 |
ide | -0.028 |
salad | -0.028 |
ull | -0.027 |
structures | -0.027 |
Token | time |
Token ID | 640 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Buster | +0.099 |
Kenny | +0.097 |
pup | +0.097 |
Hanna | +0.097 |
Hannah | +0.095 |
Neg logit contributions | |
ide | -0.147 |
castle | -0.147 |
ull | -0.140 |
room | -0.138 |
structures | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
Buster | +0.027 |
Hanna | +0.026 |
Kel | +0.026 |
Kenny | +0.026 |
uster | +0.026 |
Neg logit contributions | |
castle | -0.016 |
ide | -0.016 |
structures | -0.015 |
room | -0.015 |
ull | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Buster | +0.006 |
Kenny | +0.006 |
pup | +0.006 |
uster | +0.006 |
Kel | +0.006 |
Neg logit contributions | |
ide | -0.005 |
castle | -0.005 |
ull | -0.005 |
room | -0.005 |
structures | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ide | +0.035 |
castle | +0.035 |
ull | +0.034 |
room | +0.033 |
structures | +0.033 |
Neg logit contributions | |
Buster | -0.026 |
Kenny | -0.025 |
pup | -0.025 |
Hanna | -0.025 |
Cindy | -0.025 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ide | +0.031 |
castle | +0.030 |
ull | +0.028 |
room | +0.028 |
structures | +0.027 |
Neg logit contributions | |
Buster | -0.033 |
Kenny | -0.033 |
pup | -0.032 |
Hanna | -0.032 |
Cindy | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Buster | +0.113 |
pup | +0.110 |
Kenny | +0.109 |
Cindy | +0.109 |
Hanna | +0.108 |
Neg logit contributions | |
ide | -0.120 |
castle | -0.120 |
room | -0.113 |
ull | -0.112 |
structures | -0.107 |
Token | dad |
Token ID | 9955 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Kenny | +0.024 |
Kel | +0.023 |
Buster | +0.023 |
uster | +0.023 |
Hanna | +0.023 |
Neg logit contributions | |
castle | -0.018 |
ide | -0.017 |
salad | -0.017 |
ull | -0.016 |
room | -0.016 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ide | +0.047 |
castle | +0.047 |
room | +0.044 |
ull | +0.044 |
salad | +0.041 |
Neg logit contributions | |
Buster | -0.049 |
Kenny | -0.049 |
Kel | -0.048 |
pup | -0.048 |
Hanna | -0.048 |
Token | Anna |
Token ID | 11735 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Buster | +0.259 |
Kel | +0.254 |
Kenny | +0.254 |
uster | +0.252 |
Matthew | +0.251 |
Neg logit contributions | |
ide | -0.211 |
room | -0.193 |
structures | -0.183 |
ull | -0.179 |
castle | -0.178 |
Token | and |
Token ID | 290 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Buster | +0.035 |
Kenny | +0.035 |
Kel | +0.035 |
Hanna | +0.034 |
Cindy | +0.034 |
Neg logit contributions | |
ide | -0.032 |
castle | -0.031 |
ull | -0.029 |
room | -0.029 |
structures | -0.028 |
Token | day |
Token ID | 1110 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
Buster | +0.117 |
Kenny | +0.115 |
Hanna | +0.113 |
pup | +0.113 |
Cindy | +0.113 |
Neg logit contributions | |
ide | -0.147 |
castle | -0.146 |
ull | -0.140 |
room | -0.136 |
structures | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ide | +0.046 |
castle | +0.046 |
ull | +0.044 |
room | +0.043 |
structures | +0.043 |
Neg logit contributions | |
Buster | -0.052 |
uster | -0.052 |
pup | -0.052 |
Kenny | -0.051 |
Hanna | -0.051 |
Token | their |
Token ID | 511 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Buster | +0.028 |
Kenny | +0.027 |
pup | +0.027 |
uster | +0.027 |
Hanna | +0.027 |
Neg logit contributions | |
castle | -0.023 |
ide | -0.023 |
structures | -0.022 |
ull | -0.022 |
room | -0.022 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
castle | +0.027 |
ide | +0.027 |
structures | +0.025 |
salad | +0.025 |
ull | +0.025 |
Neg logit contributions | |
Buster | -0.032 |
Kenny | -0.032 |
Hanna | -0.032 |
Kel | -0.032 |
uster | -0.032 |
Token | told |
Token ID | 1297 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Buster | +0.014 |
Kenny | +0.014 |
Hanna | +0.014 |
pup | +0.014 |
Hannah | +0.014 |
Neg logit contributions | |
castle | -0.019 |
ide | -0.019 |
ull | -0.018 |
structures | -0.018 |
room | -0.017 |
Token | them |
Token ID | 606 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Buster | +0.151 |
Kenny | +0.148 |
Hanna | +0.147 |
pup | +0.147 |
Hannah | +0.145 |
Neg logit contributions | |
castle | -0.183 |
ide | -0.181 |
ull | -0.172 |
room | -0.168 |
structures | -0.168 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
Buster | +0.126 |
Kenny | +0.124 |
pup | +0.124 |
Hanna | +0.124 |
Cindy | +0.122 |
Neg logit contributions | |
ide | -0.138 |
castle | -0.138 |
ull | -0.130 |
structures | -0.128 |
room | -0.128 |
Token | clean |
Token ID | 3424 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Buster | +0.001 |
Hanna | +0.001 |
Hannah | +0.001 |
pup | +0.001 |
Kenny | +0.001 |
Neg logit contributions | |
castle | -0.001 |
ide | -0.001 |
structures | -0.001 |
ull | -0.001 |
room | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ide | +0.019 |
castle | +0.019 |
structures | +0.018 |
room | +0.018 |
ull | +0.018 |
Neg logit contributions | |
Buster | -0.022 |
Kenny | -0.022 |
uster | -0.022 |
pup | -0.022 |
Hanna | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
ide | +0.016 |
castle | +0.016 |
ull | +0.015 |
room | +0.015 |
structures | +0.015 |
Neg logit contributions | |
Buster | -0.018 |
Kenny | -0.018 |
pup | -0.017 |
Hanna | -0.017 |
Cindy | -0.017 |
Token | attic |
Token ID | 46113 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Buster | +0.002 |
Kenny | +0.002 |
F | +0.002 |
Peggy | +0.002 |
Haley | +0.002 |
Neg logit contributions | |
ide | -0.001 |
castle | -0.001 |
structures | -0.001 |
salad | -0.001 |
structure | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ide | +0.132 |
castle | +0.128 |
ull | +0.122 |
structures | +0.120 |
room | +0.117 |
Neg logit contributions | |
Buster | -0.133 |
pup | -0.133 |
Hanna | -0.132 |
uster | -0.132 |
Kenny | -0.131 |
Token | He |
Token ID | 679 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Buster | +0.003 |
Hanna | +0.003 |
pup | +0.003 |
Kenny | +0.003 |
uster | +0.003 |
Neg logit contributions | |
ide | -0.003 |
castle | -0.003 |
ull | -0.003 |
room | -0.003 |
structures | -0.003 |
Token | should |
Token ID | 815 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Buster | +0.018 |
uster | +0.018 |
Kenny | +0.018 |
Hanna | +0.018 |
pup | +0.018 |
Neg logit contributions | |
castle | -0.017 |
ide | -0.017 |
ull | -0.016 |
structures | -0.015 |
room | -0.015 |
Token | not |
Token ID | 407 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Buster | +0.150 |
pup | +0.148 |
Kenny | +0.148 |
Hanna | +0.148 |
uster | +0.145 |
Neg logit contributions | |
castle | -0.129 |
ide | -0.128 |
ull | -0.119 |
room | -0.117 |
structures | -0.116 |
Token | do |
Token ID | 466 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
castle | +0.204 |
ide | +0.202 |
ull | +0.192 |
structures | +0.191 |
room | +0.189 |
Neg logit contributions | |
Buster | -0.186 |
pup | -0.184 |
Kenny | -0.183 |
F | -0.180 |
Cindy | -0.179 |
Token | that |
Token ID | 326 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
uster | +0.045 |
Hanna | +0.045 |
Buster | +0.045 |
pup | +0.044 |
Kenny | +0.044 |
Neg logit contributions | |
castle | -0.041 |
ide | -0.041 |
structures | -0.039 |
ull | -0.039 |
room | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Buster | +0.072 |
Kenny | +0.070 |
Hanna | +0.070 |
pup | +0.070 |
Cindy | +0.069 |
Neg logit contributions | |
castle | -0.076 |
ide | -0.076 |
ull | -0.072 |
structures | -0.070 |
room | -0.070 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ide | +0.013 |
castle | +0.013 |
ull | +0.013 |
room | +0.012 |
structures | +0.012 |
Neg logit contributions | |
Buster | -0.015 |
pup | -0.015 |
Hanna | -0.015 |
Kenny | -0.014 |
hesitation | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ide | +0.094 |
castle | +0.093 |
ull | +0.087 |
room | +0.085 |
structures | +0.085 |
Neg logit contributions | |
Buster | -0.125 |
Kenny | -0.124 |
Hanna | -0.124 |
pup | -0.123 |
Hannah | -0.122 |
Token | go |
Token ID | 467 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ide | +0.104 |
castle | +0.103 |
ull | +0.098 |
structures | +0.095 |
room | +0.095 |
Neg logit contributions | |
Buster | -0.106 |
Kenny | -0.105 |
pup | -0.104 |
Hanna | -0.104 |
Cindy | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
castle | +0.134 |
ide | +0.121 |
room | +0.117 |
ull | +0.114 |
build | +0.103 |
Neg logit contributions | |
Kel | -0.205 |
Michael | -0.200 |
hesitation | -0.199 |
Haley | -0.198 |
Matthew | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
Buster | +0.059 |
Kenny | +0.058 |
pup | +0.057 |
Hanna | +0.057 |
Hannah | +0.057 |
Neg logit contributions | |
castle | -0.065 |
ide | -0.065 |
ull | -0.061 |
structures | -0.060 |
room | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Buster | +0.003 |
Kenny | +0.003 |
Hanna | +0.003 |
pup | +0.003 |
Cindy | +0.003 |
Neg logit contributions | |
ide | -0.003 |
castle | -0.003 |
ull | -0.002 |
room | -0.002 |
structures | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
castle | +0.037 |
ide | +0.036 |
ull | +0.034 |
structures | +0.034 |
room | +0.034 |
Neg logit contributions | |
Buster | -0.028 |
Kenny | -0.027 |
Hanna | -0.027 |
pup | -0.027 |
Cindy | -0.026 |
Token | They |
Token ID | 2990 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
castle | +0.033 |
ide | +0.033 |
ull | +0.031 |
structures | +0.030 |
room | +0.030 |
Neg logit contributions | |
Buster | -0.032 |
pup | -0.032 |
Kenny | -0.031 |
Hanna | -0.031 |
Hannah | -0.031 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
castle | +0.054 |
ide | +0.054 |
ull | +0.051 |
room | +0.050 |
structures | +0.049 |
Neg logit contributions | |
Buster | -0.049 |
Kenny | -0.048 |
Hanna | -0.048 |
pup | -0.048 |
Cindy | -0.047 |
Token | at |
Token ID | 379 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
castle | +0.115 |
ide | +0.115 |
structures | +0.109 |
ull | +0.107 |
salad | +0.105 |
Neg logit contributions | |
Hanna | -0.156 |
Buster | -0.156 |
Kenny | -0.154 |
Kel | -0.153 |
Hannah | -0.152 |
Token | the |
Token ID | 262 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
ide | +0.086 |
castle | +0.082 |
structures | +0.081 |
room | +0.078 |
ull | +0.078 |
Neg logit contributions | |
Hanna | -0.144 |
Buster | -0.144 |
uster | -0.143 |
Kenny | -0.142 |
Matthew | -0.142 |
Token | ground |
Token ID | 2323 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Buster | +0.007 |
Kenny | +0.007 |
Hanna | +0.007 |
uster | +0.006 |
Kel | +0.006 |
Neg logit contributions | |
castle | -0.005 |
structures | -0.005 |
salad | -0.005 |
ide | -0.005 |
room | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
castle | +0.106 |
ide | +0.105 |
ull | +0.103 |
room | +0.100 |
structures | +0.098 |
Neg logit contributions | |
pup | -0.077 |
Kenny | -0.076 |
F | -0.076 |
Buster | -0.075 |
Hannah | -0.073 |
Token | They |
Token ID | 1119 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
castle | +0.000 |
ide | +0.000 |
ull | +0.000 |
structures | +0.000 |
room | +0.000 |
Neg logit contributions | |
Buster | -0.000 |
Kenny | -0.000 |
pup | -0.000 |
Hanna | -0.000 |
F | -0.000 |
Token | did |
Token ID | 750 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ide | +0.017 |
castle | +0.017 |
ull | +0.017 |
structures | +0.016 |
room | +0.016 |
Neg logit contributions | |
Buster | -0.015 |
Kenny | -0.015 |
pup | -0.014 |
F | -0.014 |
Cindy | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
Buster | +0.027 |
F | +0.026 |
Cindy | +0.026 |
Hanna | +0.026 |
pup | +0.025 |
Neg logit contributions | |
castle | -0.042 |
ide | -0.042 |
room | -0.040 |
structures | -0.039 |
ull | -0.038 |
Token | confused |
Token ID | 10416 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
castle | +0.059 |
ide | +0.058 |
room | +0.056 |
structures | +0.055 |
ull | +0.054 |
Neg logit contributions | |
F | -0.037 |
Buster | -0.037 |
Cindy | -0.036 |
Hanna | -0.036 |
pup | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
castle | +0.027 |
ide | +0.024 |
structures | +0.024 |
room | +0.024 |
ull | +0.024 |
Neg logit contributions | |
F | -0.015 |
pup | -0.014 |
Buster | -0.014 |
ahead | -0.013 |
Kenny | -0.013 |
Token | It |
Token ID | 632 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
F | +0.003 |
Kenny | +0.002 |
Cindy | +0.002 |
Buster | +0.002 |
pup | +0.002 |
Neg logit contributions | |
castle | -0.008 |
ide | -0.007 |
ics | -0.007 |
structures | -0.006 |
ull | -0.006 |
Token | did |
Token ID | 750 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
F | +0.039 |
buck | +0.037 |
pup | +0.037 |
Buster | +0.037 |
Hanna | +0.037 |
Neg logit contributions | |
castle | -0.053 |
ide | -0.051 |
room | -0.050 |
structures | -0.048 |
ull | -0.047 |
Token | not |
Token ID | 407 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
castle | +0.159 |
room | +0.152 |
ide | +0.149 |
ull | +0.143 |
ase | +0.132 |
Neg logit contributions | |
training | -0.132 |
F | -0.131 |
hesitation | -0.127 |
buck | -0.125 |
ahead | -0.125 |
Token | know |
Token ID | 760 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
castle | +0.255 |
ide | +0.239 |
structures | +0.236 |
room | +0.236 |
ull | +0.219 |
Neg logit contributions | |
training | -0.144 |
buck | -0.143 |
Buster | -0.141 |
Hanna | -0.141 |
pup | -0.140 |
Token | where |
Token ID | 810 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
castle | +0.008 |
ide | +0.007 |
room | +0.007 |
ull | +0.007 |
structures | +0.007 |
Neg logit contributions | |
F | -0.007 |
Buster | -0.006 |
pup | -0.006 |
Kenny | -0.006 |
Hanna | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
castle | +0.294 |
ide | +0.289 |
room | +0.272 |
structures | +0.262 |
ull | +0.259 |
Neg logit contributions | |
F | -0.158 |
pup | -0.156 |
Buster | -0.155 |
Hanna | -0.151 |
training | -0.148 |
Token | go |
Token ID | 467 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
castle | +0.017 |
structures | +0.015 |
ocado | +0.014 |
pulp | +0.014 |
imm | +0.014 |
Neg logit contributions | |
F | -0.008 |
pup | -0.007 |
Mag | -0.007 |
training | -0.007 |
Hanna | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
castle | +0.227 |
ide | +0.214 |
room | +0.204 |
ull | +0.201 |
structures | +0.197 |
Neg logit contributions | |
F | -0.140 |
Buster | -0.138 |
pup | -0.138 |
Cindy | -0.131 |
Mag | -0.130 |
Token | On |
Token ID | 1550 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
Buster | +0.002 |
Hanna | +0.002 |
Kenny | +0.002 |
pup | +0.002 |
Hannah | +0.002 |
Neg logit contributions | |
castle | -0.002 |
ide | -0.002 |
ull | -0.001 |
structures | -0.001 |
room | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
uster | +0.087 |
pup | +0.085 |
reins | +0.085 |
training | +0.082 |
Hanna | +0.082 |
Neg logit contributions | |
castle | -0.064 |
ide | -0.063 |
room | -0.060 |
ics | -0.057 |
ull | -0.057 |
Token | way |
Token ID | 835 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
castle | +0.035 |
ide | +0.035 |
structures | +0.033 |
salad | +0.032 |
room | +0.031 |
Neg logit contributions | |
uster | -0.039 |
Kenny | -0.039 |
Buster | -0.039 |
Hanna | -0.038 |
Kel | -0.038 |
Token | out |
Token ID | 503 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ide | +0.099 |
castle | +0.099 |
ull | +0.093 |
room | +0.091 |
structures | +0.086 |
Neg logit contributions | |
Hanna | -0.105 |
Buster | -0.103 |
Matthew | -0.102 |
Kenny | -0.101 |
Haley | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ide | +0.147 |
castle | +0.145 |
room | +0.138 |
ull | +0.136 |
structures | +0.133 |
Neg logit contributions | |
Hanna | -0.164 |
Buster | -0.164 |
pup | -0.163 |
Cindy | -0.163 |
Kenny | -0.160 |
Token | Billy |
Token ID | 15890 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Hanna | +0.015 |
uster | +0.015 |
Hannah | +0.014 |
Haley | +0.014 |
Kenny | +0.014 |
Neg logit contributions | |
castle | -0.014 |
ide | -0.014 |
ull | -0.014 |
structures | -0.013 |
room | -0.013 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
Buster | +0.054 |
pup | +0.053 |
Hanna | +0.053 |
Kenny | +0.053 |
Hannah | +0.052 |
Neg logit contributions | |
castle | -0.056 |
ide | -0.056 |
ull | -0.053 |
structures | -0.053 |
room | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
castle | +0.081 |
ide | +0.080 |
ull | +0.078 |
structures | +0.076 |
room | +0.076 |
Neg logit contributions | |
Hanna | -0.067 |
Buster | -0.067 |
Kenny | -0.066 |
uster | -0.065 |
pup | -0.065 |
Token | bin |
Token ID | 9874 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Kenny | +0.022 |
Buster | +0.022 |
Hanna | +0.022 |
Kel | +0.022 |
uster | +0.022 |
Neg logit contributions | |
castle | -0.021 |
ide | -0.019 |
salad | -0.019 |
ull | -0.019 |
structures | -0.018 |
Token | for |
Token ID | 329 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
Buster | +0.110 |
Hanna | +0.109 |
Kenny | +0.108 |
pup | +0.107 |
Hannah | +0.107 |
Neg logit contributions | |
castle | -0.107 |
ide | -0.107 |
room | -0.099 |
ull | -0.098 |
structures | -0.097 |
Token | waste |
Token ID | 7030 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Hanna | +0.054 |
uster | +0.053 |
Haley | +0.053 |
Michael | +0.052 |
pup | +0.052 |
Neg logit contributions | |
castle | -0.038 |
ull | -0.037 |
ide | -0.037 |
salad | -0.036 |
structures | -0.036 |
Token | again |
Token ID | 757 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
castle | +0.144 |
ide | +0.143 |
ull | +0.135 |
room | +0.133 |
structures | +0.132 |
Neg logit contributions | |
Buster | -0.135 |
Kenny | -0.133 |
pup | -0.132 |
Hanna | -0.132 |
Cindy | -0.130 |
Token | to |
Token ID | 284 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
castle | +0.112 |
ide | +0.112 |
ull | +0.105 |
room | +0.103 |
structures | +0.102 |
Neg logit contributions | |
Buster | -0.111 |
Kenny | -0.110 |
pup | -0.109 |
Hanna | -0.109 |
Cindy | -0.107 |
Token | help |
Token ID | 1037 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Buster | +0.005 |
Kenny | +0.005 |
pup | +0.005 |
Hanna | +0.005 |
Cindy | +0.005 |
Neg logit contributions | |
castle | -0.005 |
ide | -0.005 |
ull | -0.004 |
room | -0.004 |
structures | -0.004 |
Token | clean |
Token ID | 3424 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Buster | +0.144 |
Hanna | +0.143 |
Kenny | +0.142 |
pup | +0.141 |
Hannah | +0.141 |
Neg logit contributions | |
castle | -0.147 |
ide | -0.143 |
ull | -0.136 |
structures | -0.133 |
room | -0.132 |
Token | up |
Token ID | 510 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ide | +0.025 |
castle | +0.024 |
room | +0.023 |
structures | +0.023 |
ull | +0.023 |
Neg logit contributions | |
Buster | -0.026 |
Kenny | -0.026 |
pup | -0.026 |
uster | -0.025 |
F | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ide | +0.028 |
castle | +0.027 |
structures | +0.026 |
ull | +0.025 |
room | +0.025 |
Neg logit contributions | |
Buster | -0.029 |
Kenny | -0.029 |
pup | -0.028 |
Hanna | -0.028 |
uster | -0.028 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
castle | +0.016 |
ide | +0.016 |
structures | +0.015 |
ull | +0.015 |
salad | +0.015 |
Neg logit contributions | |
Buster | -0.020 |
Kenny | -0.020 |
Hanna | -0.020 |
Kel | -0.020 |
F | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ide | +0.009 |
castle | +0.009 |
ull | +0.009 |
room | +0.009 |
structures | +0.009 |
Neg logit contributions | |
Hanna | -0.008 |
pup | -0.008 |
Buster | -0.008 |
Hannah | -0.008 |
Cindy | -0.007 |
Token | It |
Token ID | 632 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
Buster | +0.002 |
Kenny | +0.002 |
pup | +0.002 |
Hanna | +0.002 |
Cindy | +0.002 |
Neg logit contributions | |
ide | -0.002 |
castle | -0.002 |
ull | -0.002 |
room | -0.002 |
structures | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Buster | +0.046 |
Hanna | +0.045 |
Kenny | +0.045 |
pup | +0.045 |
Hannah | +0.045 |
Neg logit contributions | |
castle | -0.056 |
ide | -0.056 |
ull | -0.053 |
room | -0.053 |
structures | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
pup | +0.042 |
uster | +0.042 |
Buster | +0.042 |
Kenny | +0.042 |
Hanna | +0.041 |
Neg logit contributions | |
ide | -0.041 |
castle | -0.041 |
ull | -0.039 |
salad | -0.039 |
room | -0.038 |
Token | is |
Token ID | 318 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
Buster | +0.027 |
pup | +0.027 |
Kenny | +0.027 |
Hanna | +0.027 |
F | +0.027 |
Neg logit contributions | |
castle | -0.030 |
ide | -0.030 |
ull | -0.029 |
structures | -0.028 |
room | -0.028 |
Token | angry |
Token ID | 7954 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ide | +0.006 |
castle | +0.006 |
ull | +0.006 |
room | +0.006 |
structures | +0.006 |
Neg logit contributions | |
Buster | -0.006 |
Kenny | -0.006 |
pup | -0.006 |
Hanna | -0.006 |
Cindy | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
castle | +0.102 |
ide | +0.100 |
ull | +0.097 |
structures | +0.093 |
room | +0.092 |
Neg logit contributions | |
pup | -0.073 |
Kenny | -0.073 |
F | -0.072 |
Buster | -0.071 |
Hannah | -0.071 |
Token | He |
Token ID | 679 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
castle | +0.013 |
ide | +0.013 |
ull | +0.012 |
structures | +0.012 |
room | +0.012 |
Neg logit contributions | |
Buster | -0.011 |
Kenny | -0.011 |
pup | -0.011 |
Hanna | -0.011 |
F | -0.011 |
Token | does |
Token ID | 857 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
uster | +0.004 |
Buster | +0.004 |
Kenny | +0.004 |
Hanna | +0.004 |
pup | +0.004 |
Neg logit contributions | |
castle | -0.003 |
ide | -0.003 |
structures | -0.003 |
salad | -0.003 |
ull | -0.003 |
Token | not |
Token ID | 407 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
castle | +0.096 |
ide | +0.094 |
ull | +0.086 |
structures | +0.083 |
room | +0.082 |
Neg logit contributions | |
Buster | -0.219 |
Kenny | -0.217 |
pup | -0.216 |
Hanna | -0.215 |
Cindy | -0.213 |
Token | understand |
Token ID | 1833 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
castle | +0.210 |
ide | +0.207 |
structures | +0.196 |
ull | +0.194 |
room | +0.194 |
Neg logit contributions | |
Buster | -0.167 |
pup | -0.165 |
Hanna | -0.164 |
Kenny | -0.164 |
Cindy | -0.161 |
Token | why |
Token ID | 1521 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
castle | +0.038 |
ide | +0.037 |
ull | +0.036 |
room | +0.035 |
structures | +0.035 |
Neg logit contributions | |
Kenny | -0.028 |
Buster | -0.028 |
Hannah | -0.027 |
F | -0.027 |
Hanna | -0.027 |
Token | she |
Token ID | 673 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
ide | +0.001 |
castle | +0.001 |
ull | +0.001 |
room | +0.001 |
structures | +0.001 |
Neg logit contributions | |
Buster | -0.001 |
Kenny | -0.001 |
pup | -0.001 |
Hanna | -0.001 |
Cindy | -0.001 |
Token | does |
Token ID | 857 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Buster | +0.005 |
Hanna | +0.005 |
Kenny | +0.005 |
Cindy | +0.005 |
pup | +0.005 |
Neg logit contributions | |
ide | -0.004 |
castle | -0.004 |
room | -0.004 |
structures | -0.004 |
ull | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
castle | +0.090 |
ide | +0.087 |
ull | +0.083 |
structures | +0.078 |
room | +0.076 |
Neg logit contributions | |
Buster | -0.221 |
Kenny | -0.220 |
uster | -0.218 |
pup | -0.218 |
Hanna | -0.218 |
Token | started |
Token ID | 2067 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Buster | +0.014 |
Hanna | +0.014 |
Kenny | +0.014 |
pup | +0.014 |
Hannah | +0.014 |
Neg logit contributions | |
castle | -0.016 |
ide | -0.016 |
ull | -0.015 |
structures | -0.015 |
room | -0.015 |
Token | squeezing |
Token ID | 40237 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Hanna | +0.067 |
uster | +0.067 |
Buster | +0.066 |
pup | +0.066 |
Kenny | +0.065 |
Neg logit contributions | |
castle | -0.064 |
ide | -0.064 |
ull | -0.062 |
structures | -0.061 |
salad | -0.059 |
Token | it |
Token ID | 340 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Buster | +0.100 |
Hanna | +0.099 |
Kenny | +0.099 |
pup | +0.098 |
Hannah | +0.097 |
Neg logit contributions | |
ide | -0.128 |
castle | -0.127 |
ull | -0.121 |
structures | -0.119 |
room | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Kenny | +0.047 |
Buster | +0.047 |
pup | +0.046 |
F | +0.046 |
Kel | +0.045 |
Neg logit contributions | |
castle | -0.063 |
ide | -0.061 |
ull | -0.060 |
room | -0.058 |
structures | -0.057 |
Token | The |
Token ID | 383 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Buster | +0.013 |
Kenny | +0.013 |
pup | +0.013 |
Hanna | +0.013 |
Hannah | +0.013 |
Neg logit contributions | |
castle | -0.014 |
ide | -0.014 |
ull | -0.013 |
room | -0.013 |
structures | -0.013 |
Token | cheese |
Token ID | 9891 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
castle | +0.054 |
salad | +0.052 |
ide | +0.050 |
ull | +0.050 |
structures | +0.050 |
Neg logit contributions | |
Kenny | -0.059 |
Kel | -0.059 |
Hanna | -0.058 |
Buster | -0.057 |
Haley | -0.057 |
Token | was |
Token ID | 373 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
ide | +0.505 |
structures | +0.486 |
castle | +0.484 |
room | +0.481 |
ull | +0.460 |
Neg logit contributions | |
pup | -0.334 |
Buster | -0.328 |
Kenny | -0.325 |
buck | -0.321 |
F | -0.319 |
Token | fragile |
Token ID | 21049 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Hanna | +0.033 |
Buster | +0.033 |
pup | +0.032 |
Kenny | +0.032 |
Hannah | +0.032 |
Neg logit contributions | |
castle | -0.034 |
ide | -0.034 |
ull | -0.033 |
structures | -0.031 |
room | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Hanna | +0.155 |
Buster | +0.152 |
Kenny | +0.150 |
Haley | +0.149 |
Kel | +0.148 |
Neg logit contributions | |
ide | -0.140 |
castle | -0.139 |
structures | -0.128 |
room | -0.126 |
ull | -0.125 |
Token | it |
Token ID | 340 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
Buster | +0.014 |
Kenny | +0.013 |
pup | +0.013 |
Hanna | +0.013 |
Hannah | +0.013 |
Neg logit contributions | |
ide | -0.017 |
castle | -0.017 |
ull | -0.016 |
room | -0.016 |
structures | -0.016 |
Token | broke |
Token ID | 6265 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Buster | +0.046 |
Kenny | +0.045 |
F | +0.044 |
pup | +0.044 |
Kel | +0.044 |
Neg logit contributions | |
ide | -0.062 |
castle | -0.061 |
room | -0.059 |
structures | -0.058 |
ull | -0.058 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Buster | +0.019 |
Kenny | +0.019 |
pup | +0.019 |
Hanna | +0.019 |
Hannah | +0.018 |
Neg logit contributions | |
castle | -0.020 |
ide | -0.020 |
ull | -0.019 |
room | -0.019 |
structures | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
uster | +0.008 |
Matthew | +0.008 |
Buster | +0.008 |
Michael | +0.008 |
Kenny | +0.008 |
Neg logit contributions | |
ide | -0.008 |
ull | -0.008 |
salad | -0.008 |
castle | -0.008 |
room | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
pup | +0.048 |
F | +0.047 |
Buster | +0.047 |
Kenny | +0.045 |
Cindy | +0.045 |
Neg logit contributions | |
castle | -0.080 |
ide | -0.079 |
room | -0.075 |
ull | -0.074 |
structures | -0.073 |
Token | piece |
Token ID | 3704 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
Buster | +0.022 |
Kenny | +0.022 |
pup | +0.022 |
Hanna | +0.022 |
Hannah | +0.021 |
Neg logit contributions | |
ide | -0.023 |
castle | -0.023 |
ull | -0.022 |
room | -0.022 |
structures | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
castle | +0.470 |
ide | +0.467 |
structures | +0.448 |
room | +0.437 |
ull | +0.437 |
Neg logit contributions | |
pup | -0.338 |
Buster | -0.337 |
F | -0.331 |
Kenny | -0.330 |
Hanna | -0.327 |
Token | bread |
Token ID | 8509 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
Buster | +0.071 |
Kenny | +0.070 |
pup | +0.070 |
Hanna | +0.070 |
Cindy | +0.069 |
Neg logit contributions | |
ide | -0.032 |
castle | -0.031 |
ull | -0.028 |
room | -0.028 |
structures | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ide | +0.381 |
castle | +0.377 |
room | +0.358 |
structures | +0.357 |
ull | +0.356 |
Neg logit contributions | |
Buster | -0.308 |
pup | -0.306 |
F | -0.301 |
Kenny | -0.299 |
Hanna | -0.299 |
Token | The |
Token ID | 383 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Cindy | +0.012 |
Hannah | +0.012 |
Buster | +0.012 |
Hanna | +0.011 |
Kenny | +0.011 |
Neg logit contributions | |
castle | -0.017 |
ide | -0.017 |
ull | -0.016 |
structures | -0.016 |
room | -0.016 |
Token | duck |
Token ID | 22045 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
castle | +0.049 |
ide | +0.048 |
ull | +0.046 |
room | +0.045 |
structures | +0.045 |
Neg logit contributions | |
Buster | -0.053 |
Kenny | -0.053 |
Hanna | -0.052 |
pup | -0.052 |
Hannah | -0.051 |
Token | che |
Token ID | 1125 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
pup | +0.064 |
F | +0.063 |
Buster | +0.061 |
buck | +0.061 |
Kenny | +0.059 |
Neg logit contributions | |
room | -0.138 |
castle | -0.136 |
ide | -0.133 |
structures | -0.131 |
anish | -0.123 |
Token | wed |
Token ID | 19103 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
castle | +0.056 |
ide | +0.053 |
structures | +0.051 |
ull | +0.049 |
room | +0.049 |
Neg logit contributions | |
Buster | -0.065 |
buck | -0.065 |
uster | -0.065 |
Hanna | -0.064 |
Kenny | -0.064 |
Token | I |
Token ID | 314 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ide | +0.005 |
castle | +0.005 |
room | +0.005 |
ull | +0.005 |
structures | +0.005 |
Neg logit contributions | |
Buster | -0.005 |
Kenny | -0.005 |
pup | -0.005 |
Hanna | -0.005 |
Cindy | -0.005 |
Token | want |
Token ID | 765 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
Buster | +0.019 |
Kenny | +0.019 |
Cindy | +0.018 |
Hanna | +0.018 |
Hannah | +0.018 |
Neg logit contributions | |
ide | -0.016 |
castle | -0.016 |
ull | -0.015 |
room | -0.015 |
salad | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
castle | +0.002 |
ide | +0.002 |
room | +0.002 |
ull | +0.002 |
structures | +0.002 |
Neg logit contributions | |
F | -0.001 |
Hanna | -0.001 |
Hannah | -0.001 |
Buster | -0.001 |
pup | -0.001 |
Token | taste |
Token ID | 6938 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
F | +0.004 |
Hanna | +0.004 |
buck | +0.004 |
Cindy | +0.004 |
Hannah | +0.004 |
Neg logit contributions | |
ide | -0.006 |
castle | -0.006 |
structures | -0.006 |
ull | -0.006 |
room | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
ide | +0.171 |
castle | +0.170 |
ull | +0.162 |
structures | +0.160 |
room | +0.159 |
Neg logit contributions | |
Buster | -0.120 |
Kenny | -0.118 |
pup | -0.117 |
Hanna | -0.117 |
Hannah | -0.115 |
Token | cake |
Token ID | 12187 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
pup | +0.009 |
luggage | +0.008 |
Hanna | +0.008 |
buck | +0.008 |
Cindy | +0.008 |
Neg logit contributions | |
ide | -0.006 |
castle | -0.005 |
room | -0.005 |
ull | -0.005 |
structures | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
ull | +0.437 |
castle | +0.417 |
ide | +0.410 |
structures | +0.410 |
room | +0.405 |
Neg logit contributions | |
Hanna | -0.262 |
F | -0.261 |
Hannah | -0.256 |
buck | -0.254 |
pup | -0.250 |
Token | Just |
Token ID | 2329 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ide | +0.005 |
castle | +0.005 |
room | +0.005 |
ull | +0.005 |
structures | +0.005 |
Neg logit contributions | |
Buster | -0.005 |
Kenny | -0.005 |
pup | -0.005 |
Hanna | -0.005 |
Cindy | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Buster | +0.080 |
pup | +0.080 |
Hanna | +0.079 |
F | +0.079 |
Hannah | +0.079 |
Neg logit contributions | |
ide | -0.110 |
castle | -0.110 |
ull | -0.104 |
structures | -0.103 |
room | -0.102 |
Token | little |
Token ID | 1310 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Buster | +0.023 |
Kenny | +0.023 |
Hanna | +0.023 |
pup | +0.022 |
Cindy | +0.022 |
Neg logit contributions | |
castle | -0.023 |
ide | -0.023 |
ull | -0.022 |
room | -0.021 |
structures | -0.021 |
Token | bit |
Token ID | 1643 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
pup | +0.015 |
Buster | +0.015 |
Hanna | +0.015 |
Kenny | +0.015 |
Hannah | +0.015 |
Neg logit contributions | |
ide | -0.021 |
castle | -0.021 |
ull | -0.020 |
room | -0.020 |
structures | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Kenny | +0.009 |
Buster | +0.009 |
F | +0.008 |
pup | +0.008 |
Cindy | +0.008 |
Neg logit contributions | |
castle | -0.010 |
ide | -0.010 |
ull | -0.010 |
room | -0.009 |
salad | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
castle | +0.036 |
ide | +0.035 |
ull | +0.033 |
structures | +0.033 |
room | +0.033 |
Neg logit contributions | |
Buster | -0.028 |
Kenny | -0.028 |
Hanna | -0.027 |
pup | -0.027 |
Hannah | -0.027 |
Token | Max |
Token ID | 11518 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ide | +0.035 |
room | +0.033 |
castle | +0.033 |
structures | +0.032 |
ull | +0.032 |
Neg logit contributions | |
Hanna | -0.032 |
Cindy | -0.032 |
Hannah | -0.032 |
hesitation | -0.031 |
Kel | -0.031 |
Token | had |
Token ID | 550 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Buster | +0.177 |
Kenny | +0.174 |
pup | +0.174 |
Hanna | +0.173 |
Cindy | +0.171 |
Neg logit contributions | |
castle | -0.194 |
ide | -0.194 |
ull | -0.183 |
room | -0.181 |
structures | -0.180 |
Token | an |
Token ID | 281 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
Buster | +0.188 |
pup | +0.185 |
F | +0.182 |
Kenny | +0.181 |
Cindy | +0.180 |
Neg logit contributions | |
ide | -0.294 |
castle | -0.293 |
ull | -0.275 |
room | -0.273 |
structures | -0.272 |
Token | idea |
Token ID | 2126 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
ide | +0.006 |
castle | +0.006 |
ull | +0.006 |
room | +0.005 |
structures | +0.005 |
Neg logit contributions | |
Buster | -0.009 |
pup | -0.009 |
Kenny | -0.009 |
Hanna | -0.009 |
Cindy | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ide | +0.284 |
ull | +0.267 |
castle | +0.265 |
room | +0.249 |
structures | +0.241 |
Neg logit contributions | |
Hanna | -0.411 |
Cindy | -0.403 |
Buster | -0.402 |
Hannah | -0.399 |
uster | -0.396 |
Token | He |
Token ID | 679 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Buster | +0.010 |
Kenny | +0.010 |
pup | +0.010 |
F | +0.010 |
Hannah | +0.010 |
Neg logit contributions | |
ide | -0.013 |
castle | -0.012 |
ull | -0.012 |
room | -0.011 |
ics | -0.011 |
Token | showed |
Token ID | 3751 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Buster | +0.018 |
Kenny | +0.017 |
Hanna | +0.017 |
pup | +0.017 |
Hannah | +0.017 |
Neg logit contributions | |
castle | -0.018 |
ide | -0.018 |
ull | -0.017 |
room | -0.017 |
structures | -0.017 |
Token | Sam |
Token ID | 3409 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
castle | +0.089 |
ide | +0.087 |
ull | +0.080 |
room | +0.078 |
structures | +0.077 |
Neg logit contributions | |
Buster | -0.098 |
Kenny | -0.097 |
pup | -0.095 |
F | -0.093 |
Cindy | -0.092 |
Token | his |
Token ID | 465 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
castle | +0.163 |
ide | +0.162 |
room | +0.153 |
ull | +0.152 |
structures | +0.149 |
Neg logit contributions | |
Buster | -0.144 |
pup | -0.142 |
Kenny | -0.141 |
Hannah | -0.139 |
Hanna | -0.139 |
Token | They |
Token ID | 2990 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
castle | +0.041 |
ide | +0.041 |
ull | +0.039 |
structures | +0.038 |
room | +0.038 |
Neg logit contributions | |
Buster | -0.036 |
Kenny | -0.035 |
pup | -0.035 |
Hanna | -0.035 |
Hannah | -0.034 |
Token | go |
Token ID | 467 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ide | +0.058 |
castle | +0.058 |
ull | +0.055 |
structures | +0.054 |
room | +0.053 |
Neg logit contributions | |
Buster | -0.046 |
Hanna | -0.045 |
Kenny | -0.045 |
pup | -0.045 |
Hannah | -0.044 |
Token | back |
Token ID | 736 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
castle | +0.145 |
ide | +0.137 |
room | +0.130 |
structures | +0.127 |
ull | +0.126 |
Neg logit contributions | |
Buster | -0.166 |
Kel | -0.164 |
Kenny | -0.162 |
Hanna | -0.161 |
Matthew | -0.161 |
Token | to |
Token ID | 284 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
Buster | +0.041 |
Kenny | +0.041 |
Hanna | +0.040 |
pup | +0.040 |
Hannah | +0.040 |
Neg logit contributions | |
ide | -0.050 |
castle | -0.050 |
ull | -0.047 |
room | -0.046 |
structures | -0.046 |
Token | their |
Token ID | 511 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Buster | +0.005 |
Kenny | +0.005 |
pup | +0.005 |
Hanna | +0.005 |
Hannah | +0.005 |
Neg logit contributions | |
castle | -0.005 |
ide | -0.005 |
ull | -0.005 |
room | -0.005 |
structures | -0.005 |
Token | game |
Token ID | 983 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
castle | +0.029 |
ide | +0.029 |
structures | +0.027 |
ull | +0.027 |
room | +0.027 |
Neg logit contributions | |
Buster | -0.035 |
Kenny | -0.035 |
Hanna | -0.035 |
pup | -0.034 |
Cindy | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
castle | +0.363 |
ide | +0.361 |
ull | +0.345 |
structures | +0.336 |
room | +0.332 |
Neg logit contributions | |
Buster | -0.326 |
Kenny | -0.322 |
pup | -0.322 |
Hanna | -0.319 |
Hannah | -0.316 |
Token | They |
Token ID | 1119 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
room | +0.002 |
structures | +0.002 |
ide | +0.002 |
castle | +0.002 |
ull | +0.002 |
Neg logit contributions | |
hesitation | -0.005 |
Buster | -0.005 |
uster | -0.005 |
training | -0.005 |
Matthew | -0.005 |
Token | are |
Token ID | 389 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
castle | +0.010 |
ide | +0.010 |
room | +0.009 |
ull | +0.009 |
structures | +0.009 |
Neg logit contributions | |
Buster | -0.011 |
Kenny | -0.011 |
pup | -0.011 |
Hanna | -0.011 |
Cindy | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ide | +0.062 |
castle | +0.061 |
ull | +0.058 |
room | +0.057 |
structures | +0.056 |
Neg logit contributions | |
Buster | -0.069 |
Kenny | -0.068 |
Hanna | -0.068 |
pup | -0.067 |
Hannah | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
ide | +0.194 |
castle | +0.194 |
ull | +0.184 |
room | +0.181 |
structures | +0.179 |
Neg logit contributions | |
Buster | -0.167 |
Kenny | -0.165 |
pup | -0.165 |
Hanna | -0.163 |
F | -0.163 |