TOP ACTIVATIONS
MAX = 13.377

floor . They talk to Luna in soft voices . They
's house . We found Luna in a box in the
water and food , but Luna did not want to play
of fun . Max and Luna like each other . They
bad dog . Anna gave Luna water and food , but
clay balls together !" But Luna ignored Max . She did
, I 'm sorry ," Luna says . " I was
" We are sorry , Luna . We want to be
am Ben . This is Luna . She is my puppy
, please . Max and Luna can be friends too ,"
was a little girl named Luna . She was only three
You are good friends to Luna . I am proud of
mist to go away . Luna knew something good would come
to the tree . But Luna does not want to see
" Look , Luna , birds !" Mia says
lady to come and take Luna home . They are glad
They jog with Rex . Luna waves to them . She
say , " Hello , Luna . We are happy to
birds . She picks up Luna and carries her to the
. She wants to show Luna the birds . She picks

MIN ACTIVATIONS
MIN = -10.913

had done it ! Ag nes skipped home , full of
. Tim my loved Wed nes days because that was the
always so happy on Wed nes days because of their lucky
over the place . Ag nes said ,
was always excited for Wed nes days because it was the
. Tim my loved Wed nes days because that was the
So , Ag nes resisted and eventually the wall
aches on Mondays , Wed nes days , and Fridays ."
a special hat for Wed nes days ." L
's so special about Wed nes days ?" Max
Lily . She loved Wed nes days because that 's when
One day , Ag nes came home from school and
â Ag nes smiled and said ,
Daisy . Daisy loved Wed nes days because on Wed nes
m sorry , Ag nes . I was too busy
baby 's name was Ag nes . Ag nes loved to
was Ag nes . Ag nes loved to wink at all
nes days because on Wed nes days she did something special
way . Ag nes loved to help out and
something special . On Wed nes days she liked to count

INTERVAL 7.305 - 13.377
CONTAINS 0.132%

needed help . So , Remy closed his eyes and prayed
Tim said sorry to the snake and they kept playing .
oo . It was the cow . It was angry .
had to go home , Andy was sad . He missed
too , Mitt ens ?" Mitt ens l icked his lips

INTERVAL 1.232 - 7.305
CONTAINS 20.494%

, look at this wig !" Anna says . " It
One of the friends , David , said to
wave he had ever seen ! But he was still brave
. It was a nice squirrel . Anna and
them together to fill the gap . Finally , the ceiling

INTERVAL -4.840 - 1.232
CONTAINS 78.342%

learned to be more careful and to always look out for
little sister watched in amaz ement . She climbed up the
friends and new drawings . They hold hands and follow the
catch flies and name them . But it 's not nice
Setup and Pay off : The setup was

INTERVAL -10.913 - -4.840
CONTAINS 1.033%

sad . They liked the penny . It was shiny and
follow the rules . The attic is not a place for
One day he saw a wreck that was underwater . He
, she saw a kindly old man . He wanted to
great time . <|endoftext|> L ily and Tom were twins .
Token floor
Token ID4314
Feature activation-3.99e+00

Pos logit contributions
 officer+0.028
 salon+0.024
 accident+0.022
ople+0.022
 ma+0.022
Neg logit contributions
Fel-0.031
Bet-0.030
tails-0.029
 Louise-0.028
June-0.028
Token.
Token ID13
Feature activation-6.49e-02

Pos logit contributions
 officer+0.316
 sir+0.279
 ma+0.271
iza+0.264
ateful+0.249
Neg logit contributions
tails-0.293
 buzzing-0.289
Fel-0.269
 webs-0.267
Bet-0.262
Token They
Token ID1119
Feature activation+1.47e+00

Pos logit contributions
 officer+0.004
 ma+0.004
 salon+0.003
 sir+0.003
ily+0.003
Neg logit contributions
Fel-0.006
tails-0.006
Bet-0.006
June-0.005
 buzzing-0.005
Token talk
Token ID1561
Feature activation+2.80e+00

Pos logit contributions
tails+0.133
Fel+0.130
 buzzing+0.122
Bet+0.120
 Louise+0.118
Neg logit contributions
 officer-0.090
 sir-0.081
 ma-0.079
 salon-0.075
ily-0.074
Token to
Token ID284
Feature activation-1.83e-01

Pos logit contributions
Fel+0.267
tails+0.265
Bet+0.256
 buzzing+0.248
June+0.245
Neg logit contributions
 officer-0.169
 salon-0.142
 ma-0.141
iza-0.138
 sir-0.134
Token Luna
Token ID23694
Feature activation+1.34e+01

Pos logit contributions
 officer+0.011
 ma+0.008
 salon+0.008
 sir+0.008
ily+0.008
Neg logit contributions
Fel-0.018
tails-0.018
Bet-0.018
June-0.017
 buzzing-0.017
Token in
Token ID287
Feature activation-1.83e+00

Pos logit contributions
Fel+1.429
tails+1.405
Bet+1.388
June+1.318
 buzzing+1.297
Neg logit contributions
 officer-0.698
 ma-0.537
 salon-0.526
 sir-0.516
 kids-0.497
Token soft
Token ID2705
Feature activation+2.28e+00

Pos logit contributions
 officer+0.092
 kids+0.074
 ma+0.072
 Dad+0.070
 accident+0.069
Neg logit contributions
Fel-0.196
tails-0.195
Bet-0.192
June-0.181
 buzzing-0.176
Token voices
Token ID10839
Feature activation+7.78e-02

Pos logit contributions
Fel+0.239
Bet+0.233
tails+0.221
June+0.216
 buzzing+0.210
Neg logit contributions
 officer-0.119
 kids-0.110
 ma-0.095
 Dad-0.095
 accident-0.094
Token.
Token ID13
Feature activation+1.71e-01

Pos logit contributions
tails+0.008
Fel+0.008
Bet+0.007
 buzzing+0.007
June+0.007
Neg logit contributions
 officer-0.005
 ma-0.004
 salon-0.004
 sir-0.004
iza-0.004
Token They
Token ID1119
Feature activation+1.17e+00

Pos logit contributions
tails+0.018
Fel+0.018
 buzzing+0.017
Bet+0.017
 leaping+0.016
Neg logit contributions
 officer-0.008
 Dad-0.007
 ma-0.007
ily-0.007
 sir-0.007
Token's
Token ID338
Feature activation+2.22e+00

Pos logit contributions
tails+0.067
Fel+0.066
Bet+0.064
 buzzing+0.061
June+0.061
Neg logit contributions
 officer-0.041
 ma-0.033
 salon-0.032
 sir-0.031
ily-0.031
Token house
Token ID2156
Feature activation-6.54e-01

Pos logit contributions
Fel+0.217
tails+0.217
Bet+0.210
 buzzing+0.200
June+0.199
Neg logit contributions
 officer-0.130
 ma-0.105
 salon-0.100
ily-0.100
 sir-0.100
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
 officer+0.045
ily+0.038
iza+0.038
 ma+0.038
 salon+0.036
Neg logit contributions
tails-0.055
 buzzing-0.051
Bet-0.051
Fel-0.049
 Louise-0.048
Token We
Token ID775
Feature activation+1.50e+00

Pos logit contributions
Fel+0.011
tails+0.011
Bet+0.011
June+0.010
 buzzing+0.010
Neg logit contributions
 officer-0.009
 ma-0.008
 salon-0.008
 sir-0.008
ily-0.007
Token found
Token ID1043
Feature activation-4.46e-01

Pos logit contributions
tails+0.132
Fel+0.127
Bet+0.124
 buzzing+0.118
 webs+0.116
Neg logit contributions
 officer-0.102
 ma-0.092
 salon-0.089
 sir-0.088
line-0.082
Token Luna
Token ID23694
Feature activation+1.34e+01

Pos logit contributions
 officer+0.023
 kids+0.020
 Dad+0.020
ily+0.019
 ma+0.019
Neg logit contributions
Fel-0.048
tails-0.046
Bet-0.046
June-0.043
 buzzing-0.042
Token in
Token ID287
Feature activation-1.84e+00

Pos logit contributions
tails+1.311
Fel+1.302
Bet+1.255
 buzzing+1.213
June+1.196
Neg logit contributions
 officer-0.782
 ma-0.629
 sir-0.606
 salon-0.606
iza-0.589
Token a
Token ID257
Feature activation+5.09e-03

Pos logit contributions
 officer+0.097
 ma+0.079
 salon+0.077
 kids+0.076
 sir+0.075
Neg logit contributions
Fel-0.193
tails-0.191
Bet-0.186
June-0.177
 buzzing-0.175
Token box
Token ID3091
Feature activation-2.68e+00

Pos logit contributions
Fel+0.000
tails+0.000
Bet+0.000
June+0.000
 Louise+0.000
Neg logit contributions
 officer-0.000
 salon-0.000
 store-0.000
 ma-0.000
 boy-0.000
Token in
Token ID287
Feature activation-1.89e+00

Pos logit contributions
 officer+0.188
 ma+0.162
ateful+0.158
 salesman+0.155
iza+0.154
Neg logit contributions
tails-0.216
 buzzing-0.210
Bet-0.194
 Louise-0.188
ches-0.183
Token the
Token ID262
Feature activation+1.25e-01

Pos logit contributions
 officer+0.102
 ma+0.082
 salon+0.079
 kids+0.079
 sir+0.077
Neg logit contributions
Fel-0.199
tails-0.195
Bet-0.190
June-0.180
 buzzing-0.179
Token water
Token ID1660
Feature activation-5.78e-01

Pos logit contributions
Fel+1.347
tails+1.328
Bet+1.304
June+1.240
 buzzing+1.223
Neg logit contributions
 officer-0.754
 ma-0.600
 salon-0.582
 sir-0.580
ily-0.571
Token and
Token ID290
Feature activation-5.56e-02

Pos logit contributions
 officer+0.035
 ma+0.028
 salon+0.028
 sir+0.027
iza+0.026
Neg logit contributions
Fel-0.056
tails-0.056
Bet-0.054
 buzzing-0.052
June-0.051
Token food
Token ID2057
Feature activation+3.16e+00

Pos logit contributions
 officer+0.003
 ma+0.003
 kids+0.003
ily+0.003
 sir+0.003
Neg logit contributions
Fel-0.005
Bet-0.005
tails-0.005
June-0.005
 buzzing-0.005
Token,
Token ID11
Feature activation+3.34e-01

Pos logit contributions
tails+0.299
Fel+0.297
Bet+0.289
 buzzing+0.282
 Louise+0.270
Neg logit contributions
 officer-0.192
 ma-0.157
 salon-0.155
iza-0.149
 sir-0.147
Token but
Token ID475
Feature activation-3.01e-01

Pos logit contributions
Fel+0.035
tails+0.034
Bet+0.033
June+0.032
 buzzing+0.032
Neg logit contributions
 officer-0.018
 ma-0.014
 salon-0.014
 sir-0.014
ily-0.013
Token Luna
Token ID23694
Feature activation+1.33e+01

Pos logit contributions
 officer+0.017
 ma+0.014
 salon+0.014
 kids+0.014
ily+0.014
Neg logit contributions
Fel-0.030
tails-0.030
Bet-0.029
June-0.028
 buzzing-0.027
Token did
Token ID750
Feature activation-3.29e+00

Pos logit contributions
Fel+1.332
tails+1.315
Bet+1.275
 buzzing+1.237
 Louise+1.209
Neg logit contributions
 officer-0.755
 ma-0.603
 salon-0.593
 sir-0.588
iza-0.540
Token not
Token ID407
Feature activation-9.36e-01

Pos logit contributions
 officer+0.085
 accident+0.060
ily+0.060
 salon+0.058
 ma+0.055
Neg logit contributions
Fel-0.421
Bet-0.421
tails-0.413
June-0.405
Lou-0.386
Token want
Token ID765
Feature activation-4.94e-01

Pos logit contributions
 officer+0.053
 salon+0.044
 ma+0.043
 sir+0.041
iza+0.040
Neg logit contributions
tails-0.094
Fel-0.092
Bet-0.091
 buzzing-0.088
June-0.085
Token to
Token ID284
Feature activation-3.38e-01

Pos logit contributions
 officer+0.016
ily+0.015
 Dad+0.014
 kids+0.014
 dad+0.012
Neg logit contributions
Bet-0.060
Fel-0.060
tails-0.060
June-0.057
elope-0.055
Token play
Token ID711
Feature activation+1.82e+00

Pos logit contributions
 officer+0.024
 ma+0.020
 salon+0.020
 sir+0.019
ily+0.019
Neg logit contributions
tails-0.030
Bet-0.028
Fel-0.027
 buzzing-0.027
June-0.025
Token of
Token ID286
Feature activation+6.04e-01

Pos logit contributions
Fel+0.386
tails+0.379
Bet+0.373
 buzzing+0.357
June+0.350
Neg logit contributions
 officer-0.295
 ma-0.256
 salon-0.252
 sir-0.243
iza-0.232
Token fun
Token ID1257
Feature activation+7.15e-01

Pos logit contributions
Fel+0.052
tails+0.052
Bet+0.050
June+0.047
 buzzing+0.047
Neg logit contributions
 officer-0.044
 ma-0.037
 salon-0.036
 sir-0.036
iza-0.034
Token.
Token ID13
Feature activation+1.00e-03

Pos logit contributions
Fel+0.082
tails+0.081
Bet+0.081
June+0.077
 Louise+0.076
Neg logit contributions
 officer-0.030
 kids-0.023
 ma-0.022
ily-0.022
 accident-0.022
Token Max
Token ID5436
Feature activation+4.86e+00

Pos logit contributions
tails+0.000
Fel+0.000
Bet+0.000
 buzzing+0.000
June+0.000
Neg logit contributions
 officer-0.000
 ma-0.000
 Dad-0.000
 kids-0.000
ily-0.000
Token and
Token ID290
Feature activation-5.92e-02

Pos logit contributions
Bet+0.469
tails+0.461
Fel+0.459
June+0.441
 Louise+0.413
Neg logit contributions
 officer-0.300
 ma-0.252
 salon-0.246
 kids-0.245
 sir-0.230
Token Luna
Token ID23694
Feature activation+1.33e+01

Pos logit contributions
 officer+0.004
 kids+0.004
 ma+0.004
 boy+0.004
 Dad+0.004
Neg logit contributions
Bet-0.005
Fel-0.005
tails-0.005
June-0.005
 buzzing-0.004
Token like
Token ID588
Feature activation+4.93e-01

Pos logit contributions
Fel+1.347
tails+1.333
Bet+1.315
June+1.252
 buzzing+1.223
Neg logit contributions
 officer-0.752
 ma-0.605
 salon-0.582
 sir-0.567
 kids-0.561
Token each
Token ID1123
Feature activation-3.10e-01

Pos logit contributions
Fel+0.050
tails+0.050
Bet+0.049
June+0.046
elope+0.045
Neg logit contributions
 officer-0.028
 kids-0.023
ily-0.022
 salon-0.022
 ma-0.021
Token other
Token ID584
Feature activation+1.49e+00

Pos logit contributions
 officer+0.017
 kids+0.013
 ma+0.012
ily+0.012
 salon+0.012
Neg logit contributions
Fel-0.034
tails-0.033
Bet-0.033
June-0.031
 Louise-0.030
Token.
Token ID13
Feature activation+1.73e-02

Pos logit contributions
tails+0.149
Fel+0.148
Bet+0.141
 buzzing+0.138
June+0.135
Neg logit contributions
 officer-0.084
 ma-0.069
 salon-0.068
 sir-0.066
iza-0.065
Token They
Token ID1119
Feature activation+1.09e+00

Pos logit contributions
tails+0.002
Fel+0.002
Bet+0.002
 buzzing+0.002
June+0.002
Neg logit contributions
 officer-0.001
 Dad-0.001
 ma-0.001
 kids-0.001
ily-0.001
Token bad
Token ID2089
Feature activation-7.04e-01

Pos logit contributions
 officer+0.057
 ma+0.047
 salon+0.046
 sir+0.045
 kids+0.044
Neg logit contributions
Fel-0.082
tails-0.081
Bet-0.079
June-0.075
 Louise-0.073
Token dog
Token ID3290
Feature activation+3.68e+00

Pos logit contributions
 officer+0.046
 salon+0.038
 ma+0.038
iza+0.038
ily+0.036
Neg logit contributions
tails-0.062
Fel-0.062
Bet-0.060
 buzzing-0.059
 Louise-0.057
Token.
Token ID13
Feature activation-8.15e-02

Pos logit contributions
Fel+0.347
tails+0.345
Bet+0.336
 buzzing+0.319
June+0.317
Neg logit contributions
 officer-0.228
 ma-0.190
 salon-0.186
 sir-0.182
iza-0.176
Token Anna
Token ID11735
Feature activation+5.89e-01

Pos logit contributions
 officer+0.005
 salon+0.004
 ma+0.004
 accident+0.004
iza+0.004
Neg logit contributions
Fel-0.007
tails-0.007
Bet-0.007
June-0.007
 Louise-0.007
Token gave
Token ID2921
Feature activation-1.06e+00

Pos logit contributions
Fel+0.057
tails+0.056
Bet+0.055
June+0.052
 buzzing+0.052
Neg logit contributions
 officer-0.036
 ma-0.030
 salon-0.029
 sir-0.028
ily-0.028
Token Luna
Token ID23694
Feature activation+1.33e+01

Pos logit contributions
 officer+0.052
 kids+0.043
 Dad+0.042
ily+0.039
 dad+0.039
Neg logit contributions
Fel-0.117
Bet-0.116
tails-0.114
 buzzing-0.108
June-0.107
Token water
Token ID1660
Feature activation-5.78e-01

Pos logit contributions
Fel+1.347
tails+1.328
Bet+1.304
June+1.240
 buzzing+1.223
Neg logit contributions
 officer-0.754
 ma-0.600
 salon-0.582
 sir-0.580
ily-0.571
Token and
Token ID290
Feature activation-5.56e-02

Pos logit contributions
 officer+0.035
 ma+0.028
 salon+0.028
 sir+0.027
iza+0.026
Neg logit contributions
Fel-0.056
tails-0.056
Bet-0.054
 buzzing-0.052
June-0.051
Token food
Token ID2057
Feature activation+3.16e+00

Pos logit contributions
 officer+0.003
 ma+0.003
 kids+0.003
ily+0.003
 sir+0.003
Neg logit contributions
Fel-0.005
Bet-0.005
tails-0.005
June-0.005
 buzzing-0.005
Token,
Token ID11
Feature activation+3.34e-01

Pos logit contributions
tails+0.299
Fel+0.297
Bet+0.289
 buzzing+0.282
 Louise+0.270
Neg logit contributions
 officer-0.192
 ma-0.157
 salon-0.155
iza-0.149
 sir-0.147
Token but
Token ID475
Feature activation-3.01e-01

Pos logit contributions
Fel+0.035
tails+0.034
Bet+0.033
June+0.032
 buzzing+0.032
Neg logit contributions
 officer-0.018
 ma-0.014
 salon-0.014
 sir-0.014
ily-0.013
Token clay
Token ID21558
Feature activation+1.40e+00

Pos logit contributions
Fel+0.224
Bet+0.220
tails+0.218
June+0.209
 Louise+0.206
Neg logit contributions
 officer-0.098
 kids-0.078
 ma-0.073
 salon-0.073
 sir-0.070
Token balls
Token ID11333
Feature activation+2.56e+00

Pos logit contributions
Fel+0.136
tails+0.132
Bet+0.131
June+0.124
 buzzing+0.123
Neg logit contributions
 officer-0.086
 ma-0.069
 sir-0.069
 salon-0.068
 kids-0.067
Token together
Token ID1978
Feature activation+1.05e+00

Pos logit contributions
tails+0.193
Fel+0.187
Bet+0.184
ches+0.174
 buzzing+0.174
Neg logit contributions
 officer-0.189
 ma-0.168
iza-0.168
ateful-0.158
 salon-0.156
Token!"
Token ID2474
Feature activation+2.94e+00

Pos logit contributions
Fel+0.091
tails+0.090
Bet+0.088
June+0.083
 buzzing+0.082
Neg logit contributions
 officer-0.075
 ma-0.062
 salon-0.061
 sir-0.060
ily-0.059
Token But
Token ID887
Feature activation+1.86e-01

Pos logit contributions
Fel+0.256
tails+0.253
 buzzing+0.249
Bet+0.245
June+0.230
Neg logit contributions
 officer-0.208
 ma-0.174
 kids-0.171
 sir-0.167
 Dad-0.167
Token Luna
Token ID23694
Feature activation+1.33e+01

Pos logit contributions
Fel+0.016
Bet+0.015
 buzzing+0.015
tails+0.015
June+0.014
Neg logit contributions
 officer-0.013
 kids-0.011
 salon-0.011
 dad-0.011
 sir-0.011
Token ignored
Token ID9514
Feature activation-4.27e+00

Pos logit contributions
Fel+1.382
tails+1.360
Bet+1.330
 buzzing+1.268
June+1.261
Neg logit contributions
 officer-0.705
 ma-0.558
 salon-0.553
 sir-0.535
iza-0.512
Token Max
Token ID5436
Feature activation+4.80e+00

Pos logit contributions
 officer+0.179
 Dad+0.141
 kids+0.136
 dad+0.134
 Tommy+0.130
Neg logit contributions
Bet-0.483
tails-0.461
Fel-0.459
 buzzing-0.440
June-0.438
Token.
Token ID13
Feature activation+2.74e-02

Pos logit contributions
Fel+0.506
Bet+0.492
tails+0.490
June+0.466
 buzzing+0.455
Neg logit contributions
 officer-0.261
 ma-0.198
 salon-0.195
 sir-0.191
 kids-0.188
Token She
Token ID1375
Feature activation+8.56e-01

Pos logit contributions
tails+0.003
 buzzing+0.003
Fel+0.003
odic+0.003
 hovering+0.003
Neg logit contributions
 Dad-0.001
 officer-0.001
 ma-0.001
 kids-0.001
 Tom-0.001
Token did
Token ID750
Feature activation-3.34e+00

Pos logit contributions
Fel+0.092
tails+0.091
Bet+0.090
June+0.086
 buzzing+0.085
Neg logit contributions
 officer-0.044
 ma-0.033
 salon-0.032
ily-0.031
 kids-0.031
Token,
Token ID11
Feature activation+8.07e-02

Pos logit contributions
tails+0.262
Fel+0.261
Bet+0.253
 buzzing+0.240
 Louise+0.238
Neg logit contributions
 officer-0.182
 salon-0.147
 ma-0.146
 sir-0.142
iza-0.138
Token I
Token ID314
Feature activation-1.52e+00

Pos logit contributions
Fel+0.008
tails+0.007
Bet+0.007
 Louise+0.007
 buzzing+0.007
Neg logit contributions
 officer-0.005
 salon-0.004
ateful-0.004
 ma-0.004
ople-0.004
Token'm
Token ID1101
Feature activation+1.36e+00

Pos logit contributions
 officer+0.104
 ma+0.086
 salon+0.085
 sir+0.083
ily+0.079
Neg logit contributions
Fel-0.139
tails-0.136
Bet-0.133
 buzzing-0.125
June-0.124
Token sorry
Token ID7926
Feature activation-1.63e+00

Pos logit contributions
Fel+0.138
tails+0.137
Bet+0.134
June+0.127
 buzzing+0.126
Neg logit contributions
 officer-0.077
 ma-0.062
 salon-0.060
 sir-0.059
ily-0.057
Token,"
Token ID553
Feature activation-3.11e+00

Pos logit contributions
 officer+0.086
 ma+0.071
 sir+0.071
 kids+0.069
 Dad+0.066
Neg logit contributions
Fel-0.172
tails-0.170
Bet-0.168
June-0.161
 buzzing-0.155
Token Luna
Token ID23694
Feature activation+1.33e+01

Pos logit contributions
 officer+0.196
 salon+0.165
 ma+0.159
ople+0.151
 sir+0.149
Neg logit contributions
Fel-0.286
tails-0.283
Bet-0.278
 Louise-0.272
 buzzing-0.264
Token says
Token ID1139
Feature activation+2.36e+00

Pos logit contributions
Fel+1.186
tails+1.165
Bet+1.127
 Louise+1.098
 buzzing+1.088
Neg logit contributions
 officer-0.879
 salon-0.740
 ma-0.729
 sir-0.701
iza-0.688
Token.
Token ID13
Feature activation-3.67e-02

Pos logit contributions
tails+0.212
Fel+0.211
 buzzing+0.204
Bet+0.201
 Louise+0.199
Neg logit contributions
 officer-0.151
 salon-0.130
 ma-0.126
 sir-0.118
ople-0.118
Token "
Token ID366
Feature activation+3.05e-01

Pos logit contributions
 officer+0.001
 Dad+0.001
ily+0.001
 ma+0.001
 sir+0.001
Neg logit contributions
tails-0.004
Fel-0.004
eds-0.004
Bet-0.004
ches-0.004
TokenI
Token ID40
Feature activation-1.05e+00

Pos logit contributions
Fel+0.025
Bet+0.024
June+0.023
tails+0.023
 buzzing+0.022
Neg logit contributions
 officer-0.024
 ma-0.020
 sir-0.020
 salon-0.020
ople-0.019
Token was
Token ID373
Feature activation+1.85e+00

Pos logit contributions
 officer+0.064
 ma+0.054
 salon+0.053
 sir+0.052
 kids+0.049
Neg logit contributions
Fel-0.100
tails-0.098
Bet-0.097
 buzzing-0.091
June-0.091
Token "
Token ID366
Feature activation+3.13e-01

Pos logit contributions
tails+0.040
Fel+0.040
Bet+0.039
June+0.037
 Louise+0.036
Neg logit contributions
 officer-0.022
 ma-0.019
 sir-0.018
 salon-0.017
 Dad-0.017
TokenWe
Token ID1135
Feature activation+1.33e+00

Pos logit contributions
tails+0.030
Fel+0.029
Bet+0.028
 buzzing+0.027
 Louise+0.027
Neg logit contributions
 officer-0.019
 kids-0.015
 salon-0.015
 ma-0.015
ily-0.015
Token are
Token ID389
Feature activation-2.25e+00

Pos logit contributions
tails+0.127
Fel+0.127
Bet+0.122
 buzzing+0.116
June+0.116
Neg logit contributions
 officer-0.083
 ma-0.069
 salon-0.068
 sir-0.066
line-0.062
Token sorry
Token ID7926
Feature activation-1.93e+00

Pos logit contributions
 officer+0.128
 kids+0.109
 ma+0.106
 Dad+0.101
ily+0.101
Neg logit contributions
Fel-0.233
tails-0.225
Bet-0.225
June-0.211
 Louise-0.202
Token,
Token ID11
Feature activation+2.79e-01

Pos logit contributions
 officer+0.089
 kids+0.076
 sir+0.075
 Dad+0.072
 ma+0.072
Neg logit contributions
Fel-0.217
Bet-0.217
tails-0.213
June-0.206
 buzzing-0.197
Token Luna
Token ID23694
Feature activation+1.33e+01

Pos logit contributions
tails+0.018
Fel+0.017
Bet+0.016
itching+0.015
Mo+0.015
Neg logit contributions
 officer-0.027
 sir-0.026
 kids-0.026
 ma-0.025
 dad-0.024
Token.
Token ID13
Feature activation+1.67e-01

Pos logit contributions
Fel+1.448
tails+1.417
Bet+1.406
June+1.347
 buzzing+1.311
Neg logit contributions
 officer-0.658
 ma-0.522
 sir-0.501
 kids-0.492
ily-0.482
Token We
Token ID775
Feature activation+1.37e+00

Pos logit contributions
Fel+0.017
tails+0.017
Bet+0.017
 buzzing+0.016
 leaping+0.016
Neg logit contributions
 officer-0.008
 Dad-0.007
 sir-0.007
 ma-0.007
 kids-0.007
Token want
Token ID765
Feature activation-5.57e-01

Pos logit contributions
tails+0.128
Fel+0.125
Bet+0.121
 buzzing+0.116
June+0.113
Neg logit contributions
 officer-0.086
 ma-0.076
 salon-0.074
 sir-0.073
line-0.071
Token to
Token ID284
Feature activation-3.55e-01

Pos logit contributions
 officer+0.024
 Dad+0.019
 kids+0.019
 dad+0.018
 sir+0.018
Neg logit contributions
Fel-0.065
Bet-0.063
tails-0.063
June-0.059
 buzzing-0.058
Token be
Token ID307
Feature activation-1.65e+00

Pos logit contributions
 officer+0.024
 ma+0.020
 salon+0.019
 sir+0.019
ily+0.019
Neg logit contributions
tails-0.032
Fel-0.032
Bet-0.031
 buzzing-0.029
June-0.029
Token am
Token ID716
Feature activation+1.54e+00

Pos logit contributions
 officer+0.103
 kids+0.087
ily+0.085
iza+0.082
 salon+0.082
Neg logit contributions
Fel-0.145
Bet-0.144
tails-0.144
June-0.140
 Louise-0.138
Token Ben
Token ID3932
Feature activation+1.09e+00

Pos logit contributions
tails+0.160
Bet+0.159
Fel+0.157
June+0.148
 buzzing+0.146
Neg logit contributions
 officer-0.082
ily-0.068
 kids-0.067
 sir-0.066
 Dad-0.065
Token.
Token ID13
Feature activation+4.56e-03

Pos logit contributions
tails+0.109
Fel+0.106
Bet+0.104
 buzzing+0.100
June+0.099
Neg logit contributions
 officer-0.062
 salon-0.051
 ma-0.050
iza-0.047
 sir-0.047
Token This
Token ID770
Feature activation-8.51e-01

Pos logit contributions
Fel+0.000
tails+0.000
Bet+0.000
 buzzing+0.000
June+0.000
Neg logit contributions
 officer-0.000
 ma-0.000
 sir-0.000
 salon-0.000
ily-0.000
Token is
Token ID318
Feature activation+1.30e+00

Pos logit contributions
 officer+0.054
 kids+0.042
 boy+0.040
 sir+0.039
 ma+0.038
Neg logit contributions
Bet-0.085
Fel-0.084
tails-0.081
June-0.078
 Louise-0.076
Token Luna
Token ID23694
Feature activation+1.33e+01

Pos logit contributions
Fel+0.136
tails+0.135
Bet+0.134
June+0.125
 buzzing+0.122
Neg logit contributions
 officer-0.072
 ma-0.057
ily-0.056
 sir-0.056
 kids-0.056
Token.
Token ID13
Feature activation+1.25e-03

Pos logit contributions
Fel+1.471
Bet+1.440
tails+1.436
June+1.364
 buzzing+1.334
Neg logit contributions
 officer-0.643
 ma-0.485
 sir-0.465
 salon-0.462
 kids-0.458
Token She
Token ID1375
Feature activation+9.19e-01

Pos logit contributions
tails+0.000
Fel+0.000
Bet+0.000
 buzzing+0.000
June+0.000
Neg logit contributions
 officer-0.000
 ma-0.000
ily-0.000
 sir-0.000
 Dad-0.000
Token is
Token ID318
Feature activation+1.32e+00

Pos logit contributions
Fel+0.086
Bet+0.085
tails+0.083
June+0.079
 buzzing+0.077
Neg logit contributions
 officer-0.061
 ma-0.049
 kids-0.048
 salon-0.047
 sir-0.047
Token my
Token ID616
Feature activation+8.35e-01

Pos logit contributions
Fel+0.134
Bet+0.131
tails+0.129
June+0.121
 webs+0.115
Neg logit contributions
 officer-0.076
 kids-0.064
ily-0.063
 ma-0.062
 dad-0.059
Token puppy
Token ID26188
Feature activation+1.72e+00

Pos logit contributions
Fel+0.082
Bet+0.081
tails+0.080
June+0.075
 buzzing+0.074
Neg logit contributions
 officer-0.053
 kids-0.042
 sir-0.041
 ma-0.040
 salon-0.040
Token,
Token ID11
Feature activation+1.67e-01

Pos logit contributions
Fel+0.002
tails+0.002
Bet+0.002
 Louise+0.002
 buzzing+0.002
Neg logit contributions
 officer-0.002
 salon-0.002
iza-0.002
 ma-0.002
ateful-0.002
Token please
Token ID3387
Feature activation-1.57e+00

Pos logit contributions
Fel+0.018
tails+0.017
Bet+0.017
 buzzing+0.016
 Louise+0.016
Neg logit contributions
 officer-0.009
 salon-0.007
 ma-0.007
 sir-0.006
iza-0.006
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
 officer+0.083
 ma+0.065
 sir+0.062
 salon+0.062
ily+0.060
Neg logit contributions
Fel-0.167
tails-0.164
Bet-0.162
June-0.154
 buzzing-0.152
Token Max
Token ID5436
Feature activation+4.83e+00

Pos logit contributions
 officer+0.001
 sir+0.001
 ma+0.001
ily+0.001
 Dad+0.001
Neg logit contributions
Fel-0.002
tails-0.002
Bet-0.002
 buzzing-0.001
June-0.001
Token and
Token ID290
Feature activation-9.00e-02

Pos logit contributions
Fel+0.434
tails+0.427
Bet+0.421
June+0.396
 buzzing+0.391
Neg logit contributions
 officer-0.330
 ma-0.274
 salon-0.267
 sir-0.265
ily-0.259
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
 officer+0.006
 ma+0.005
 kids+0.005
 sir+0.005
ily+0.004
Neg logit contributions
Bet-0.009
tails-0.009
Fel-0.008
 buzzing-0.008
June-0.008
Token can
Token ID460
Feature activation+4.49e-01

Pos logit contributions
tails+1.282
Fel+1.278
Bet+1.213
 buzzing+1.188
 Louise+1.154
Neg logit contributions
 officer-0.779
 salon-0.633
 ma-0.625
 sir-0.617
iza-0.595
Token be
Token ID307
Feature activation-1.77e+00

Pos logit contributions
Fel+0.043
tails+0.042
Bet+0.041
June+0.039
 buzzing+0.039
Neg logit contributions
 officer-0.029
 ma-0.023
 salon-0.023
 sir-0.022
ily-0.022
Token friends
Token ID2460
Feature activation+2.40e+00

Pos logit contributions
 officer+0.099
 kids+0.082
ily+0.078
 ma+0.074
 dad+0.073
Neg logit contributions
Fel-0.185
Bet-0.178
tails-0.175
June-0.166
 Louise-0.162
Token too
Token ID1165
Feature activation-1.77e-01

Pos logit contributions
tails+0.228
Fel+0.227
Bet+0.217
 buzzing+0.214
June+0.209
Neg logit contributions
 officer-0.144
 ma-0.122
 salon-0.117
iza-0.114
 sir-0.113
Token,"
Token ID553
Feature activation-3.21e+00

Pos logit contributions
 officer+0.009
 ma+0.007
 sir+0.006
 salon+0.006
 kids+0.006
Neg logit contributions
Fel-0.020
tails-0.019
Bet-0.019
June-0.018
 buzzing-0.018
Token was
Token ID373
Feature activation+1.43e+00

Pos logit contributions
 officer+0.290
 ma+0.242
 salon+0.237
 sir+0.234
ily+0.229
Neg logit contributions
Fel-0.372
tails-0.367
Bet-0.358
June-0.338
 buzzing-0.335
Token a
Token ID257
Feature activation-3.80e-01

Pos logit contributions
Fel+0.147
tails+0.146
Bet+0.141
June+0.134
 buzzing+0.133
Neg logit contributions
 officer-0.080
 ma-0.064
 salon-0.061
ily-0.061
 sir-0.060
Token little
Token ID1310
Feature activation-2.30e+00

Pos logit contributions
 officer+0.020
 ma+0.016
 sir+0.015
 boy+0.015
 kids+0.015
Neg logit contributions
tails-0.042
Fel-0.042
Bet-0.040
June-0.039
 Louise-0.038
Token girl
Token ID2576
Feature activation-1.73e+00

Pos logit contributions
 officer+0.095
 ma+0.069
 salon+0.066
 sir+0.064
ily+0.061
Neg logit contributions
Fel-0.269
tails-0.266
Bet-0.261
June-0.250
 buzzing-0.249
Token named
Token ID3706
Feature activation+3.17e+00

Pos logit contributions
 officer+0.110
 salon+0.088
 ma+0.087
 kids+0.086
ily+0.085
Neg logit contributions
Fel-0.169
Bet-0.159
tails-0.158
June-0.150
 Louise-0.146
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
Fel+0.328
tails+0.324
Bet+0.315
 buzzing+0.301
June+0.298
Neg logit contributions
 officer-0.175
 ma-0.141
 salon-0.136
ily-0.135
 sir-0.133
Token.
Token ID13
Feature activation-4.82e-01

Pos logit contributions
Fel+1.347
tails+1.338
Bet+1.306
June+1.243
 buzzing+1.242
Neg logit contributions
 officer-0.733
 ma-0.591
 salon-0.585
 sir-0.565
iza-0.534
Token She
Token ID1375
Feature activation+6.91e-01

Pos logit contributions
ily+0.034
 ma+0.031
 kids+0.030
 Sara+0.030
 Tom+0.030
Neg logit contributions
odic-0.035
tails-0.034
itching-0.033
 hovering-0.033
 buzzing-0.033
Token was
Token ID373
Feature activation+1.38e+00

Pos logit contributions
Fel+0.072
tails+0.071
Bet+0.069
June+0.066
 buzzing+0.065
Neg logit contributions
 officer-0.037
 ma-0.029
ily-0.028
 salon-0.028
 kids-0.027
Token only
Token ID691
Feature activation-3.08e+00

Pos logit contributions
Fel+0.150
tails+0.145
Bet+0.142
June+0.135
ches+0.131
Neg logit contributions
 officer-0.069
 ma-0.056
 kids-0.055
 salon-0.054
ily-0.054
Token three
Token ID1115
Feature activation-5.22e+00

Pos logit contributions
 officer+0.101
 ma+0.066
 salon+0.063
 sir+0.060
ily+0.056
Neg logit contributions
Fel-0.387
tails-0.382
Bet-0.377
June-0.361
 buzzing-0.358
Token You
Token ID921
Feature activation-2.80e-01

Pos logit contributions
tails+0.001
Fel+0.001
Bet+0.001
 buzzing+0.001
June+0.001
Neg logit contributions
 officer-0.000
 ma-0.000
ily-0.000
 sir-0.000
 kids-0.000
Token are
Token ID389
Feature activation-2.41e+00

Pos logit contributions
 officer+0.016
 salon+0.013
 ma+0.013
 sir+0.012
iza+0.012
Neg logit contributions
Fel-0.028
tails-0.028
Bet-0.027
 buzzing-0.026
June-0.026
Token good
Token ID922
Feature activation+5.71e-02

Pos logit contributions
 officer+0.136
 ma+0.114
 kids+0.112
ily+0.110
 sir+0.107
Neg logit contributions
Fel-0.246
tails-0.239
Bet-0.237
June-0.221
 buzzing-0.217
Token friends
Token ID2460
Feature activation+2.50e+00

Pos logit contributions
tails+0.006
Fel+0.005
Bet+0.005
 buzzing+0.005
 Louise+0.005
Neg logit contributions
 officer-0.003
 salon-0.003
 ma-0.003
iza-0.003
line-0.003
Token to
Token ID284
Feature activation-3.51e-01

Pos logit contributions
Fel+0.230
tails+0.228
Bet+0.220
 buzzing+0.215
 Louise+0.214
Neg logit contributions
 officer-0.155
 salon-0.134
 ma-0.129
iza-0.122
 sir-0.119
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
 officer+0.017
 kids+0.015
 ma+0.014
 Dad+0.013
 dad+0.013
Neg logit contributions
Fel-0.037
tails-0.035
Bet-0.035
June-0.034
 buzzing-0.033
Token.
Token ID13
Feature activation+1.48e-02

Pos logit contributions
tails+1.272
Fel+1.266
Bet+1.209
 buzzing+1.179
 Louise+1.171
Neg logit contributions
 officer-0.773
 ma-0.629
 salon-0.604
iza-0.596
 sir-0.590
Token I
Token ID314
Feature activation-1.52e+00

Pos logit contributions
tails+0.002
Fel+0.002
Bet+0.001
 buzzing+0.001
June+0.001
Neg logit contributions
 officer-0.001
ily-0.001
 ma-0.001
 Dad-0.001
 sir-0.001
Token am
Token ID716
Feature activation+1.58e+00

Pos logit contributions
 officer+0.102
 ma+0.083
 salon+0.081
 sir+0.080
ily+0.080
Neg logit contributions
Fel-0.139
tails-0.137
Bet-0.135
June-0.128
 Louise-0.125
Token proud
Token ID6613
Feature activation+7.69e-01

Pos logit contributions
Fel+0.155
tails+0.152
Bet+0.148
June+0.140
 Louise+0.137
Neg logit contributions
 officer-0.097
 ma-0.080
 sir-0.077
 salon-0.077
ily-0.076
Token of
Token ID286
Feature activation+6.78e-01

Pos logit contributions
Fel+0.071
tails+0.069
Bet+0.069
 buzzing+0.067
 Louise+0.066
Neg logit contributions
 officer-0.049
 salon-0.040
 ma-0.039
 sir-0.038
iza-0.038
Token mist
Token ID4020
Feature activation+2.91e+00

Pos logit contributions
Fel+0.027
tails+0.027
Bet+0.026
 buzzing+0.025
June+0.024
Neg logit contributions
 officer-0.020
 ma-0.017
 salon-0.017
ily-0.016
 sir-0.016
Token to
Token ID284
Feature activation-2.70e-01

Pos logit contributions
tails+0.269
Fel+0.264
Bet+0.260
 buzzing+0.248
 Louise+0.245
Neg logit contributions
 officer-0.185
 ma-0.153
 salon-0.147
 sir-0.143
ily-0.143
Token go
Token ID467
Feature activation+6.12e-01

Pos logit contributions
 officer+0.019
 salon+0.016
ily+0.015
ople+0.015
 salesman+0.015
Neg logit contributions
Bet-0.023
tails-0.023
Fel-0.023
 buzzing-0.022
 Louise-0.021
Token away
Token ID1497
Feature activation-1.40e-01

Pos logit contributions
tails+0.050
Fel+0.049
Bet+0.048
 buzzing+0.045
June+0.045
Neg logit contributions
 officer-0.044
 ma-0.040
 salon-0.039
 sir-0.038
ily-0.038
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
 officer+0.009
 salon+0.007
 ma+0.007
 sir+0.007
iza+0.007
Neg logit contributions
tails-0.013
Fel-0.013
Bet-0.013
 buzzing-0.013
 Louise-0.012
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
 officer+0.008
 ma+0.007
 sir+0.006
 salon+0.006
ily+0.006
Neg logit contributions
Fel-0.010
tails-0.010
Bet-0.010
 buzzing-0.009
June-0.009
Token knew
Token ID2993
Feature activation+9.15e-01

Pos logit contributions
Fel+1.239
tails+1.222
Bet+1.191
 buzzing+1.138
 Louise+1.126
Neg logit contributions
 officer-0.832
 ma-0.686
 salon-0.676
 sir-0.676
iza-0.638
Token something
Token ID1223
Feature activation-4.75e-01

Pos logit contributions
Fel+0.093
tails+0.092
Bet+0.090
June+0.085
 buzzing+0.084
Neg logit contributions
 officer-0.051
ily-0.041
 ma-0.040
 salon-0.039
 sir-0.039
Token good
Token ID922
Feature activation+2.31e-01

Pos logit contributions
 officer+0.029
 ma+0.024
ily+0.024
 kids+0.023
 accident+0.023
Neg logit contributions
tails-0.046
Fel-0.046
Bet-0.044
June-0.042
 Louise-0.040
Token would
Token ID561
Feature activation+2.77e+00

Pos logit contributions
Fel+0.019
tails+0.019
Bet+0.019
 Louise+0.018
 buzzing+0.018
Neg logit contributions
 officer-0.016
 salon-0.014
 ma-0.014
 sir-0.013
iza-0.013
Token come
Token ID1282
Feature activation-9.15e-02

Pos logit contributions
tails+0.237
Fel+0.235
Bet+0.234
 buzzing+0.226
June+0.219
Neg logit contributions
 officer-0.193
 salon-0.166
 ma-0.160
 sir-0.158
iza-0.153
Token to
Token ID284
Feature activation-4.47e-01

Pos logit contributions
Fel+0.159
Bet+0.151
tails+0.148
June+0.144
 Louise+0.140
Neg logit contributions
 officer-0.086
 kids-0.070
 ma-0.069
 salon-0.068
 sir-0.067
Token the
Token ID262
Feature activation+6.70e-02

Pos logit contributions
 officer+0.015
 kids+0.013
 dad+0.012
 Dad+0.012
 salon+0.011
Neg logit contributions
Fel-0.054
tails-0.052
Bet-0.052
ches-0.049
June-0.049
Token tree
Token ID5509
Feature activation+1.61e+00

Pos logit contributions
Fel+0.006
tails+0.006
Bet+0.006
June+0.005
 Louise+0.005
Neg logit contributions
 officer-0.005
 ma-0.004
 salon-0.004
 kids-0.004
 sir-0.004
Token.
Token ID13
Feature activation-3.70e-01

Pos logit contributions
Fel+0.177
tails+0.172
Bet+0.169
June+0.162
 buzzing+0.160
Neg logit contributions
 officer-0.079
 ma-0.060
 salon-0.060
 sir-0.058
ily-0.056
Token But
Token ID887
Feature activation+2.63e-01

Pos logit contributions
ily+0.029
 Dad+0.027
 Tom+0.027
 Sara+0.027
 kids+0.027
Neg logit contributions
odic-0.024
eds-0.024
 leaping-0.023
 hovering-0.023
tails-0.023
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
Bet+0.018
oing+0.018
tails+0.018
Fel+0.018
pill+0.017
Neg logit contributions
ily-0.021
 officer-0.019
 kids-0.019
 did-0.019
 first-0.018
Token does
Token ID857
Feature activation+1.12e+00

Pos logit contributions
Fel+1.289
Bet+1.282
tails+1.275
June+1.220
 Louise+1.153
Neg logit contributions
 officer-0.782
 ma-0.649
 salon-0.630
 kids-0.628
 sir-0.615
Token not
Token ID407
Feature activation-1.01e+00

Pos logit contributions
Fel+0.126
tails+0.125
Bet+0.123
June+0.118
 Louise+0.115
Neg logit contributions
 officer-0.051
 ma-0.039
 salon-0.037
 sir-0.037
ily-0.035
Token want
Token ID765
Feature activation-5.63e-01

Pos logit contributions
 officer+0.064
 salon+0.058
ople+0.056
 cash+0.054
 cubes+0.054
Neg logit contributions
tails-0.091
 buzzing-0.088
Bet-0.088
Fel-0.087
 Louise-0.086
Token to
Token ID284
Feature activation-4.34e-01

Pos logit contributions
ily+0.014
 officer+0.014
 kids+0.012
 Dad+0.012
 dad+0.010
Neg logit contributions
Fel-0.072
Bet-0.071
tails-0.070
oing-0.067
oc-0.066
Token see
Token ID766
Feature activation+2.20e+00

Pos logit contributions
 officer+0.029
 salon+0.024
isher+0.024
 ma+0.024
iza+0.023
Neg logit contributions
tails-0.040
Bet-0.038
Fel-0.037
 buzzing-0.036
 Louise-0.034
Token
Token ID198
Feature activation+5.55e-01

Pos logit contributions
ily+0.017
 Dad+0.014
 kids+0.014
 Sara+0.014
 Tom+0.014
Neg logit contributions
tails-0.032
Fel-0.030
odic-0.030
 buzzing-0.030
 leaping-0.030
Token
Token ID198
Feature activation+5.45e-01

Pos logit contributions
tails+0.068
Fel+0.062
 buzzing+0.061
 webs+0.060
Bet+0.060
Neg logit contributions
ily-0.020
 officer-0.015
 Dad-0.014
 kids-0.013
 ma-0.012
Token"
Token ID1
Feature activation+9.81e-01

Pos logit contributions
tails+0.051
 tal+0.046
Fel+0.045
 buzzing+0.045
 webs+0.044
Neg logit contributions
ily-0.032
 kids-0.025
Dad-0.024
 ma-0.024
 officer-0.024
TokenLook
Token ID8567
Feature activation+3.27e-01

Pos logit contributions
tails+0.088
Fel+0.079
 Louise+0.076
 buzzing+0.075
Bet+0.074
Neg logit contributions
 officer-0.065
ily-0.061
 kids-0.055
 boy-0.053
 salon-0.053
Token,
Token ID11
Feature activation+2.69e-02

Pos logit contributions
Bet+0.039
Fel+0.038
tails+0.038
June+0.038
 buzzing+0.036
Neg logit contributions
 kids-0.010
ily-0.010
 Dad-0.010
 dad-0.009
 officer-0.009
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
Fel+0.002
tails+0.002
Bet+0.002
June+0.002
itching+0.002
Neg logit contributions
 officer-0.002
 kids-0.002
ily-0.002
 sir-0.002
 ma-0.002
Token,
Token ID11
Feature activation+4.54e-02

Pos logit contributions
Fel+1.199
Bet+1.134
tails+1.129
June+1.113
 buzzing+1.025
Neg logit contributions
 officer-0.878
 ma-0.798
 sir-0.769
 kids-0.755
ily-0.747
Token birds
Token ID10087
Feature activation+1.22e+00

Pos logit contributions
Fel+0.005
tails+0.004
Bet+0.004
 buzzing+0.004
 Louise+0.004
Neg logit contributions
 officer-0.003
 salon-0.002
 ma-0.002
iza-0.002
 sir-0.002
Token!"
Token ID2474
Feature activation+2.97e+00

Pos logit contributions
Fel+0.106
tails+0.101
Bet+0.100
June+0.096
 Louise+0.093
Neg logit contributions
 officer-0.088
 ma-0.076
 kids-0.073
 sir-0.073
 salon-0.073
Token Mia
Token ID32189
Feature activation+5.56e+00

Pos logit contributions
Fel+0.290
tails+0.290
Bet+0.277
 leaping+0.271
eds+0.269
Neg logit contributions
ily-0.157
 officer-0.154
 kids-0.148
 Dad-0.136
 ma-0.132
Token says
Token ID1139
Feature activation+2.39e+00

Pos logit contributions
Bet+0.548
Fel+0.546
tails+0.535
June+0.510
 buzzing+0.486
Neg logit contributions
 officer-0.341
 ma-0.274
 kids-0.274
 sir-0.269
 salon-0.266
Token lady
Token ID10846
Feature activation-3.11e+00

Pos logit contributions
 officer+0.002
 ma+0.002
 salon+0.002
 sir+0.002
ily+0.002
Neg logit contributions
Fel-0.003
tails-0.003
Bet-0.003
 buzzing-0.003
June-0.003
Token to
Token ID284
Feature activation-4.41e-01

Pos logit contributions
 officer+0.189
 ma+0.156
 salon+0.151
 sir+0.147
 accident+0.143
Neg logit contributions
tails-0.300
Fel-0.296
Bet-0.289
June-0.274
 buzzing-0.274
Token come
Token ID1282
Feature activation-2.66e-01

Pos logit contributions
 officer+0.029
 salon+0.023
 ma+0.023
 sir+0.023
ily+0.022
Neg logit contributions
tails-0.041
Fel-0.041
Bet-0.040
 buzzing-0.037
June-0.037
Token and
Token ID290
Feature activation-1.41e-01

Pos logit contributions
 officer+0.012
 ma+0.009
 sir+0.009
ily+0.008
 Dad+0.008
Neg logit contributions
Fel-0.030
tails-0.029
Bet-0.029
June-0.028
 buzzing-0.027
Token take
Token ID1011
Feature activation-5.53e-01

Pos logit contributions
 officer+0.009
 ma+0.007
 salon+0.007
 sir+0.007
 kids+0.006
Neg logit contributions
Fel-0.014
tails-0.014
Bet-0.013
June-0.013
 buzzing-0.013
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
 officer+0.025
 kids+0.024
ily+0.023
 Dad+0.023
 dad+0.021
Neg logit contributions
Bet-0.060
Fel-0.058
 buzzing-0.055
tails-0.055
ousy-0.054
Token home
Token ID1363
Feature activation-1.68e+00

Pos logit contributions
Fel+1.327
tails+1.307
Bet+1.284
June+1.218
 buzzing+1.208
Neg logit contributions
 officer-0.761
 ma-0.607
 salon-0.595
 sir-0.584
ily-0.567
Token.
Token ID13
Feature activation-8.20e-02

Pos logit contributions
 officer+0.121
 ma+0.106
 salon+0.099
 sir+0.099
ople+0.098
Neg logit contributions
tails-0.142
Fel-0.131
 buzzing-0.130
Bet-0.130
 Louise-0.123
Token They
Token ID1119
Feature activation+1.04e+00

Pos logit contributions
 Dad+0.003
 officer+0.003
 ma+0.003
 dad+0.002
ily+0.002
Neg logit contributions
tails-0.010
Fel-0.009
Bet-0.009
 buzzing-0.009
 leaping-0.009
Token are
Token ID389
Feature activation-2.43e+00

Pos logit contributions
Fel+0.097
tails+0.097
Bet+0.094
 buzzing+0.089
 Louise+0.088
Neg logit contributions
 officer-0.065
 ma-0.053
 salon-0.053
 sir-0.052
ily-0.051
Token glad
Token ID9675
Feature activation+1.41e+00

Pos logit contributions
 officer+0.137
 ma+0.116
 kids+0.111
ily+0.110
 sir+0.107
Neg logit contributions
Fel-0.250
tails-0.242
Bet-0.239
June-0.226
 Louise-0.218
Token They
Token ID1119
Feature activation+1.09e+00

Pos logit contributions
tails+0.008
Fel+0.008
 buzzing+0.008
Bet+0.007
 leaping+0.007
Neg logit contributions
 officer-0.003
 Dad-0.003
 ma-0.003
 kids-0.003
 sir-0.003
Token jog
Token ID48342
Feature activation-7.63e-01

Pos logit contributions
Fel+0.101
tails+0.100
Bet+0.096
 buzzing+0.091
June+0.091
Neg logit contributions
 officer-0.071
 ma-0.058
 salon-0.058
 sir-0.057
ily-0.056
Token with
Token ID351
Feature activation-5.23e-02

Pos logit contributions
 officer+0.052
 ma+0.046
 sir+0.044
 salon+0.043
 accident+0.043
Neg logit contributions
Fel-0.067
tails-0.066
Bet-0.062
 buzzing-0.060
June-0.060
Token Rex
Token ID17853
Feature activation+7.54e+00

Pos logit contributions
 officer+0.003
 kids+0.003
 dad+0.002
 Dad+0.002
ily+0.002
Neg logit contributions
Fel-0.005
Bet-0.005
tails-0.005
oing-0.005
June-0.005
Token.
Token ID13
Feature activation+9.52e-02

Pos logit contributions
Fel+0.789
tails+0.780
Bet+0.765
June+0.728
 buzzing+0.723
Neg logit contributions
 officer-0.403
 ma-0.317
 salon-0.308
 sir-0.302
ily-0.292
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
tails+0.010
 buzzing+0.010
Fel+0.010
Bet+0.010
 leaping+0.009
Neg logit contributions
 officer-0.004
 Dad-0.004
 ma-0.004
 kids-0.003
ily-0.003
Token waves
Token ID9813
Feature activation-6.65e-01

Pos logit contributions
Fel+1.108
tails+1.092
Bet+1.061
June+0.998
 buzzing+0.993
Neg logit contributions
 officer-0.972
 ma-0.821
 salon-0.806
 sir-0.797
ily-0.779
Token to
Token ID284
Feature activation-3.30e-01

Pos logit contributions
 officer+0.038
 ma+0.030
 salon+0.029
 sir+0.029
 kids+0.029
Neg logit contributions
Fel-0.067
tails-0.066
Bet-0.065
June-0.062
 buzzing-0.061
Token them
Token ID606
Feature activation-5.29e-01

Pos logit contributions
 officer+0.018
 kids+0.015
 dad+0.014
ily+0.013
 Dad+0.013
Neg logit contributions
Fel-0.033
tails-0.032
Bet-0.032
oing-0.030
June-0.030
Token.
Token ID13
Feature activation+1.01e-01

Pos logit contributions
 officer+0.030
 ma+0.025
 sir+0.024
 salon+0.024
iza+0.023
Neg logit contributions
Fel-0.053
tails-0.053
Bet-0.050
 buzzing-0.049
June-0.048
Token She
Token ID1375
Feature activation+9.55e-01

Pos logit contributions
tails+0.011
 buzzing+0.011
Fel+0.011
itching+0.011
Bet+0.011
Neg logit contributions
 officer-0.004
 Dad-0.004
ily-0.003
 ma-0.003
 Tommy-0.003
Token say
Token ID910
Feature activation+1.60e+00

Pos logit contributions
Fel+0.100
tails+0.099
Bet+0.097
 buzzing+0.091
June+0.091
Neg logit contributions
 officer-0.060
 ma-0.048
 salon-0.047
 sir-0.046
ily-0.045
Token,
Token ID11
Feature activation+1.90e-01

Pos logit contributions
Fel+0.156
tails+0.154
Bet+0.150
June+0.142
 buzzing+0.142
Neg logit contributions
 officer-0.098
 ma-0.080
 salon-0.079
 sir-0.077
ily-0.074
Token "
Token ID366
Feature activation+2.12e-01

Pos logit contributions
tails+0.020
Fel+0.019
Bet+0.018
June+0.018
 webs+0.017
Neg logit contributions
 officer-0.011
 ma-0.009
 sir-0.008
 Dad-0.008
 kids-0.008
TokenHello
Token ID15496
Feature activation-3.12e+00

Pos logit contributions
tails+0.022
Fel+0.022
Bet+0.020
 Louise+0.020
 webs+0.020
Neg logit contributions
 officer-0.012
ily-0.009
 ma-0.009
 kids-0.009
 boy-0.009
Token,
Token ID11
Feature activation+1.96e-01

Pos logit contributions
 kids+0.100
 sir+0.084
 Dad+0.081
 boy+0.079
 ma+0.077
Neg logit contributions
Bet-0.388
tails-0.383
June-0.377
Fel-0.374
 buzzing-0.355
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
tails+0.017
Bet+0.016
Fel+0.016
June+0.015
itching+0.015
Neg logit contributions
 kids-0.014
 officer-0.014
 ma-0.013
 sir-0.013
ily-0.013
Token.
Token ID13
Feature activation-3.14e-02

Pos logit contributions
Fel+1.494
tails+1.470
Bet+1.454
June+1.407
 buzzing+1.349
Neg logit contributions
 officer-0.589
 ma-0.458
 sir-0.448
 kids-0.444
ily-0.435
Token We
Token ID775
Feature activation+1.35e+00

Pos logit contributions
 officer+0.002
 ma+0.001
ily+0.001
 kids+0.001
 sir+0.001
Neg logit contributions
tails-0.003
Fel-0.003
Bet-0.003
 buzzing-0.003
June-0.003
Token are
Token ID389
Feature activation-2.46e+00

Pos logit contributions
Fel+0.137
tails+0.136
Bet+0.133
June+0.126
 buzzing+0.125
Neg logit contributions
 officer-0.077
 ma-0.061
 salon-0.060
 sir-0.059
ily-0.056
Token happy
Token ID3772
Feature activation-5.21e-01

Pos logit contributions
 officer+0.119
 kids+0.114
ily+0.107
 ma+0.101
 Dad+0.101
Neg logit contributions
Fel-0.267
tails-0.257
Bet-0.255
June-0.240
ches-0.233
Token to
Token ID284
Feature activation-4.06e-01

Pos logit contributions
 officer+0.029
 ma+0.023
 salon+0.022
 sir+0.022
ily+0.021
Neg logit contributions
Fel-0.054
tails-0.053
Bet-0.052
June-0.050
 buzzing-0.049
Token birds
Token ID10087
Feature activation+1.20e+00

Pos logit contributions
Fel+0.003
tails+0.003
Bet+0.003
June+0.003
 Louise+0.003
Neg logit contributions
 officer-0.003
 ma-0.002
 kids-0.002
 salon-0.002
 sir-0.002
Token.
Token ID13
Feature activation-3.79e-01

Pos logit contributions
Fel+0.140
Bet+0.133
tails+0.131
June+0.128
Lou+0.123
Neg logit contributions
 officer-0.052
 ma-0.039
 kids-0.039
 sir-0.038
 salon-0.038
Token She
Token ID1375
Feature activation+7.55e-01

Pos logit contributions
 kids+0.028
ily+0.028
 officer+0.028
 Dad+0.026
 boy+0.026
Neg logit contributions
Fel-0.027
odic-0.026
 leaping-0.026
Bet-0.026
 buzzing-0.026
Token picks
Token ID11103
Feature activation-9.44e-01

Pos logit contributions
Bet+0.070
tails+0.070
Fel+0.070
June+0.066
 buzzing+0.063
Neg logit contributions
 officer-0.049
 ma-0.041
 kids-0.040
 salon-0.040
 sir-0.039
Token up
Token ID510
Feature activation+2.03e+00

Pos logit contributions
 kids+0.030
ily+0.029
 officer+0.029
 right+0.027
 Dad+0.025
Neg logit contributions
Fel-0.110
Bet-0.109
tails-0.108
elope-0.105
June-0.102
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
Fel+0.228
Bet+0.227
tails+0.222
June+0.214
elope+0.209
Neg logit contributions
 officer-0.077
 kids-0.072
ily-0.066
 Dad-0.064
 dad-0.060
Token and
Token ID290
Feature activation-3.70e-01

Pos logit contributions
Fel+1.507
Bet+1.493
tails+1.468
June+1.417
Lou+1.335
Neg logit contributions
 officer-0.560
 ma-0.414
 kids-0.408
 salon-0.405
 sir-0.389
Token carries
Token ID10732
Feature activation+2.93e+00

Pos logit contributions
 officer+0.020
 kids+0.017
 dad+0.017
 Dad+0.016
 ma+0.016
Neg logit contributions
Bet-0.039
Fel-0.037
June-0.036
tails-0.035
 buzzing-0.034
Token her
Token ID607
Feature activation+1.54e+00

Pos logit contributions
Bet+0.252
oing+0.243
Fel+0.242
itching+0.239
odic+0.239
Neg logit contributions
ily-0.181
 officer-0.170
 kids-0.168
 Dad-0.158
 Tom-0.156
Token to
Token ID284
Feature activation-4.47e-01

Pos logit contributions
Fel+0.159
Bet+0.151
tails+0.148
June+0.144
 Louise+0.140
Neg logit contributions
 officer-0.086
 kids-0.070
 ma-0.069
 salon-0.068
 sir-0.067
Token the
Token ID262
Feature activation+6.70e-02

Pos logit contributions
 officer+0.015
 kids+0.013
 dad+0.012
 Dad+0.012
 salon+0.011
Neg logit contributions
Fel-0.054
tails-0.052
Bet-0.052
ches-0.049
June-0.049
Token.
Token ID13
Feature activation-3.97e-01

Pos logit contributions
Fel+0.141
Bet+0.134
June+0.130
tails+0.130
 Louise+0.125
Neg logit contributions
 officer-0.050
 kids-0.039
 salon-0.036
 accident-0.036
 ma-0.035
Token She
Token ID1375
Feature activation+7.41e-01

Pos logit contributions
 officer+0.024
 kids+0.023
ily+0.023
 Dad+0.022
 ma+0.022
Neg logit contributions
Fel-0.035
tails-0.034
Bet-0.033
June-0.033
odic-0.033
Token wants
Token ID3382
Feature activation+6.97e-01

Pos logit contributions
Bet+0.076
Fel+0.076
tails+0.076
June+0.071
 buzzing+0.068
Neg logit contributions
 officer-0.040
 kids-0.033
 ma-0.033
 salon-0.031
ily-0.031
Token to
Token ID284
Feature activation-4.53e-01

Pos logit contributions
Fel+0.090
tails+0.085
Bet+0.084
oc+0.082
elope+0.082
Neg logit contributions
 officer-0.018
 kids-0.017
 Dad-0.016
 dad-0.015
ily-0.014
Token show
Token ID905
Feature activation+2.19e+00

Pos logit contributions
 officer+0.026
 ma+0.022
 kids+0.021
 salon+0.021
 sir+0.021
Neg logit contributions
Fel-0.046
tails-0.044
Bet-0.043
June-0.042
 Louise-0.040
Token Luna
Token ID23694
Feature activation+1.32e+01

Pos logit contributions
Bet+0.171
Fel+0.166
oing+0.161
odic+0.156
oc+0.156
Neg logit contributions
 officer-0.163
 kids-0.160
ily-0.156
 dad-0.152
 Dad-0.152
Token the
Token ID262
Feature activation+3.67e-02

Pos logit contributions
Fel+1.449
Bet+1.432
tails+1.415
June+1.358
 buzzing+1.293
Neg logit contributions
 officer-0.598
ily-0.477
 kids-0.476
 ma-0.463
 salon-0.453
Token birds
Token ID10087
Feature activation+1.20e+00

Pos logit contributions
Fel+0.003
tails+0.003
Bet+0.003
June+0.003
 Louise+0.003
Neg logit contributions
 officer-0.003
 ma-0.002
 kids-0.002
 salon-0.002
 sir-0.002
Token.
Token ID13
Feature activation-3.79e-01

Pos logit contributions
Fel+0.140
Bet+0.133
tails+0.131
June+0.128
Lou+0.123
Neg logit contributions
 officer-0.052
 ma-0.039
 kids-0.039
 sir-0.038
 salon-0.038
Token She
Token ID1375
Feature activation+7.55e-01

Pos logit contributions
 kids+0.028
ily+0.028
 officer+0.028
 Dad+0.026
 boy+0.026
Neg logit contributions
Fel-0.027
odic-0.026
 leaping-0.026
Bet-0.026
 buzzing-0.026
Token picks
Token ID11103
Feature activation-9.44e-01

Pos logit contributions
Bet+0.070
tails+0.070
Fel+0.070
June+0.066
 buzzing+0.063
Neg logit contributions
 officer-0.049
 ma-0.041
 kids-0.040
 salon-0.040
 sir-0.039
Token had
Token ID550
Feature activation+6.69e-03

Pos logit contributions
Fel+0.064
tails+0.064
Bet+0.062
June+0.059
 Louise+0.058
Neg logit contributions
 officer-0.034
 ma-0.027
 salon-0.026
 kids-0.025
 sir-0.025
Token done
Token ID1760
Feature activation-4.08e+00

Pos logit contributions
Fel+0.001
tails+0.001
Bet+0.001
 buzzing+0.001
June+0.001
Neg logit contributions
 officer-0.000
 sir-0.000
 ma-0.000
 salon-0.000
ily-0.000
Token it
Token ID340
Feature activation+9.14e-01

Pos logit contributions
 officer+0.224
 ma+0.188
 salon+0.185
 kids+0.180
 accident+0.178
Neg logit contributions
Fel-0.407
tails-0.405
Bet-0.402
June-0.378
 Louise-0.361
Token!
Token ID0
Feature activation+5.68e+00

Pos logit contributions
Fel+0.077
tails+0.076
Bet+0.075
June+0.069
 buzzing+0.068
Neg logit contributions
 officer-0.067
 ma-0.057
 salon-0.056
 sir-0.055
ily-0.055
Token Ag
Token ID2449
Feature activation-3.97e+00

Pos logit contributions
Fel+0.482
tails+0.477
Bet+0.463
June+0.435
 buzzing+0.434
Neg logit contributions
 officer-0.416
 ma-0.351
 salon-0.343
 sir-0.339
ily-0.335
Tokennes
Token ID2516
Feature activation-1.08e+01

Pos logit contributions
 officer+0.159
 ma+0.129
 sir+0.125
 Dad+0.116
 kids+0.113
Neg logit contributions
Fel-0.472
tails-0.457
Bet-0.445
June-0.438
 buzzing-0.421
Token skipped
Token ID26684
Feature activation+1.28e-01

Pos logit contributions
 officer+0.781
 ma+0.660
 sir+0.654
 salon+0.637
 kids+0.612
Neg logit contributions
tails-0.924
Fel-0.908
Bet-0.876
 buzzing-0.845
June-0.830
Token home
Token ID1363
Feature activation-1.81e+00

Pos logit contributions
Fel+0.012
tails+0.012
Bet+0.012
June+0.011
 buzzing+0.011
Neg logit contributions
 officer-0.008
 ma-0.007
 salon-0.007
ily-0.007
 kids-0.006
Token,
Token ID11
Feature activation-1.87e-01

Pos logit contributions
 officer+0.122
 ma+0.099
 sir+0.098
 salon+0.097
ily+0.096
Neg logit contributions
tails-0.164
Fel-0.163
Bet-0.156
 buzzing-0.154
 Louise-0.149
Token full
Token ID1336
Feature activation+1.28e+00

Pos logit contributions
 officer+0.011
 ma+0.009
 salon+0.009
 sir+0.009
 kids+0.009
Neg logit contributions
Fel-0.018
tails-0.018
Bet-0.018
June-0.017
 buzzing-0.016
Token of
Token ID286
Feature activation+3.14e-01

Pos logit contributions
Fel+0.115
tails+0.114
Bet+0.113
 buzzing+0.111
 Louise+0.107
Neg logit contributions
 officer-0.084
 salon-0.066
 sir-0.065
 ma-0.065
ople-0.063
Token.
Token ID13
Feature activation-6.08e-01

Pos logit contributions
Fel+0.022
tails+0.022
Bet+0.021
June+0.020
 buzzing+0.020
Neg logit contributions
 officer-0.010
 ma-0.008
 salon-0.008
 sir-0.007
ily-0.007
Token Tim
Token ID5045
Feature activation-1.15e+00

Pos logit contributions
 officer+0.032
 ma+0.025
 sir+0.024
 salon+0.024
ily+0.023
Neg logit contributions
Fel-0.065
tails-0.064
Bet-0.062
June-0.060
 buzzing-0.059
Tokenmy
Token ID1820
Feature activation+2.36e-01

Pos logit contributions
 officer+0.084
 salon+0.073
 sir+0.072
 ma+0.072
iza+0.067
Neg logit contributions
tails-0.097
Fel-0.095
Bet-0.095
June-0.090
 buzzing-0.088
Token loved
Token ID6151
Feature activation-3.88e-01

Pos logit contributions
Fel+0.022
tails+0.022
Bet+0.021
June+0.020
 buzzing+0.020
Neg logit contributions
 officer-0.015
 ma-0.013
 salon-0.012
 sir-0.012
ily-0.012
Token Wed
Token ID3300
Feature activation-1.80e+00

Pos logit contributions
 officer+0.022
 ma+0.018
 salon+0.017
 sir+0.017
 kids+0.017
Neg logit contributions
Fel-0.039
tails-0.039
Bet-0.038
June-0.036
 buzzing-0.036
Tokennes
Token ID2516
Feature activation-1.07e+01

Pos logit contributions
 kids+0.100
 ma+0.098
 Dad+0.096
 officer+0.096
 boy+0.091
Neg logit contributions
Fel-0.164
tails-0.161
Bet-0.161
June-0.156
 buzzing-0.145
Tokendays
Token ID12545
Feature activation-3.02e+00

Pos logit contributions
 officer+0.742
 ma+0.662
 sir+0.622
 salon+0.588
 kids+0.567
Neg logit contributions
tails-0.960
Fel-0.925
Bet-0.920
 buzzing-0.880
June-0.862
Token because
Token ID780
Feature activation+6.23e-01

Pos logit contributions
 officer+0.212
 ma+0.191
 sir+0.185
iza+0.180
 salon+0.176
Neg logit contributions
tails-0.249
Fel-0.247
Bet-0.227
 buzzing-0.224
June-0.216
Token that
Token ID326
Feature activation-5.31e-01

Pos logit contributions
Fel+0.052
tails+0.049
 Felix+0.048
Bet+0.047
 buzzing+0.046
Neg logit contributions
 officer-0.042
 ma-0.037
 sir-0.035
iza-0.035
 salon-0.035
Token was
Token ID373
Feature activation+1.31e+00

Pos logit contributions
 officer+0.035
iza+0.032
ople+0.031
 sir+0.030
ily+0.030
Neg logit contributions
Fel-0.046
tails-0.045
 buzzing-0.042
Bet-0.041
 Felix-0.040
Token the
Token ID262
Feature activation-2.94e-01

Pos logit contributions
Fel+0.107
tails+0.106
Bet+0.103
 buzzing+0.101
June+0.096
Neg logit contributions
 officer-0.095
ople-0.081
 ma-0.080
 sir-0.080
 salon-0.078
Token always
Token ID1464
Feature activation-2.74e+00

Pos logit contributions
 officer+0.114
 kids+0.100
 ma+0.096
 Dad+0.095
 dad+0.092
Neg logit contributions
Fel-0.245
Bet-0.235
tails-0.231
June-0.221
ches-0.212
Token so
Token ID523
Feature activation-2.14e-01

Pos logit contributions
 officer+0.169
 kids+0.145
 ma+0.143
 Dad+0.137
iza+0.134
Neg logit contributions
Fel-0.264
Bet-0.253
tails-0.252
June-0.236
ches-0.228
Token happy
Token ID3772
Feature activation-5.52e-01

Pos logit contributions
 officer+0.015
 salon+0.013
 ma+0.012
 sir+0.012
ily+0.012
Neg logit contributions
Fel-0.019
tails-0.018
Bet-0.018
 buzzing-0.017
June-0.017
Token on
Token ID319
Feature activation+2.36e+00

Pos logit contributions
 officer+0.030
 kids+0.025
 ma+0.024
 sir+0.023
 Dad+0.023
Neg logit contributions
Fel-0.057
tails-0.056
Bet-0.056
June-0.053
 Louise-0.051
Token Wed
Token ID3300
Feature activation-1.71e+00

Pos logit contributions
Fel+0.247
tails+0.245
Bet+0.244
June+0.232
 webs+0.225
Neg logit contributions
 officer-0.115
 Dad-0.100
 ma-0.098
 kids-0.098
 dad-0.095
Tokennes
Token ID2516
Feature activation-1.07e+01

Pos logit contributions
 officer+0.080
 kids+0.069
 ma+0.066
 Dad+0.063
 boy+0.063
Neg logit contributions
tails-0.183
Fel-0.183
Bet-0.180
June-0.176
 buzzing-0.169
Tokendays
Token ID12545
Feature activation-3.04e+00

Pos logit contributions
 officer+0.581
 salon+0.453
ily+0.450
 ma+0.447
iza+0.442
Neg logit contributions
Fel-1.118
Bet-1.067
tails-1.062
June-1.005
 buzzing-0.994
Token because
Token ID780
Feature activation+6.35e-01

Pos logit contributions
 officer+0.196
 ma+0.170
 salon+0.164
 sir+0.163
iza+0.159
Neg logit contributions
tails-0.274
Fel-0.270
Bet-0.254
 buzzing-0.249
June-0.245
Token of
Token ID286
Feature activation+3.31e-01

Pos logit contributions
Fel+0.059
tails+0.058
Bet+0.057
June+0.054
 buzzing+0.053
Neg logit contributions
 officer-0.042
 ma-0.034
 salon-0.034
 sir-0.033
ily-0.032
Token their
Token ID511
Feature activation+4.94e-01

Pos logit contributions
Fel+0.034
tails+0.034
Bet+0.033
June+0.031
 Louise+0.030
Neg logit contributions
 officer-0.018
 kids-0.015
 ma-0.015
 Dad-0.014
 salon-0.014
Token lucky
Token ID9670
Feature activation+1.01e+00

Pos logit contributions
Fel+0.043
tails+0.043
Bet+0.041
 buzzing+0.039
June+0.039
Neg logit contributions
 officer-0.035
 ma-0.029
 salon-0.029
 sir-0.028
ily-0.028
Token over
Token ID625
Feature activation+1.56e+00

Pos logit contributions
 officer+0.246
 sir+0.216
 ma+0.207
 salon+0.204
 cash+0.201
Neg logit contributions
tails-0.249
 buzzing-0.247
Bet-0.244
Fel-0.242
June-0.231
Token the
Token ID262
Feature activation-1.49e-01

Pos logit contributions
Fel+0.140
tails+0.137
Bet+0.137
 buzzing+0.129
June+0.128
Neg logit contributions
 officer-0.105
 ma-0.087
 sir-0.085
 salon-0.082
ily-0.079
Token place
Token ID1295
Feature activation+5.44e-01

Pos logit contributions
 officer+0.009
 sir+0.008
 ma+0.008
iza+0.008
ateful+0.008
Neg logit contributions
Fel-0.013
tails-0.013
 buzzing-0.013
Bet-0.012
 webs-0.012
Token.
Token ID13
Feature activation-4.99e-01

Pos logit contributions
tails+0.049
Fel+0.046
Bet+0.046
 buzzing+0.046
 Louise+0.044
Neg logit contributions
 officer-0.036
 ma-0.030
 sir-0.028
 salon-0.027
iza-0.027
Token Ag
Token ID2449
Feature activation-3.99e+00

Pos logit contributions
 officer+0.041
 sir+0.035
 ma+0.035
 accident+0.035
 salon+0.035
Neg logit contributions
Fel-0.037
Bet-0.036
tails-0.035
 Louise-0.033
June-0.033
Tokennes
Token ID2516
Feature activation-1.07e+01

Pos logit contributions
 officer+0.176
 ma+0.158
 sir+0.156
 Dad+0.154
 kids+0.144
Neg logit contributions
Fel-0.449
tails-0.427
Bet-0.421
June-0.417
ches-0.405
Token said
Token ID531
Feature activation-6.33e-01

Pos logit contributions
 officer+0.789
 ma+0.697
 sir+0.691
 salon+0.654
 cash+0.638
Neg logit contributions
tails-0.880
Fel-0.839
Bet-0.826
 buzzing-0.803
 Louise-0.778
Token,
Token ID11
Feature activation-3.14e-01

Pos logit contributions
 officer+0.045
ople+0.040
 salon+0.038
 ma+0.038
ateful+0.038
Neg logit contributions
Fel-0.053
tails-0.051
Bet-0.049
 buzzing-0.048
 Louise-0.048
Token
Token ID6184
Feature activation-4.20e-01

Pos logit contributions
 officer+0.025
 salon+0.023
ople+0.023
ateful+0.022
 cubes+0.022
Neg logit contributions
Fel-0.024
Bet-0.022
tails-0.022
 Louise-0.021
 buzzing-0.021
Token
Token ID95
Feature activation-2.82e+00

Pos logit contributions
 officer+0.033
 cubes+0.029
 kids+0.029
 ma+0.028
 dad+0.027
Neg logit contributions
Fel-0.035
tails-0.030
Bet-0.029
 buzzing-0.028
 Louise-0.027
Token
Token ID26391
Feature activation-2.87e+00

Pos logit contributions
 officer+0.217
 cubes+0.200
 sir+0.192
 dad+0.191
 Dad+0.187
Neg logit contributions
Fel-0.229
Bet-0.204
tails-0.203
June-0.202
 Louise-0.193
Token was
Token ID373
Feature activation+1.29e+00

Pos logit contributions
 officer+0.344
 ma+0.276
 salon+0.269
 sir+0.265
ily+0.256
Neg logit contributions
Fel-0.594
tails-0.587
Bet-0.574
June-0.545
 buzzing-0.542
Token always
Token ID1464
Feature activation-2.87e+00

Pos logit contributions
Fel+0.115
tails+0.114
Bet+0.111
June+0.104
 buzzing+0.103
Neg logit contributions
 officer-0.089
 ma-0.075
 salon-0.074
 sir-0.072
ily-0.071
Token excited
Token ID6568
Feature activation-4.63e-01

Pos logit contributions
 officer+0.203
 ma+0.169
 salon+0.166
 sir+0.164
ily+0.160
Neg logit contributions
Fel-0.250
tails-0.247
Bet-0.240
 buzzing-0.228
June-0.226
Token for
Token ID329
Feature activation+1.71e+00

Pos logit contributions
 officer+0.030
 ma+0.025
 salon+0.025
 sir+0.024
iza+0.024
Neg logit contributions
tails-0.042
Fel-0.042
Bet-0.040
 buzzing-0.040
 Louise-0.039
Token Wed
Token ID3300
Feature activation-1.69e+00

Pos logit contributions
Fel+0.155
tails+0.153
Bet+0.145
 buzzing+0.144
 Louise+0.143
Neg logit contributions
 officer-0.115
 salon-0.095
 sir-0.094
 ma-0.093
ily-0.087
Tokennes
Token ID2516
Feature activation-1.07e+01

Pos logit contributions
 officer+0.095
 kids+0.094
 boy+0.087
 ma+0.084
 knee+0.082
Neg logit contributions
Fel-0.158
Bet-0.156
June-0.153
tails-0.151
 buzzing-0.143
Tokendays
Token ID12545
Feature activation-3.02e+00

Pos logit contributions
 officer+0.616
 ma+0.492
 salon+0.482
 sir+0.473
ily+0.459
Neg logit contributions
Fel-1.070
tails-1.055
Bet-1.033
June-0.982
 buzzing-0.975
Token because
Token ID780
Feature activation+5.70e-01

Pos logit contributions
 officer+0.204
 ma+0.183
ily+0.176
iza+0.175
 salon+0.174
Neg logit contributions
tails-0.250
Fel-0.246
Bet-0.226
 Louise-0.220
 buzzing-0.220
Token it
Token ID340
Feature activation+8.57e-01

Pos logit contributions
Fel+0.052
tails+0.049
 Felix+0.047
Bet+0.047
 Louise+0.047
Neg logit contributions
 officer-0.037
 ma-0.031
 salon-0.030
 sir-0.029
iza-0.028
Token was
Token ID373
Feature activation+1.31e+00

Pos logit contributions
Fel+0.077
tails+0.077
Bet+0.075
June+0.070
 buzzing+0.069
Neg logit contributions
 officer-0.058
 ma-0.048
 salon-0.047
 sir-0.046
 kids-0.045
Token the
Token ID262
Feature activation-2.14e-01

Pos logit contributions
Fel+0.126
tails+0.124
Bet+0.122
June+0.115
 buzzing+0.115
Neg logit contributions
 officer-0.081
 ma-0.066
 salon-0.065
 sir-0.064
ily-0.062
Token.
Token ID13
Feature activation-5.84e-01

Pos logit contributions
Fel+0.021
tails+0.021
Bet+0.021
June+0.020
 Louise+0.020
Neg logit contributions
 officer-0.009
 ma-0.007
 salon-0.007
 sir-0.007
ily-0.007
Token Tim
Token ID5045
Feature activation-1.13e+00

Pos logit contributions
 officer+0.031
 ma+0.024
 sir+0.023
 salon+0.023
ily+0.022
Neg logit contributions
Fel-0.062
tails-0.061
Bet-0.060
June-0.057
 buzzing-0.057
Tokenmy
Token ID1820
Feature activation+2.29e-01

Pos logit contributions
 officer+0.080
 sir+0.070
 salon+0.070
 ma+0.069
iza+0.064
Neg logit contributions
tails-0.098
Fel-0.095
Bet-0.095
June-0.090
 buzzing-0.089
Token loved
Token ID6151
Feature activation-4.57e-01

Pos logit contributions
Fel+0.021
tails+0.021
Bet+0.020
June+0.019
 buzzing+0.019
Neg logit contributions
 officer-0.015
 ma-0.012
 salon-0.012
 sir-0.012
iza-0.011
Token Wed
Token ID3300
Feature activation-1.73e+00

Pos logit contributions
 officer+0.026
 ma+0.021
 salon+0.020
 sir+0.020
ily+0.020
Neg logit contributions
Fel-0.046
tails-0.046
Bet-0.045
June-0.042
 buzzing-0.042
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 ma+0.093
 officer+0.093
 kids+0.092
 Dad+0.088
 sir+0.084
Neg logit contributions
tails-0.162
Fel-0.161
Bet-0.159
June-0.154
 buzzing-0.145
Tokendays
Token ID12545
Feature activation-2.98e+00

Pos logit contributions
 officer+0.713
 ma+0.624
 sir+0.591
 salon+0.566
 kids+0.541
Neg logit contributions
tails-0.970
Fel-0.941
Bet-0.935
 buzzing-0.893
June-0.878
Token because
Token ID780
Feature activation+6.18e-01

Pos logit contributions
 officer+0.203
 ma+0.182
 sir+0.176
iza+0.169
 salon+0.167
Neg logit contributions
tails-0.255
Fel-0.253
Bet-0.234
 buzzing-0.232
June-0.224
Token that
Token ID326
Feature activation-6.06e-01

Pos logit contributions
Fel+0.053
tails+0.049
 Felix+0.048
Bet+0.047
 buzzing+0.047
Neg logit contributions
 officer-0.042
 ma-0.036
 sir-0.035
 salon-0.035
iza-0.034
Token was
Token ID373
Feature activation+1.24e+00

Pos logit contributions
 officer+0.040
iza+0.035
ople+0.034
 sir+0.034
 salon+0.033
Neg logit contributions
Fel-0.054
tails-0.053
 buzzing-0.050
Bet-0.050
June-0.047
Token the
Token ID262
Feature activation-3.16e-01

Pos logit contributions
Fel+0.102
tails+0.101
Bet+0.099
 buzzing+0.097
June+0.092
Neg logit contributions
 officer-0.089
ople-0.075
 ma-0.075
 sir-0.075
 salon-0.073
Token
Token ID198
Feature activation+6.36e-01

Pos logit contributions
tails+0.531
Fel+0.528
Bet+0.498
 buzzing+0.489
June+0.470
Neg logit contributions
 officer-0.405
 ma-0.343
 sir-0.331
 salon-0.325
ily-0.322
Token
Token ID198
Feature activation+6.24e-01

Pos logit contributions
tails+0.066
Fel+0.060
 buzzing+0.058
Bet+0.057
 webs+0.057
Neg logit contributions
 officer-0.034
ily-0.031
 ma-0.027
iza-0.026
 kids-0.026
TokenSo
Token ID2396
Feature activation+5.93e-01

Pos logit contributions
tails+0.058
Fel+0.051
 buzzing+0.051
 webs+0.051
 Louise+0.049
Neg logit contributions
 officer-0.040
ily-0.036
 ma-0.034
iza-0.033
 salon-0.033
Token,
Token ID11
Feature activation-2.23e-01

Pos logit contributions
Fel+0.055
tails+0.054
Bet+0.053
June+0.050
 buzzing+0.050
Neg logit contributions
 officer-0.039
 ma-0.032
 salon-0.031
 sir-0.031
 kids-0.030
Token Ag
Token ID2449
Feature activation-3.90e+00

Pos logit contributions
 officer+0.014
 ma+0.012
 salon+0.011
 kids+0.011
 sir+0.011
Neg logit contributions
Fel-0.021
tails-0.021
Bet-0.020
June-0.019
 buzzing-0.019
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.185
 ma+0.154
 sir+0.144
 kids+0.143
 salon+0.139
Neg logit contributions
Fel-0.428
tails-0.420
Bet-0.415
June-0.401
 Louise-0.385
Token resisted
Token ID26643
Feature activation-1.54e+00

Pos logit contributions
 officer+0.687
 ma+0.584
 sir+0.563
 salon+0.558
ily+0.535
Neg logit contributions
tails-0.993
Fel-0.957
Bet-0.941
 buzzing-0.898
June-0.887
Token and
Token ID290
Feature activation-5.14e-01

Pos logit contributions
 officer+0.099
 ma+0.080
 salon+0.079
 sir+0.078
ily+0.076
Neg logit contributions
Fel-0.145
tails-0.144
Bet-0.140
 buzzing-0.133
June-0.133
Token eventually
Token ID4191
Feature activation+2.73e+00

Pos logit contributions
 officer+0.034
 ma+0.028
 salon+0.027
 sir+0.027
ily+0.026
Neg logit contributions
Fel-0.047
tails-0.047
Bet-0.046
 buzzing-0.043
June-0.043
Token the
Token ID262
Feature activation-2.14e-01

Pos logit contributions
Fel+0.246
tails+0.246
Bet+0.240
 buzzing+0.226
 Louise+0.226
Neg logit contributions
 officer-0.184
 salon-0.150
 ma-0.149
 sir-0.149
 kids-0.141
Token wall
Token ID3355
Feature activation-2.35e+00

Pos logit contributions
 officer+0.013
 ma+0.011
 salon+0.011
 sir+0.011
iza+0.011
Neg logit contributions
Fel-0.020
tails-0.020
Bet-0.019
 buzzing-0.018
June-0.018
Tokenaches
Token ID3694
Feature activation-3.77e+00

Pos logit contributions
 officer+0.134
 ma+0.106
 sir+0.102
 salon+0.100
 accident+0.097
Neg logit contributions
tails-0.206
Fel-0.201
Bet-0.194
 buzzing-0.190
June-0.183
Token on
Token ID319
Feature activation+2.31e+00

Pos logit contributions
 officer+0.272
 ma+0.216
 salon+0.213
 accident+0.209
 sir+0.203
Neg logit contributions
tails-0.322
Fel-0.315
Bet-0.309
 buzzing-0.297
 Louise-0.296
Token Mondays
Token ID49748
Feature activation-1.07e+00

Pos logit contributions
Fel+0.222
tails+0.220
Bet+0.215
June+0.203
 buzzing+0.202
Neg logit contributions
 officer-0.142
 ma-0.116
 salon-0.113
 sir-0.111
ily-0.108
Token,
Token ID11
Feature activation-3.63e-01

Pos logit contributions
 officer+0.068
 ma+0.053
ily+0.053
 salon+0.051
iza+0.051
Neg logit contributions
tails-0.101
Fel-0.098
Bet-0.095
 buzzing-0.091
 Louise-0.091
Token Wed
Token ID3300
Feature activation-1.79e+00

Pos logit contributions
 officer+0.021
 ma+0.016
 salon+0.016
 sir+0.016
ily+0.015
Neg logit contributions
Fel-0.037
tails-0.036
Bet-0.035
June-0.034
 buzzing-0.033
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.090
 cubes+0.089
 kids+0.088
 boy+0.081
 knee+0.080
Neg logit contributions
Bet-0.168
Fel-0.166
June-0.166
tails-0.165
 Louise-0.155
Tokendays
Token ID12545
Feature activation-3.05e+00

Pos logit contributions
 officer+0.703
 ma+0.588
 sir+0.560
 salon+0.549
 kids+0.543
Neg logit contributions
tails-0.982
Fel-0.964
Bet-0.947
June-0.893
 buzzing-0.890
Token,
Token ID11
Feature activation-3.50e-01

Pos logit contributions
 officer+0.217
 ma+0.176
 sir+0.171
 salon+0.170
iza+0.168
Neg logit contributions
tails-0.262
Fel-0.261
Bet-0.249
 buzzing-0.238
June-0.236
Token and
Token ID290
Feature activation-5.29e-01

Pos logit contributions
 officer+0.019
 ma+0.016
 salon+0.015
 sir+0.015
 kids+0.014
Neg logit contributions
Fel-0.036
tails-0.036
Bet-0.035
June-0.033
 buzzing-0.033
Token Fridays
Token ID45011
Feature activation+2.48e-01

Pos logit contributions
 officer+0.028
 ma+0.023
 sir+0.022
 salon+0.022
 kids+0.022
Neg logit contributions
Fel-0.056
tails-0.054
Bet-0.054
June-0.051
 buzzing-0.050
Token."
Token ID526
Feature activation-2.27e+00

Pos logit contributions
Fel+0.026
Bet+0.026
tails+0.025
June+0.024
 buzzing+0.024
Neg logit contributions
 officer-0.013
 ma-0.011
 salon-0.010
 sir-0.010
 kids-0.010
Token a
Token ID257
Feature activation-2.31e-01

Pos logit contributions
Fel+0.194
Bet+0.187
tails+0.186
June+0.177
 buzzing+0.171
Neg logit contributions
 officer-0.124
 ma-0.102
 sir-0.099
 kids-0.097
ily-0.096
Token special
Token ID2041
Feature activation+4.45e-01

Pos logit contributions
 officer+0.015
 ma+0.013
 salon+0.012
 sir+0.012
 kids+0.012
Neg logit contributions
Fel-0.021
tails-0.021
Bet-0.021
June-0.020
 Louise-0.019
Token hat
Token ID6877
Feature activation+1.55e+00

Pos logit contributions
tails+0.040
Fel+0.040
Bet+0.038
 buzzing+0.037
 Louise+0.036
Neg logit contributions
 officer-0.029
 ma-0.024
 salon-0.024
 sir-0.023
ily-0.023
Token for
Token ID329
Feature activation+1.70e+00

Pos logit contributions
tails+0.145
Fel+0.140
Bet+0.135
 buzzing+0.132
 Louise+0.129
Neg logit contributions
 officer-0.094
 ma-0.081
 salon-0.078
iza-0.077
 sir-0.075
Token Wed
Token ID3300
Feature activation-1.76e+00

Pos logit contributions
Fel+0.161
tails+0.160
Bet+0.155
June+0.148
 buzzing+0.147
Neg logit contributions
 officer-0.106
 ma-0.086
 salon-0.085
 sir-0.083
ily-0.081
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.093
 kids+0.092
 boy+0.090
 Dad+0.085
 ma+0.082
Neg logit contributions
Fel-0.166
Bet-0.162
tails-0.162
June-0.160
ches-0.156
Tokendays
Token ID12545
Feature activation-3.00e+00

Pos logit contributions
 officer+0.709
 ma+0.606
 salon+0.579
 sir+0.569
 kids+0.543
Neg logit contributions
tails-0.970
Fel-0.947
Bet-0.930
June-0.878
 buzzing-0.875
Token."
Token ID526
Feature activation-2.15e+00

Pos logit contributions
 officer+0.193
 ma+0.166
 salon+0.161
iza+0.159
 cash+0.153
Neg logit contributions
tails-0.268
Fel-0.253
Bet-0.236
 buzzing-0.236
 Louise-0.234
Token
Token ID198
Feature activation+3.30e-01

Pos logit contributions
 officer+0.155
 ma+0.130
 salon+0.127
 sir+0.126
ily+0.123
Neg logit contributions
Fel-0.186
tails-0.184
Bet-0.179
 buzzing-0.168
June-0.168
Token
Token ID198
Feature activation+3.34e-01

Pos logit contributions
tails+0.033
Fel+0.032
Bet+0.032
 buzzing+0.030
 Louise+0.030
Neg logit contributions
 officer-0.020
ily-0.016
 ma-0.015
 kids-0.015
 salon-0.014
TokenL
Token ID43
Feature activation-3.02e+00

Pos logit contributions
tails+0.034
Fel+0.034
Bet+0.033
 buzzing+0.031
June+0.031
Neg logit contributions
 officer-0.019
 ma-0.015
 salon-0.015
 sir-0.014
ily-0.014
Token's
Token ID338
Feature activation+2.00e+00

Pos logit contributions
Fel+0.299
tails+0.295
Bet+0.289
June+0.273
 buzzing+0.270
Neg logit contributions
 officer-0.212
 ma-0.176
 salon-0.171
 sir-0.170
ily-0.165
Token so
Token ID523
Feature activation-2.04e-01

Pos logit contributions
tails+0.174
Fel+0.171
 buzzing+0.160
Bet+0.159
 Louise+0.157
Neg logit contributions
 officer-0.139
 ma-0.120
 salon-0.117
 sir-0.113
ople-0.113
Token special
Token ID2041
Feature activation+4.59e-01

Pos logit contributions
 officer+0.015
 ma+0.012
 salon+0.012
 sir+0.012
ily+0.011
Neg logit contributions
Fel-0.018
tails-0.017
Bet-0.017
 buzzing-0.016
June-0.016
Token about
Token ID546
Feature activation-2.59e+00

Pos logit contributions
tails+0.048
Fel+0.048
Bet+0.046
 buzzing+0.046
 Louise+0.045
Neg logit contributions
 officer-0.023
 ma-0.018
 salon-0.018
iza-0.017
ily-0.016
Token Wed
Token ID3300
Feature activation-1.74e+00

Pos logit contributions
 officer+0.142
 kids+0.120
 Dad+0.117
 dad+0.115
 sir+0.115
Neg logit contributions
Fel-0.266
Bet-0.262
tails-0.253
June-0.244
elope-0.228
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.094
 kids+0.084
 boy+0.083
 Dad+0.080
 knee+0.079
Neg logit contributions
Fel-0.170
Bet-0.169
tails-0.167
June-0.165
 buzzing-0.158
Tokendays
Token ID12545
Feature activation-2.99e+00

Pos logit contributions
 officer+0.607
 ma+0.490
 salon+0.470
 sir+0.459
ily+0.437
Neg logit contributions
tails-1.066
Fel-1.059
Bet-1.036
June-0.986
 buzzing-0.985
Token?"
Token ID1701
Feature activation-2.75e+00

Pos logit contributions
 officer+0.181
 cash+0.152
iza+0.149
ateful+0.144
 knee+0.143
Neg logit contributions
tails-0.258
Fel-0.249
 buzzing-0.238
 Louise-0.237
 June-0.235
Token
Token ID198
Feature activation+3.17e-01

Pos logit contributions
 officer+0.186
 ma+0.151
 sir+0.146
 salon+0.146
 kids+0.144
Neg logit contributions
tails-0.250
Fel-0.248
Bet-0.242
 buzzing-0.231
June-0.224
Token
Token ID198
Feature activation+3.14e-01

Pos logit contributions
tails+0.031
Bet+0.030
Fel+0.030
 buzzing+0.029
 Louise+0.028
Neg logit contributions
 officer-0.019
 ma-0.015
ily-0.015
 kids-0.015
 sir-0.014
TokenMax
Token ID11518
Feature activation+3.81e+00

Pos logit contributions
tails+0.025
Bet+0.024
Fel+0.024
 buzzing+0.023
 Louise+0.023
Neg logit contributions
 officer-0.025
 ma-0.020
 salon-0.020
 sir-0.019
 kids-0.019
Token Lily
Token ID20037
Feature activation-1.88e+00

Pos logit contributions
Fel+0.366
tails+0.362
Bet+0.361
June+0.344
 Louise+0.342
Neg logit contributions
 officer-0.172
 ma-0.126
 sir-0.126
 salon-0.124
iza-0.116
Token.
Token ID13
Feature activation-5.07e-01

Pos logit contributions
 officer+0.097
 ma+0.076
 salon+0.074
 sir+0.072
ily+0.069
Neg logit contributions
Fel-0.200
tails-0.198
Bet-0.194
June-0.185
 buzzing-0.184
Token She
Token ID1375
Feature activation+5.54e-01

Pos logit contributions
 officer+0.041
 sir+0.035
iza+0.034
 salon+0.034
 ma+0.034
Neg logit contributions
Fel-0.040
Bet-0.038
tails-0.038
June-0.036
 Louise-0.036
Token loved
Token ID6151
Feature activation-2.75e-01

Pos logit contributions
Fel+0.053
tails+0.053
Bet+0.051
June+0.049
 buzzing+0.049
Neg logit contributions
 officer-0.035
 ma-0.028
 salon-0.028
 sir-0.027
ily-0.026
Token Wed
Token ID3300
Feature activation-1.65e+00

Pos logit contributions
 officer+0.014
 salon+0.011
 kids+0.011
 ma+0.011
 Dad+0.011
Neg logit contributions
Fel-0.029
tails-0.028
Bet-0.028
June-0.027
 Louise-0.026
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.081
 kids+0.077
 ma+0.076
 Dad+0.074
 sir+0.070
Neg logit contributions
Bet-0.168
tails-0.168
Fel-0.164
June-0.162
 buzzing-0.154
Tokendays
Token ID12545
Feature activation-2.92e+00

Pos logit contributions
 officer+0.689
 ma+0.587
 sir+0.557
 salon+0.537
 kids+0.523
Neg logit contributions
tails-0.989
Fel-0.971
Bet-0.965
 buzzing-0.913
June-0.908
Token because
Token ID780
Feature activation+7.22e-01

Pos logit contributions
 officer+0.193
 ma+0.165
 sir+0.160
 salon+0.153
iza+0.152
Neg logit contributions
tails-0.261
Fel-0.261
Bet-0.249
 buzzing-0.240
June-0.237
Token that
Token ID326
Feature activation-4.21e-01

Pos logit contributions
Fel+0.060
tails+0.058
Bet+0.056
June+0.054
 buzzing+0.054
Neg logit contributions
 officer-0.053
 ma-0.045
 sir-0.044
 salon-0.042
iza-0.042
Token's
Token ID338
Feature activation+1.98e+00

Pos logit contributions
 officer+0.029
 sir+0.025
 ma+0.024
iza+0.024
 salon+0.024
Neg logit contributions
Fel-0.036
tails-0.036
Bet-0.035
 buzzing-0.033
June-0.033
Token when
Token ID618
Feature activation+2.16e+00

Pos logit contributions
tails+0.159
Fel+0.158
Bet+0.153
 buzzing+0.150
June+0.144
Neg logit contributions
 officer-0.150
ople-0.126
 ma-0.122
 sir-0.121
iza-0.120
Token
Token ID198
Feature activation+3.39e-01

Pos logit contributions
tails+0.032
Fel+0.032
Bet+0.030
 buzzing+0.029
 Louise+0.029
Neg logit contributions
 officer-0.025
 ma-0.021
 salon-0.020
ily-0.020
 sir-0.020
TokenOne
Token ID3198
Feature activation-1.87e-01

Pos logit contributions
tails+0.028
Fel+0.028
Bet+0.027
 buzzing+0.026
June+0.025
Neg logit contributions
 officer-0.025
 ma-0.021
 salon-0.021
 sir-0.020
ily-0.020
Token day
Token ID1110
Feature activation+5.07e-01

Pos logit contributions
 officer+0.013
 ma+0.011
 salon+0.011
 sir+0.011
ople+0.010
Neg logit contributions
Fel-0.016
tails-0.016
Bet-0.015
 buzzing-0.015
 Louise-0.015
Token,
Token ID11
Feature activation-2.35e-01

Pos logit contributions
Fel+0.048
tails+0.046
Bet+0.045
 Louise+0.043
 buzzing+0.043
Neg logit contributions
 officer-0.033
 ma-0.027
 salon-0.027
 sir-0.026
 accident-0.025
Token Ag
Token ID2449
Feature activation-3.94e+00

Pos logit contributions
 officer+0.015
 ma+0.012
 salon+0.012
 sir+0.012
ily+0.011
Neg logit contributions
Fel-0.022
tails-0.022
Bet-0.021
June-0.020
 Louise-0.020
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.218
 ma+0.192
 kids+0.184
 sir+0.183
 Dad+0.178
Neg logit contributions
Fel-0.394
tails-0.383
Bet-0.383
June-0.370
ches-0.349
Token came
Token ID1625
Feature activation-2.35e-01

Pos logit contributions
 officer+0.653
 ma+0.546
 sir+0.528
 salon+0.509
 cash+0.491
Neg logit contributions
tails-1.018
Fel-0.983
Bet-0.979
 buzzing-0.929
 Louise-0.918
Token home
Token ID1363
Feature activation-1.69e+00

Pos logit contributions
 officer+0.014
ily+0.012
 ma+0.011
 kids+0.011
 Dad+0.011
Neg logit contributions
Fel-0.023
tails-0.022
Bet-0.022
 buzzing-0.020
June-0.020
Token from
Token ID422
Feature activation-8.66e-01

Pos logit contributions
 officer+0.110
 ma+0.090
 salon+0.089
 sir+0.088
ily+0.087
Neg logit contributions
Fel-0.152
tails-0.151
Bet-0.149
 buzzing-0.144
 Louise-0.139
Token school
Token ID1524
Feature activation-3.77e+00

Pos logit contributions
 officer+0.048
 ma+0.039
 sir+0.037
 salon+0.037
ily+0.035
Neg logit contributions
Fel-0.088
tails-0.087
Bet-0.084
 buzzing-0.081
 Louise-0.081
Token and
Token ID290
Feature activation-4.54e-01

Pos logit contributions
 officer+0.248
 ma+0.225
ateful+0.218
 sir+0.217
rost+0.217
Neg logit contributions
tails-0.306
Fel-0.300
 buzzing-0.287
Bet-0.280
 Louise-0.279
Tokenâ
Token ID22940
Feature activation-1.56e+00

Pos logit contributions
 officer+0.112
 salon+0.095
 ma+0.095
 accident+0.092
 sir+0.091
Neg logit contributions
Fel-0.126
tails-0.122
Bet-0.120
June-0.113
 Louise-0.112
Token
Token ID26391
Feature activation-2.83e+00

Pos logit contributions
 officer+0.114
 cubes+0.114
 dad+0.109
 salon+0.107
 kids+0.105
Neg logit contributions
Fel-0.120
tails-0.116
Bet-0.111
ches-0.109
June-0.108
Token
Token ID198
Feature activation+2.73e-01

Pos logit contributions
 officer+0.215
 ma+0.187
 salon+0.183
 sir+0.181
 kids+0.179
Neg logit contributions
Fel-0.227
tails-0.223
Bet-0.220
 buzzing-0.208
June-0.208
Token
Token ID198
Feature activation+2.71e-01

Pos logit contributions
tails+0.025
Fel+0.024
Bet+0.023
 buzzing+0.022
June+0.022
Neg logit contributions
 officer-0.018
 ma-0.015
ily-0.015
 salon-0.015
 sir-0.015
TokenAg
Token ID10262
Feature activation-4.69e+00

Pos logit contributions
tails+0.023
Fel+0.023
Bet+0.022
 buzzing+0.021
June+0.021
Neg logit contributions
 officer-0.020
 ma-0.017
 salon-0.016
ily-0.016
 sir-0.016
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.219
 cubes+0.213
 sir+0.203
 ma+0.201
 Dad+0.198
Neg logit contributions
Fel-0.499
tails-0.468
June-0.462
Bet-0.455
ches-0.451
Token smiled
Token ID13541
Feature activation-3.73e+00

Pos logit contributions
 officer+0.769
 ma+0.653
 sir+0.644
 salon+0.639
 cubes+0.627
Neg logit contributions
tails-0.872
Fel-0.847
Bet-0.810
 buzzing-0.793
 Louise-0.793
Token and
Token ID290
Feature activation-4.89e-01

Pos logit contributions
 officer+0.265
 salon+0.236
ople+0.218
iza+0.215
 cubes+0.212
Neg logit contributions
Fel-0.316
tails-0.307
 buzzing-0.299
 Louise-0.297
Bet-0.297
Token said
Token ID531
Feature activation-6.17e-01

Pos logit contributions
 officer+0.026
 ma+0.020
 salon+0.020
 sir+0.020
ily+0.019
Neg logit contributions
Fel-0.051
tails-0.051
Bet-0.049
June-0.047
 buzzing-0.047
Token,
Token ID11
Feature activation-2.94e-01

Pos logit contributions
 officer+0.042
 salon+0.034
ople+0.034
 accident+0.034
 ma+0.033
Neg logit contributions
Fel-0.056
tails-0.055
Bet-0.052
 Louise-0.050
 buzzing-0.050
Token
Token ID6184
Feature activation-3.38e-01

Pos logit contributions
 officer+0.023
 salon+0.020
ople+0.019
 ma+0.019
 accident+0.019
Neg logit contributions
Fel-0.024
tails-0.022
Bet-0.022
 buzzing-0.021
 Louise-0.021
Token Daisy
Token ID40355
Feature activation+7.20e+00

Pos logit contributions
Fel+0.395
tails+0.390
Bet+0.380
June+0.360
 buzzing+0.358
Neg logit contributions
 officer-0.280
 ma-0.232
 salon-0.227
 sir-0.224
ily-0.218
Token.
Token ID13
Feature activation-6.03e-01

Pos logit contributions
Fel+0.837
tails+0.813
Bet+0.811
June+0.774
 Louise+0.755
Neg logit contributions
 officer-0.310
 ma-0.225
ily-0.221
 kids-0.211
 salon-0.207
Token Daisy
Token ID40355
Feature activation+7.22e+00

Pos logit contributions
 officer+0.034
 ma+0.033
ily+0.033
 Dad+0.032
 kids+0.031
Neg logit contributions
tails-0.057
Fel-0.057
Bet-0.051
 buzzing-0.050
ches-0.049
Token loved
Token ID6151
Feature activation-3.06e-01

Pos logit contributions
Fel+0.666
tails+0.664
Bet+0.643
 buzzing+0.611
June+0.610
Neg logit contributions
 officer-0.473
 ma-0.389
 sir-0.384
 salon-0.383
 kids-0.357
Token Wed
Token ID3300
Feature activation-1.59e+00

Pos logit contributions
 officer+0.017
 ma+0.013
 salon+0.013
 kids+0.013
 sir+0.012
Neg logit contributions
Fel-0.032
tails-0.031
Bet-0.031
June-0.029
 Louise-0.029
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.074
 kids+0.061
 ma+0.061
 sir+0.056
 Dad+0.056
Neg logit contributions
tails-0.175
Bet-0.174
Fel-0.174
June-0.166
 buzzing-0.162
Tokendays
Token ID12545
Feature activation-2.94e+00

Pos logit contributions
 officer+0.643
 ma+0.528
 sir+0.505
 salon+0.503
 kids+0.477
Neg logit contributions
tails-1.027
Fel-1.024
Bet-1.000
 buzzing-0.948
June-0.947
Token because
Token ID780
Feature activation+6.67e-01

Pos logit contributions
 officer+0.187
 ma+0.157
 sir+0.153
 salon+0.149
iza+0.144
Neg logit contributions
tails-0.272
Fel-0.272
Bet-0.261
 buzzing-0.251
June-0.247
Token on
Token ID319
Feature activation+2.39e+00

Pos logit contributions
Fel+0.059
tails+0.058
Bet+0.056
June+0.054
 buzzing+0.054
Neg logit contributions
 officer-0.046
 ma-0.038
 sir-0.037
 salon-0.037
iza-0.036
Token Wed
Token ID3300
Feature activation-1.60e+00

Pos logit contributions
Fel+0.202
tails+0.198
Bet+0.189
 buzzing+0.187
 Louise+0.182
Neg logit contributions
 officer-0.178
 sir-0.144
 ma-0.140
ily-0.138
ople-0.135
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.089
 boy+0.079
 kids+0.078
 sir+0.077
 Dad+0.076
Neg logit contributions
Bet-0.159
Fel-0.157
tails-0.155
June-0.155
 buzzing-0.144
Token
Token ID8151
Feature activation+2.33e+00

Pos logit contributions
 officer+0.228
 ma+0.199
 salon+0.196
 sir+0.194
 kids+0.191
Neg logit contributions
Fel-0.217
tails-0.214
Bet-0.209
June-0.197
 buzzing-0.197
Tokenm
Token ID76
Feature activation-2.53e+00

Pos logit contributions
Fel+0.210
tails+0.207
Bet+0.203
June+0.190
 buzzing+0.187
Neg logit contributions
 officer-0.156
 ma-0.130
 salon-0.127
 sir-0.123
iza-0.121
Token sorry
Token ID7926
Feature activation-1.85e+00

Pos logit contributions
 officer+0.184
 ma+0.152
 salon+0.150
 sir+0.148
ily+0.141
Neg logit contributions
Fel-0.218
tails-0.216
Bet-0.207
 buzzing-0.197
 Louise-0.194
Token,
Token ID11
Feature activation-3.13e-01

Pos logit contributions
 officer+0.126
 salon+0.105
 ma+0.101
ople+0.099
iza+0.098
Neg logit contributions
Fel-0.167
tails-0.162
Bet-0.156
 Louise-0.149
 buzzing-0.148
Token Ag
Token ID2449
Feature activation-3.96e+00

Pos logit contributions
 officer+0.020
ople+0.016
ateful+0.016
 salon+0.016
 cubes+0.016
Neg logit contributions
Fel-0.028
Bet-0.027
 buzzing-0.026
 Louise-0.026
 Felix-0.026
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.195
 ma+0.162
 cubes+0.161
 kids+0.157
 Dad+0.157
Neg logit contributions
Fel-0.431
tails-0.412
Bet-0.400
June-0.389
ches-0.381
Token.
Token ID13
Feature activation-4.21e-01

Pos logit contributions
 officer+0.734
 ma+0.618
 salon+0.612
 cash+0.586
 sir+0.581
Neg logit contributions
tails-0.919
Fel-0.877
Bet-0.857
 buzzing-0.840
 Louise-0.827
Token I
Token ID314
Feature activation-1.70e+00

Pos logit contributions
 officer+0.030
 salon+0.025
 accident+0.025
 ma+0.025
 sir+0.024
Neg logit contributions
Fel-0.036
Bet-0.035
tails-0.035
June-0.033
 Louise-0.033
Token was
Token ID373
Feature activation+1.46e+00

Pos logit contributions
 officer+0.128
 ma+0.112
 salon+0.109
 sir+0.107
 cubes+0.105
Neg logit contributions
Fel-0.139
tails-0.132
Bet-0.132
 buzzing-0.122
 Louise-0.120
Token too
Token ID1165
Feature activation-3.15e-01

Pos logit contributions
Fel+0.126
tails+0.125
Bet+0.122
 buzzing+0.122
 Louise+0.117
Neg logit contributions
 officer-0.099
 ma-0.081
 sir-0.081
 salon-0.078
line-0.077
Token busy
Token ID8179
Feature activation+1.55e-01

Pos logit contributions
 officer+0.021
 salon+0.017
 ma+0.016
ily+0.016
 sir+0.016
Neg logit contributions
Fel-0.029
tails-0.028
Bet-0.028
 buzzing-0.027
 Louise-0.026
Token baby
Token ID5156
Feature activation+1.33e+00

Pos logit contributions
 officer+0.065
line+0.060
ily+0.059
ople+0.059
iza+0.058
Neg logit contributions
tails-0.056
Fel-0.055
 buzzing-0.054
Bet-0.051
 Louise-0.050
Token's
Token ID338
Feature activation+1.98e+00

Pos logit contributions
tails+0.111
Fel+0.108
Bet+0.105
 buzzing+0.102
June+0.100
Neg logit contributions
 officer-0.096
 ma-0.083
 sir-0.081
 salon-0.081
line-0.078
Token name
Token ID1438
Feature activation+2.59e+00

Pos logit contributions
tails+0.191
Fel+0.187
Bet+0.180
 buzzing+0.175
 Louise+0.171
Neg logit contributions
 officer-0.119
 ma-0.097
 salon-0.094
ily-0.093
iza-0.092
Token was
Token ID373
Feature activation+1.36e+00

Pos logit contributions
Fel+0.207
tails+0.205
Bet+0.197
 buzzing+0.186
June+0.186
Neg logit contributions
 officer-0.198
 ma-0.171
 salon-0.169
 sir-0.168
iza-0.161
Token Ag
Token ID2449
Feature activation-3.92e+00

Pos logit contributions
Fel+0.140
tails+0.139
Bet+0.134
June+0.129
 buzzing+0.127
Neg logit contributions
 officer-0.074
 ma-0.060
 Dad-0.059
 sir-0.058
 kids-0.057
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.197
 ma+0.168
 kids+0.156
 sir+0.154
 Dad+0.150
Neg logit contributions
Fel-0.416
tails-0.410
Bet-0.401
June-0.387
 buzzing-0.376
Token.
Token ID13
Feature activation-5.45e-01

Pos logit contributions
 officer+0.563
 ma+0.434
 salon+0.428
 sir+0.421
ily+0.410
Neg logit contributions
Fel-1.115
tails-1.087
Bet-1.075
June-1.025
 buzzing-1.009
Token Ag
Token ID2449
Feature activation-3.90e+00

Pos logit contributions
 officer+0.044
 salon+0.040
 ma+0.039
 sir+0.038
iza+0.038
Neg logit contributions
Fel-0.041
Bet-0.040
tails-0.039
June-0.036
 buzzing-0.035
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.159
 ma+0.127
 sir+0.121
 Dad+0.109
 kids+0.109
Neg logit contributions
Fel-0.462
tails-0.450
Bet-0.436
June-0.427
 buzzing-0.418
Token loved
Token ID6151
Feature activation-2.91e-01

Pos logit contributions
 officer+0.766
 ma+0.672
 sir+0.666
 salon+0.634
 cash+0.626
Neg logit contributions
tails-0.916
Fel-0.860
Bet-0.853
 buzzing-0.840
June-0.800
Token to
Token ID284
Feature activation-5.58e-01

Pos logit contributions
 officer+0.015
 ma+0.011
 kids+0.011
 salon+0.011
 Dad+0.011
Neg logit contributions
Fel-0.032
tails-0.031
Bet-0.031
June-0.029
 Louise-0.029
Token was
Token ID373
Feature activation+1.36e+00

Pos logit contributions
Fel+0.207
tails+0.205
Bet+0.197
 buzzing+0.186
June+0.186
Neg logit contributions
 officer-0.198
 ma-0.171
 salon-0.169
 sir-0.168
iza-0.161
Token Ag
Token ID2449
Feature activation-3.92e+00

Pos logit contributions
Fel+0.140
tails+0.139
Bet+0.134
June+0.129
 buzzing+0.127
Neg logit contributions
 officer-0.074
 ma-0.060
 Dad-0.059
 sir-0.058
 kids-0.057
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.197
 ma+0.168
 kids+0.156
 sir+0.154
 Dad+0.150
Neg logit contributions
Fel-0.416
tails-0.410
Bet-0.401
June-0.387
 buzzing-0.376
Token.
Token ID13
Feature activation-5.45e-01

Pos logit contributions
 officer+0.563
 ma+0.434
 salon+0.428
 sir+0.421
ily+0.410
Neg logit contributions
Fel-1.115
tails-1.087
Bet-1.075
June-1.025
 buzzing-1.009
Token Ag
Token ID2449
Feature activation-3.90e+00

Pos logit contributions
 officer+0.044
 salon+0.040
 ma+0.039
 sir+0.038
iza+0.038
Neg logit contributions
Fel-0.041
Bet-0.040
tails-0.039
June-0.036
 buzzing-0.035
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.159
 ma+0.127
 sir+0.121
 Dad+0.109
 kids+0.109
Neg logit contributions
Fel-0.462
tails-0.450
Bet-0.436
June-0.427
 buzzing-0.418
Token loved
Token ID6151
Feature activation-2.91e-01

Pos logit contributions
 officer+0.766
 ma+0.672
 sir+0.666
 salon+0.634
 cash+0.626
Neg logit contributions
tails-0.916
Fel-0.860
Bet-0.853
 buzzing-0.840
June-0.800
Token to
Token ID284
Feature activation-5.58e-01

Pos logit contributions
 officer+0.015
 ma+0.011
 kids+0.011
 salon+0.011
 Dad+0.011
Neg logit contributions
Fel-0.032
tails-0.031
Bet-0.031
June-0.029
 Louise-0.029
Token wink
Token ID41955
Feature activation-2.04e-01

Pos logit contributions
 officer+0.040
 salon+0.033
 ma+0.033
 sir+0.032
ily+0.032
Neg logit contributions
tails-0.048
Fel-0.048
Bet-0.046
 buzzing-0.044
 Louise-0.043
Token at
Token ID379
Feature activation-1.17e+00

Pos logit contributions
 officer+0.013
 salon+0.011
 ma+0.010
 sir+0.010
iza+0.010
Neg logit contributions
tails-0.019
Fel-0.019
 buzzing-0.018
 Louise-0.018
Bet-0.017
Token all
Token ID477
Feature activation-3.19e+00

Pos logit contributions
 officer+0.067
 ma+0.053
 salon+0.051
 sir+0.051
 kids+0.050
Neg logit contributions
Fel-0.120
tails-0.118
Bet-0.116
June-0.110
 buzzing-0.109
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.074
 kids+0.061
 ma+0.061
 sir+0.056
 Dad+0.056
Neg logit contributions
tails-0.175
Bet-0.174
Fel-0.174
June-0.166
 buzzing-0.162
Tokendays
Token ID12545
Feature activation-2.94e+00

Pos logit contributions
 officer+0.643
 ma+0.528
 sir+0.505
 salon+0.503
 kids+0.477
Neg logit contributions
tails-1.027
Fel-1.024
Bet-1.000
 buzzing-0.948
June-0.947
Token because
Token ID780
Feature activation+6.67e-01

Pos logit contributions
 officer+0.187
 ma+0.157
 sir+0.153
 salon+0.149
iza+0.144
Neg logit contributions
tails-0.272
Fel-0.272
Bet-0.261
 buzzing-0.251
June-0.247
Token on
Token ID319
Feature activation+2.39e+00

Pos logit contributions
Fel+0.059
tails+0.058
Bet+0.056
June+0.054
 buzzing+0.054
Neg logit contributions
 officer-0.046
 ma-0.038
 sir-0.037
 salon-0.037
iza-0.036
Token Wed
Token ID3300
Feature activation-1.60e+00

Pos logit contributions
Fel+0.202
tails+0.198
Bet+0.189
 buzzing+0.187
 Louise+0.182
Neg logit contributions
 officer-0.178
 sir-0.144
 ma-0.140
ily-0.138
ople-0.135
Tokennes
Token ID2516
Feature activation-1.06e+01

Pos logit contributions
 officer+0.089
 boy+0.079
 kids+0.078
 sir+0.077
 Dad+0.076
Neg logit contributions
Bet-0.159
Fel-0.157
tails-0.155
June-0.155
 buzzing-0.144
Tokendays
Token ID12545
Feature activation-2.92e+00

Pos logit contributions
 officer+0.655
 ma+0.537
 sir+0.517
 salon+0.511
 kids+0.485
Neg logit contributions
tails-1.016
Fel-1.016
Bet-0.989
June-0.937
 buzzing-0.931
Token she
Token ID673
Feature activation+1.62e+00

Pos logit contributions
 officer+0.207
 sir+0.175
 ma+0.172
 salon+0.164
iza+0.158
Neg logit contributions
tails-0.251
Fel-0.247
Bet-0.237
 buzzing-0.232
June-0.225
Token did
Token ID750
Feature activation-3.57e+00

Pos logit contributions
Fel+0.143
tails+0.140
Bet+0.131
 buzzing+0.130
 Louise+0.128
Neg logit contributions
 officer-0.112
 sir-0.098
 ma-0.096
 salon-0.089
 cash-0.086
Token something
Token ID1223
Feature activation-4.55e-01

Pos logit contributions
 officer+0.240
 sir+0.195
 ma+0.186
 salon+0.176
ily+0.173
Neg logit contributions
Fel-0.330
tails-0.329
 buzzing-0.312
Bet-0.310
June-0.295
Token special
Token ID2041
Feature activation+6.78e-01

Pos logit contributions
 officer+0.029
 ma+0.024
 salon+0.024
 sir+0.023
ily+0.023
Neg logit contributions
Fel-0.043
tails-0.042
Bet-0.042
June-0.040
 Louise-0.038
Token way
Token ID835
Feature activation+2.70e+00

Pos logit contributions
 officer+0.335
 sir+0.294
ily+0.287
 ma+0.284
iza+0.281
Neg logit contributions
tails-0.463
Fel-0.460
Bet-0.435
 buzzing-0.427
June-0.415
Token.
Token ID13
Feature activation-3.72e-01

Pos logit contributions
tails+0.253
Fel+0.247
Bet+0.241
 buzzing+0.232
June+0.229
Neg logit contributions
 officer-0.171
 ma-0.140
 sir-0.135
 salon-0.133
ily-0.129
Token
Token ID198
Feature activation+3.00e-01

Pos logit contributions
 officer+0.027
 ma+0.023
 salon+0.023
 sir+0.022
ily+0.022
Neg logit contributions
Fel-0.031
tails-0.031
Bet-0.030
June-0.028
 buzzing-0.028
Token
Token ID198
Feature activation+2.93e-01

Pos logit contributions
tails+0.030
Fel+0.028
Bet+0.028
 buzzing+0.027
 Louise+0.027
Neg logit contributions
 officer-0.017
ily-0.015
 ma-0.014
 kids-0.014
iza-0.014
TokenAg
Token ID10262
Feature activation-4.66e+00

Pos logit contributions
tails+0.026
Fel+0.025
Bet+0.024
 Louise+0.023
 buzzing+0.023
Neg logit contributions
 officer-0.021
 ma-0.017
ily-0.017
 salon-0.017
iza-0.017
Tokennes
Token ID2516
Feature activation-1.05e+01

Pos logit contributions
 officer+0.217
 sir+0.198
 cubes+0.193
 ma+0.190
 Dad+0.187
Neg logit contributions
Fel-0.506
tails-0.474
June-0.466
Bet-0.463
ches-0.455
Token loved
Token ID6151
Feature activation-1.84e-01

Pos logit contributions
 officer+0.833
 sir+0.722
 ma+0.709
 salon+0.685
 cash+0.661
Neg logit contributions
tails-0.829
Fel-0.803
Bet-0.763
 buzzing-0.750
 Louise-0.724
Token to
Token ID284
Feature activation-4.90e-01

Pos logit contributions
 officer+0.013
 ma+0.011
 sir+0.011
ily+0.010
 salon+0.010
Neg logit contributions
Fel-0.016
tails-0.016
Bet-0.015
 buzzing-0.015
June-0.015
Token help
Token ID1037
Feature activation+7.04e-01

Pos logit contributions
 officer+0.035
 sir+0.030
 ma+0.029
 salon+0.029
ople+0.029
Neg logit contributions
Fel-0.041
tails-0.040
Bet-0.037
 Louise-0.037
 buzzing-0.037
Token out
Token ID503
Feature activation+2.82e+00

Pos logit contributions
Fel+0.068
tails+0.067
Bet+0.065
June+0.062
 buzzing+0.061
Neg logit contributions
 officer-0.044
 ma-0.036
 salon-0.035
 sir-0.034
ily-0.033
Token and
Token ID290
Feature activation-4.37e-01

Pos logit contributions
Fel+0.266
tails+0.264
Bet+0.254
 buzzing+0.244
June+0.242
Neg logit contributions
 officer-0.175
 ma-0.144
 sir-0.141
 salon-0.141
iza-0.135
Token something
Token ID1223
Feature activation-4.55e-01

Pos logit contributions
 officer+0.240
 sir+0.195
 ma+0.186
 salon+0.176
ily+0.173
Neg logit contributions
Fel-0.330
tails-0.329
 buzzing-0.312
Bet-0.310
June-0.295
Token special
Token ID2041
Feature activation+6.78e-01

Pos logit contributions
 officer+0.029
 ma+0.024
 salon+0.024
 sir+0.023
ily+0.023
Neg logit contributions
Fel-0.043
tails-0.042
Bet-0.042
June-0.040
 Louise-0.038
Token.
Token ID13
Feature activation-5.51e-01

Pos logit contributions
Fel+0.063
tails+0.063
Bet+0.060
 buzzing+0.059
 Louise+0.058
Neg logit contributions
 officer-0.042
 ma-0.036
 sir-0.034
 salon-0.034
iza-0.032
Token On
Token ID1550
Feature activation+7.64e-01

Pos logit contributions
 officer+0.026
 Dad+0.024
 ma+0.024
 kids+0.023
ily+0.022
Neg logit contributions
tails-0.059
Fel-0.058
 buzzing-0.055
Bet-0.055
 webs-0.052
Token Wed
Token ID3300
Feature activation-1.57e+00

Pos logit contributions
Fel+0.071
tails+0.070
Bet+0.068
June+0.065
 buzzing+0.065
Neg logit contributions
 officer-0.050
 ma-0.041
 sir-0.040
 salon-0.039
ily-0.038
Tokennes
Token ID2516
Feature activation-1.05e+01

Pos logit contributions
 officer+0.086
 sir+0.073
 kids+0.072
 knee+0.071
 Dad+0.068
Neg logit contributions
Fel-0.163
Bet-0.163
June-0.161
tails-0.160
Lou-0.149
Tokendays
Token ID12545
Feature activation-2.90e+00

Pos logit contributions
 officer+0.610
 ma+0.489
 salon+0.477
 sir+0.469
ily+0.455
Neg logit contributions
Fel-1.054
tails-1.041
Bet-1.018
June-0.967
 buzzing-0.961
Token she
Token ID673
Feature activation+1.66e+00

Pos logit contributions
 officer+0.213
 sir+0.178
 ma+0.171
 American+0.164
ateful+0.163
Neg logit contributions
Fel-0.238
tails-0.232
Bet-0.227
 Louise-0.216
 buzzing-0.216
Token liked
Token ID8288
Feature activation-1.90e+00

Pos logit contributions
Fel+0.129
tails+0.129
Bet+0.117
 buzzing+0.116
 Louise+0.116
Neg logit contributions
 officer-0.129
 sir-0.115
 ma-0.111
line-0.102
 cubes-0.101
Token to
Token ID284
Feature activation-5.50e-01

Pos logit contributions
 officer+0.112
 ma+0.090
 salon+0.087
 sir+0.087
ily+0.084
Neg logit contributions
Fel-0.188
tails-0.186
Bet-0.182
June-0.173
 buzzing-0.172
Token count
Token ID954
Feature activation+3.03e+00

Pos logit contributions
 officer+0.045
 sir+0.039
ople+0.037
isher+0.037
 ma+0.037
Neg logit contributions
tails-0.040
Fel-0.039
 buzzing-0.038
Bet-0.035
 Louise-0.035
Token needed
Token ID2622
Feature activation+7.03e-01

Pos logit contributions
 officer+0.073
 ma+0.059
 salon+0.057
 sir+0.056
ily+0.055
Neg logit contributions
Fel-0.123
tails-0.122
Bet-0.119
June-0.113
 buzzing-0.112
Token help
Token ID1037
Feature activation+4.99e-01

Pos logit contributions
Fel+0.070
tails+0.069
Bet+0.068
June+0.064
 buzzing+0.062
Neg logit contributions
 officer-0.041
 ma-0.034
 sir-0.033
 kids-0.033
ily-0.033
Token.
Token ID13
Feature activation-4.47e-01

Pos logit contributions
Fel+0.058
tails+0.055
Bet+0.055
June+0.053
 buzzing+0.051
Neg logit contributions
 officer-0.023
 ma-0.017
 kids-0.017
 sir-0.016
ily-0.016
Token So
Token ID1406
Feature activation-8.00e-01

Pos logit contributions
 Dad+0.030
 officer+0.029
ily+0.029
 ma+0.028
 sir+0.028
Neg logit contributions
Fel-0.034
tails-0.034
 buzzing-0.033
 leaping-0.032
Bet-0.032
Token,
Token ID11
Feature activation-2.40e-01

Pos logit contributions
 dad+0.017
 officer+0.017
 sir+0.016
 Dad+0.016
 ma+0.016
Neg logit contributions
Fel-0.097
tails-0.093
June-0.093
pill-0.093
Bet-0.091
Token Remy
Token ID32912
Feature activation+1.12e+01

Pos logit contributions
 he+0.017
 dad+0.017
 Dad+0.017
 kids+0.017
 boy+0.017
Neg logit contributions
tails-0.017
June-0.016
Fel-0.016
 webs-0.015
Bet-0.015
Token closed
Token ID4838
Feature activation-2.97e+00

Pos logit contributions
tails+1.069
Fel+1.058
Bet+1.046
 buzzing+1.009
 Louise+1.005
Neg logit contributions
 officer-0.668
 salon-0.568
 ma-0.541
 sir-0.521
 cubes-0.515
Token his
Token ID465
Feature activation-1.29e+00

Pos logit contributions
 officer+0.193
 ma+0.158
 salon+0.157
 sir+0.153
iza+0.146
Neg logit contributions
Fel-0.280
tails-0.275
Bet-0.269
 Louise-0.262
 buzzing-0.256
Token eyes
Token ID2951
Feature activation-1.48e-01

Pos logit contributions
 officer+0.069
 ma+0.056
 sir+0.054
 salon+0.053
 kids+0.052
Neg logit contributions
Fel-0.136
tails-0.133
Bet-0.132
June-0.126
 buzzing-0.123
Token and
Token ID290
Feature activation-4.80e-01

Pos logit contributions
 officer+0.011
 salon+0.009
 ma+0.009
iza+0.009
ople+0.009
Neg logit contributions
tails-0.012
Fel-0.012
Bet-0.012
 buzzing-0.012
 Louise-0.011
Token prayed
Token ID32168
Feature activation-1.80e+00

Pos logit contributions
 officer+0.030
 salon+0.025
 ma+0.024
 sir+0.024
ily+0.023
Neg logit contributions
tails-0.045
Fel-0.044
Bet-0.043
 buzzing-0.043
 Louise-0.042
Token Tim
Token ID5045
Feature activation-8.68e-01

Pos logit contributions
 officer+0.006
 ma+0.004
 salon+0.004
 sir+0.004
iza+0.004
Neg logit contributions
Fel-0.010
tails-0.010
Bet-0.009
June-0.009
 buzzing-0.009
Token said
Token ID531
Feature activation-3.10e-01

Pos logit contributions
 officer+0.051
 ma+0.041
 salon+0.040
 sir+0.039
ily+0.038
Neg logit contributions
Fel-0.086
tails-0.085
Bet-0.083
June-0.079
 buzzing-0.079
Token sorry
Token ID7926
Feature activation-1.86e+00

Pos logit contributions
 officer+0.022
 salon+0.019
iza+0.019
ople+0.018
line+0.018
Neg logit contributions
Fel-0.026
tails-0.025
 buzzing-0.025
Bet-0.024
 Louise-0.024
Token to
Token ID284
Feature activation-4.59e-01

Pos logit contributions
 officer+0.103
 ma+0.082
 salon+0.079
 sir+0.079
ily+0.076
Neg logit contributions
Fel-0.192
tails-0.190
Bet-0.186
June-0.177
 buzzing-0.175
Token the
Token ID262
Feature activation-1.84e-01

Pos logit contributions
 officer+0.029
 salon+0.024
 ma+0.024
 sir+0.023
iza+0.023
Neg logit contributions
tails-0.042
Fel-0.042
Bet-0.042
 buzzing-0.039
June-0.039
Token snake
Token ID17522
Feature activation+7.43e+00

Pos logit contributions
 officer+0.015
 kids+0.015
 boy+0.015
ily+0.014
 accident+0.014
Neg logit contributions
Fel-0.014
tails-0.014
Bet-0.013
June-0.012
 Louise-0.012
Token and
Token ID290
Feature activation-2.21e-01

Pos logit contributions
Fel+0.706
tails+0.702
Bet+0.686
 buzzing+0.653
 Louise+0.649
Neg logit contributions
 officer-0.448
 ma-0.371
 salon-0.364
iza-0.355
 sir-0.346
Token they
Token ID484
Feature activation+8.57e-01

Pos logit contributions
 officer+0.014
iza+0.012
 salon+0.012
 ma+0.012
 sir+0.011
Neg logit contributions
tails-0.020
Bet-0.019
Fel-0.018
 buzzing-0.018
 Louise-0.018
Token kept
Token ID4030
Feature activation-2.19e+00

Pos logit contributions
tails+0.077
Fel+0.076
Bet+0.074
June+0.070
 buzzing+0.069
Neg logit contributions
 officer-0.057
 ma-0.050
 salon-0.049
 sir-0.048
iza-0.046
Token playing
Token ID2712
Feature activation+2.48e+00

Pos logit contributions
 officer+0.117
 dad+0.112
 Dad+0.112
 kids+0.111
 accident+0.108
Neg logit contributions
Fel-0.228
Bet-0.219
June-0.206
tails-0.202
 Louise-0.202
Token.
Token ID13
Feature activation-8.63e-02

Pos logit contributions
Fel+0.210
tails+0.205
Bet+0.199
 buzzing+0.191
June+0.188
Neg logit contributions
 officer-0.182
 ma-0.154
 salon-0.152
 sir-0.150
iza-0.146
Tokenoo
Token ID2238
Feature activation+2.50e+00

Pos logit contributions
Fel+0.113
tails+0.109
Bet+0.108
June+0.101
 Louise+0.098
Neg logit contributions
 officer-0.127
 salon-0.109
 ma-0.109
 sir-0.108
iza-0.104
Token.
Token ID13
Feature activation+6.56e-02

Pos logit contributions
Fel+0.256
tails+0.253
Bet+0.248
June+0.236
 buzzing+0.234
Neg logit contributions
 officer-0.140
 ma-0.112
 salon-0.109
 sir-0.107
ily-0.103
Token It
Token ID632
Feature activation-5.00e-01

Pos logit contributions
Fel+0.006
tails+0.006
Bet+0.005
 buzzing+0.005
June+0.005
Neg logit contributions
 officer-0.005
 salon-0.004
 ma-0.004
 sir-0.004
iza-0.004
Token was
Token ID373
Feature activation+1.75e+00

Pos logit contributions
 officer+0.021
 boy+0.018
 did+0.016
 kids+0.015
 accident+0.015
Neg logit contributions
tails-0.057
Fel-0.057
Bet-0.056
June-0.054
 Louise-0.053
Token the
Token ID262
Feature activation+2.15e-02

Pos logit contributions
Fel+0.187
tails+0.183
Bet+0.175
June+0.170
 Louise+0.163
Neg logit contributions
 officer-0.094
 kids-0.079
 Dad-0.079
 accident-0.076
 ma-0.076
Token cow
Token ID9875
Feature activation+7.31e+00

Pos logit contributions
Fel+0.002
tails+0.002
Bet+0.002
 buzzing+0.002
June+0.002
Neg logit contributions
 officer-0.001
 ma-0.001
 salon-0.001
ily-0.001
 sir-0.001
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
Fel+0.845
Bet+0.803
June+0.778
tails+0.768
 Louise+0.741
Neg logit contributions
 officer-0.354
 kids-0.271
 sir-0.259
 salon-0.257
 ma-0.252
Token It
Token ID632
Feature activation-5.54e-01

Pos logit contributions
Fel+0.011
Bet+0.011
tails+0.011
 Louise+0.010
 buzzing+0.010
Neg logit contributions
 officer-0.010
 salon-0.008
 ma-0.008
 accident-0.008
 sir-0.008
Token was
Token ID373
Feature activation+1.72e+00

Pos logit contributions
 officer+0.028
 boy+0.021
 kids+0.020
 accident+0.020
ily+0.019
Neg logit contributions
Fel-0.060
tails-0.060
Bet-0.058
June-0.056
 Louise-0.056
Token angry
Token ID7954
Feature activation-6.40e-03

Pos logit contributions
Fel+0.178
tails+0.170
Bet+0.166
June+0.161
 Louise+0.153
Neg logit contributions
 officer-0.099
 kids-0.084
 Dad-0.083
 ma-0.083
 dad-0.081
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
 officer+0.000
 ma+0.000
 salon+0.000
 sir+0.000
iza+0.000
Neg logit contributions
Fel-0.001
tails-0.001
Bet-0.001
 buzzing-0.001
June-0.001
Token had
Token ID550
Feature activation+3.07e-04

Pos logit contributions
 officer+0.229
 ma+0.203
 sir+0.202
 salon+0.195
ateful+0.195
Neg logit contributions
tails-0.323
Fel-0.319
Bet-0.305
 buzzing-0.290
June-0.289
Token to
Token ID284
Feature activation-5.81e-01

Pos logit contributions
Fel+0.000
Bet+0.000
tails+0.000
 buzzing+0.000
 leaping+0.000
Neg logit contributions
 officer-0.000
 sir-0.000
ateful-0.000
 salon-0.000
isher-0.000
Token go
Token ID467
Feature activation+4.35e-01

Pos logit contributions
 officer+0.042
 salon+0.036
 cubes+0.035
ily+0.035
outed+0.035
Neg logit contributions
tails-0.048
Fel-0.047
Bet-0.046
 Louise-0.044
 buzzing-0.044
Token home
Token ID1363
Feature activation-1.74e+00

Pos logit contributions
Fel+0.040
tails+0.040
Bet+0.038
 buzzing+0.037
June+0.036
Neg logit contributions
 officer-0.029
 ma-0.024
 salon-0.023
 sir-0.023
ily-0.023
Token,
Token ID11
Feature activation-3.12e-01

Pos logit contributions
 officer+0.131
ily+0.111
 salon+0.109
 ma+0.107
iza+0.105
Neg logit contributions
tails-0.140
Fel-0.138
 buzzing-0.129
Bet-0.128
 Louise-0.125
Token Andy
Token ID12382
Feature activation+7.97e+00

Pos logit contributions
 officer+0.017
 Dad+0.014
 dad+0.013
 kids+0.013
 boy+0.013
Neg logit contributions
Fel-0.033
tails-0.031
Bet-0.031
ches-0.030
June-0.029
Token was
Token ID373
Feature activation+1.45e+00

Pos logit contributions
tails+0.719
Fel+0.708
Bet+0.678
 buzzing+0.656
 Louise+0.651
Neg logit contributions
 officer-0.519
 ma-0.441
 salon-0.431
 sir-0.430
ily-0.421
Token sad
Token ID6507
Feature activation-1.99e+00

Pos logit contributions
tails+0.115
Fel+0.113
 buzzing+0.112
Bet+0.109
 Louise+0.103
Neg logit contributions
 officer-0.110
 sir-0.092
 ma-0.090
ily-0.088
 salon-0.087
Token.
Token ID13
Feature activation-4.39e-01

Pos logit contributions
 officer+0.136
 salon+0.114
iza+0.113
 ma+0.113
ily+0.112
Neg logit contributions
Fel-0.171
tails-0.167
 buzzing-0.162
Bet-0.158
 Louise-0.156
Token He
Token ID679
Feature activation-1.47e+00

Pos logit contributions
 officer+0.024
 ma+0.019
 sir+0.019
 salon+0.018
 kids+0.018
Neg logit contributions
Fel-0.045
tails-0.045
Bet-0.043
 buzzing-0.041
June-0.041
Token missed
Token ID6825
Feature activation-1.42e+00

Pos logit contributions
 officer+0.092
 ma+0.078
 salon+0.078
 sir+0.076
ily+0.074
Neg logit contributions
Fel-0.136
tails-0.136
Bet-0.130
 buzzing-0.125
June-0.124
Token too
Token ID1165
Feature activation-2.85e-01

Pos logit contributions
Fel+0.274
Bet+0.269
tails+0.268
 Louise+0.250
 buzzing+0.249
Neg logit contributions
 officer-0.164
 ma-0.130
iza-0.125
ateful-0.121
 salon-0.119
Token,
Token ID11
Feature activation-7.11e-02

Pos logit contributions
 officer+0.017
 salon+0.013
ople+0.012
iza+0.012
 ma+0.012
Neg logit contributions
Fel-0.028
Bet-0.028
tails-0.028
 buzzing-0.027
 Louise-0.026
Token Mitt
Token ID16627
Feature activation+9.37e+00

Pos logit contributions
 officer+0.004
 ma+0.003
 sir+0.003
 kids+0.003
 salon+0.003
Neg logit contributions
Fel-0.007
tails-0.007
Bet-0.007
June-0.007
 buzzing-0.007
Tokenens
Token ID641
Feature activation+2.91e+00

Pos logit contributions
Fel+0.829
tails+0.819
Bet+0.796
June+0.752
 buzzing+0.748
Neg logit contributions
 officer-0.655
 ma-0.548
 salon-0.534
 sir-0.531
ily-0.520
Token?"
Token ID1701
Feature activation-2.70e+00

Pos logit contributions
Fel+0.329
tails+0.325
Bet+0.320
June+0.305
 buzzing+0.304
Neg logit contributions
 officer-0.129
 ma-0.095
 salon-0.093
 sir-0.088
ily-0.084
Token Mitt
Token ID16627
Feature activation+9.39e+00

Pos logit contributions
 officer+0.237
 Dad+0.236
 Tommy+0.232
 kids+0.222
 dad+0.220
Neg logit contributions
tails-0.162
Fel-0.160
 webs-0.151
 buzzing-0.149
June-0.145
Tokenens
Token ID641
Feature activation+2.91e+00

Pos logit contributions
Fel+0.879
tails+0.871
Bet+0.835
 buzzing+0.803
June+0.800
Neg logit contributions
 officer-0.613
 ma-0.502
ily-0.494
 sir-0.493
 kids-0.478
Token l
Token ID300
Feature activation+3.34e+00

Pos logit contributions
Fel+0.264
tails+0.260
Bet+0.254
June+0.240
 buzzing+0.238
Neg logit contributions
 officer-0.196
 ma-0.163
 salon-0.159
 sir-0.157
ily-0.153
Tokenicked
Token ID9484
Feature activation+1.40e+00

Pos logit contributions
Fel+0.283
tails+0.280
Bet+0.272
June+0.256
 buzzing+0.254
Neg logit contributions
 officer-0.246
 ma-0.208
 salon-0.203
 sir-0.201
ily-0.200
Token his
Token ID465
Feature activation-1.18e+00

Pos logit contributions
tails+0.170
Fel+0.161
elope+0.154
 buzzing+0.153
June+0.152
Neg logit contributions
ily-0.053
 Dad-0.049
 officer-0.046
 kids-0.045
 Tommy-0.044
Token lips
Token ID11914
Feature activation+1.22e+00

Pos logit contributions
 officer+0.066
 ma+0.054
 kids+0.054
 sir+0.051
 knee+0.051
Neg logit contributions
Fel-0.125
Bet-0.121
tails-0.118
June-0.114
 Louise-0.110
Token,
Token ID11
Feature activation+1.28e-01

Pos logit contributions
 officer+0.121
 ma+0.103
 kids+0.098
 sir+0.098
 salon+0.094
Neg logit contributions
Fel-0.228
Bet-0.224
tails-0.224
June-0.214
 buzzing-0.207
Token look
Token ID804
Feature activation-4.20e+00

Pos logit contributions
Fel+0.012
tails+0.011
 Louise+0.011
 Luna+0.011
 buzzing+0.011
Neg logit contributions
 officer-0.008
ople-0.006
line-0.006
 salon-0.006
 ma-0.006
Token at
Token ID379
Feature activation-1.19e+00

Pos logit contributions
 officer+0.225
 ma+0.176
 salon+0.172
 sir+0.168
ily+0.162
Neg logit contributions
Fel-0.440
tails-0.435
Bet-0.426
June-0.405
 buzzing-0.404
Token this
Token ID428
Feature activation-2.21e+00

Pos logit contributions
 officer+0.080
 ma+0.066
 salon+0.064
 sir+0.063
iza+0.061
Neg logit contributions
Fel-0.107
tails-0.106
Bet-0.102
 buzzing-0.098
 Louise-0.097
Token wig
Token ID45678
Feature activation-1.55e+00

Pos logit contributions
 officer+0.158
 ma+0.132
 sir+0.128
 salon+0.127
ily+0.125
Neg logit contributions
Fel-0.187
tails-0.186
Bet-0.176
 buzzing-0.171
 Louise-0.167
Token!"
Token ID2474
Feature activation+3.03e+00

Pos logit contributions
 officer+0.121
 ma+0.103
 salon+0.101
 sir+0.100
ily+0.098
Neg logit contributions
Fel-0.123
tails-0.123
Bet-0.117
 buzzing-0.111
June-0.110
Token Anna
Token ID11735
Feature activation+3.02e-01

Pos logit contributions
Fel+0.251
 Louise+0.245
tails+0.236
 Luna+0.236
 Izzy+0.231
Neg logit contributions
 officer-0.215
 salon-0.188
isher-0.175
 American-0.172
line-0.171
Token says
Token ID1139
Feature activation+2.42e+00

Pos logit contributions
Fel+0.025
tails+0.025
Bet+0.024
 Louise+0.023
 buzzing+0.023
Neg logit contributions
 officer-0.022
 ma-0.019
 salon-0.019
 sir-0.018
iza-0.018
Token.
Token ID13
Feature activation+3.18e-02

Pos logit contributions
tails+0.220
Fel+0.212
 buzzing+0.207
 Louise+0.201
Bet+0.199
Neg logit contributions
 officer-0.159
 salon-0.134
 ma-0.132
iza-0.126
ople-0.124
Token "
Token ID366
Feature activation+1.62e-01

Pos logit contributions
tails+0.003
Fel+0.003
Bet+0.003
June+0.003
 buzzing+0.003
Neg logit contributions
 officer-0.002
 ma-0.002
ily-0.002
 Dad-0.001
 sir-0.001
TokenIt
Token ID1026
Feature activation-1.17e+00

Pos logit contributions
Fel+0.013
tails+0.013
Bet+0.013
June+0.012
 buzzing+0.012
Neg logit contributions
 officer-0.012
 ma-0.010
 salon-0.010
 sir-0.010
 kids-0.010
Token
Token ID198
Feature activation+2.08e-01

Pos logit contributions
 officer+0.037
 ma+0.031
 sir+0.030
 kids+0.029
 Dad+0.029
Neg logit contributions
tails-0.051
Fel-0.051
Bet-0.049
 buzzing-0.047
June-0.047
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
tails+0.023
Fel+0.022
Bet+0.021
 buzzing+0.021
 webs+0.021
Neg logit contributions
 officer-0.010
ily-0.008
 Dad-0.008
 kids-0.008
 dad-0.007
TokenOne
Token ID3198
Feature activation-2.42e-01

Pos logit contributions
tails+0.020
Fel+0.019
Bet+0.018
 Louise+0.018
 webs+0.018
Neg logit contributions
 officer-0.014
 ma-0.011
ily-0.011
 kids-0.011
 sir-0.011
Token of
Token ID286
Feature activation+3.13e-01

Pos logit contributions
 officer+0.014
 ma+0.012
 sir+0.011
 kids+0.011
 salon+0.011
Neg logit contributions
Fel-0.024
tails-0.024
Bet-0.024
June-0.022
 buzzing-0.022
Token the
Token ID262
Feature activation-3.49e-01

Pos logit contributions
tails+0.033
Fel+0.032
Bet+0.031
June+0.030
 buzzing+0.030
Neg logit contributions
 officer-0.017
 kids-0.013
 ma-0.013
ily-0.013
 sir-0.013
Token friends
Token ID2460
Feature activation+2.33e+00

Pos logit contributions
 officer+0.018
 ma+0.016
 salon+0.016
iza+0.016
ily+0.015
Neg logit contributions
Fel-0.034
tails-0.033
June-0.032
 Louise-0.032
Bet-0.031
Token,
Token ID11
Feature activation-2.96e-01

Pos logit contributions
tails+0.196
Fel+0.191
Bet+0.182
 buzzing+0.181
 Louise+0.179
Neg logit contributions
 officer-0.141
 salon-0.131
 sir-0.130
 ma-0.129
 cash-0.126
Token David
Token ID3271
Feature activation-1.61e+00

Pos logit contributions
 officer+0.019
 salon+0.016
 ma+0.016
iza+0.015
 sir+0.015
Neg logit contributions
Fel-0.027
tails-0.027
Bet-0.026
 buzzing-0.025
 Louise-0.025
Token,
Token ID11
Feature activation-2.90e-01

Pos logit contributions
 officer+0.099
 salon+0.081
 ma+0.081
 sir+0.079
ily+0.076
Neg logit contributions
Fel-0.152
tails-0.151
Bet-0.147
 buzzing-0.141
 Louise-0.140
Token said
Token ID531
Feature activation-6.40e-01

Pos logit contributions
 officer+0.016
 salon+0.015
 ma+0.013
 sir+0.013
line+0.013
Neg logit contributions
Bet-0.028
tails-0.028
Fel-0.027
 buzzing-0.026
 Louise-0.026
Token to
Token ID284
Feature activation-6.22e-01

Pos logit contributions
 officer+0.042
 salon+0.034
 ma+0.034
iza+0.033
 sir+0.032
Neg logit contributions
Fel-0.059
tails-0.059
Bet-0.057
 buzzing-0.054
 Louise-0.054
Token wave
Token ID6769
Feature activation+9.79e-01

Pos logit contributions
Fel+0.272
tails+0.268
Bet+0.262
June+0.248
 buzzing+0.245
Neg logit contributions
 officer-0.194
 ma-0.161
 salon-0.157
 sir-0.155
ily-0.151
Token he
Token ID339
Feature activation-1.05e+00

Pos logit contributions
Fel+0.090
tails+0.089
Bet+0.086
 buzzing+0.085
June+0.082
Neg logit contributions
 officer-0.062
 ma-0.052
 salon-0.050
 sir-0.050
iza-0.047
Token had
Token ID550
Feature activation+1.90e-01

Pos logit contributions
 officer+0.068
 ma+0.057
 salon+0.057
 sir+0.056
ily+0.052
Neg logit contributions
Fel-0.096
tails-0.096
Bet-0.092
 buzzing-0.089
June-0.088
Token ever
Token ID1683
Feature activation+7.20e-01

Pos logit contributions
Fel+0.016
tails+0.016
Bet+0.015
 buzzing+0.015
June+0.014
Neg logit contributions
 officer-0.014
 ma-0.012
 sir-0.012
 salon-0.012
 cash-0.011
Token seen
Token ID1775
Feature activation+7.38e-01

Pos logit contributions
tails+0.063
Bet+0.061
Fel+0.061
 buzzing+0.060
June+0.056
Neg logit contributions
 officer-0.049
 sir-0.043
 salon-0.042
 ma-0.042
 cash-0.038
Token!
Token ID0
Feature activation+5.92e+00

Pos logit contributions
Fel+0.069
tails+0.068
Bet+0.066
 buzzing+0.064
June+0.063
Neg logit contributions
 officer-0.047
 ma-0.039
 salon-0.038
 sir-0.037
iza-0.036
Token But
Token ID887
Feature activation+3.22e-01

Pos logit contributions
Fel+0.522
tails+0.506
Bet+0.505
June+0.476
 Louise+0.471
Neg logit contributions
 officer-0.406
 salon-0.341
 ma-0.338
 sir-0.325
 accident-0.324
Token he
Token ID339
Feature activation-8.54e-01

Pos logit contributions
Fel+0.028
tails+0.028
Bet+0.027
 Louise+0.026
 buzzing+0.026
Neg logit contributions
 officer-0.022
 salon-0.018
 ma-0.018
ily-0.017
iza-0.017
Token was
Token ID373
Feature activation+1.76e+00

Pos logit contributions
 officer+0.057
 ma+0.047
 salon+0.046
 sir+0.045
ily+0.044
Neg logit contributions
Fel-0.078
tails-0.077
Bet-0.075
 buzzing-0.071
June-0.071
Token still
Token ID991
Feature activation-1.32e+00

Pos logit contributions
Fel+0.159
tails+0.157
Bet+0.154
 buzzing+0.150
June+0.146
Neg logit contributions
 officer-0.117
 ma-0.094
 salon-0.094
 sir-0.093
ily-0.087
Token brave
Token ID14802
Feature activation+2.10e+00

Pos logit contributions
 officer+0.087
 ma+0.071
 salon+0.070
 sir+0.069
ily+0.067
Neg logit contributions
Fel-0.122
tails-0.121
Bet-0.118
June-0.111
 buzzing-0.111
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
 officer+0.141
iza+0.124
 salon+0.121
 ma+0.118
 cash+0.114
Neg logit contributions
tails-0.161
 buzzing-0.159
Fel-0.155
 webs-0.151
Bet-0.148
Token It
Token ID632
Feature activation-5.17e-01

Pos logit contributions
Fel+0.011
tails+0.010
Bet+0.010
June+0.010
 buzzing+0.010
Neg logit contributions
 officer-0.009
 ma-0.007
 salon-0.007
 sir-0.007
 kids-0.007
Token was
Token ID373
Feature activation+1.86e+00

Pos logit contributions
 officer+0.027
 ma+0.021
 salon+0.020
 sir+0.020
ily+0.019
Neg logit contributions
Fel-0.055
tails-0.054
Bet-0.053
June-0.051
 buzzing-0.050
Token a
Token ID257
Feature activation-5.57e-02

Pos logit contributions
Fel+0.189
tails+0.186
Bet+0.182
June+0.173
 Louise+0.169
Neg logit contributions
 officer-0.107
 ma-0.087
 salon-0.083
 sir-0.082
ily-0.081
Token nice
Token ID3621
Feature activation-1.26e+00

Pos logit contributions
 officer+0.003
 ma+0.003
 salon+0.003
 sir+0.003
 kids+0.003
Neg logit contributions
Fel-0.005
tails-0.005
Bet-0.005
June-0.005
 Louise-0.005
Token squirrel
Token ID33039
Feature activation+3.04e+00

Pos logit contributions
 officer+0.081
 ma+0.067
 salon+0.065
 sir+0.064
ily+0.062
Neg logit contributions
Fel-0.119
tails-0.117
Bet-0.115
June-0.109
 buzzing-0.107
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
Fel+0.357
Bet+0.346
tails+0.342
June+0.332
 Louise+0.324
Neg logit contributions
 officer-0.138
 salon-0.095
 sir-0.092
ily-0.091
 kids-0.090
Token
Token ID198
Feature activation+8.02e-01

Pos logit contributions
Fel+0.012
tails+0.012
Bet+0.012
June+0.011
 Louise+0.011
Neg logit contributions
 officer-0.010
 ma-0.009
 salon-0.009
 sir-0.008
 kids-0.008
Token
Token ID198
Feature activation+7.95e-01

Pos logit contributions
tails+0.080
Fel+0.078
Bet+0.075
June+0.071
 buzzing+0.070
Neg logit contributions
 officer-0.048
ily-0.041
 ma-0.040
 kids-0.038
 Dad-0.038
TokenAnna
Token ID31160
Feature activation-6.74e-01

Pos logit contributions
Fel+0.076
tails+0.075
Bet+0.073
June+0.069
 buzzing+0.069
Neg logit contributions
 officer-0.050
 ma-0.041
 salon-0.040
 sir-0.040
ily-0.039
Token and
Token ID290
Feature activation-3.14e-02

Pos logit contributions
 officer+0.043
 ma+0.036
 salon+0.036
 sir+0.036
line+0.034
Neg logit contributions
Fel-0.062
tails-0.061
Bet-0.059
 buzzing-0.057
 Louise-0.056
Token them
Token ID606
Feature activation-6.99e-01

Pos logit contributions
 officer+0.121
 ma+0.102
 salon+0.100
 sir+0.099
ily+0.094
Neg logit contributions
Fel-0.145
tails-0.143
Bet-0.138
 buzzing-0.131
June-0.131
Token together
Token ID1978
Feature activation+8.94e-01

Pos logit contributions
 officer+0.058
 ma+0.049
 salon+0.049
 sir+0.048
iza+0.047
Neg logit contributions
Fel-0.053
tails-0.053
Bet-0.050
 buzzing-0.048
June-0.047
Token to
Token ID284
Feature activation-5.26e-01

Pos logit contributions
Fel+0.096
tails+0.094
Bet+0.093
June+0.088
 buzzing+0.087
Neg logit contributions
 officer-0.046
 ma-0.036
 salon-0.035
 sir-0.034
ily-0.033
Token fill
Token ID6070
Feature activation-2.82e-02

Pos logit contributions
 officer+0.038
 sir+0.031
 salon+0.030
 ma+0.030
ople+0.029
Neg logit contributions
tails-0.046
Fel-0.045
Bet-0.044
 buzzing-0.043
 Louise-0.042
Token the
Token ID262
Feature activation+9.01e-02

Pos logit contributions
 officer+0.002
 ma+0.001
 kids+0.001
 salon+0.001
ily+0.001
Neg logit contributions
Fel-0.003
tails-0.003
Bet-0.003
June-0.003
 Louise-0.002
Token gap
Token ID7625
Feature activation+2.48e+00

Pos logit contributions
Fel+0.007
 webs+0.007
tails+0.007
 buzzing+0.007
 web+0.007
Neg logit contributions
 officer-0.007
 sir-0.005
iza-0.005
 ma-0.005
ily-0.005
Token.
Token ID13
Feature activation-4.97e-01

Pos logit contributions
Fel+0.229
tails+0.229
Bet+0.222
 buzzing+0.213
June+0.210
Neg logit contributions
 officer-0.161
 ma-0.131
 salon-0.128
 sir-0.126
ily-0.120
Token Finally
Token ID9461
Feature activation+2.78e+00

Pos logit contributions
 Dad+0.031
ily+0.030
 ma+0.030
 officer+0.028
 kids+0.028
Neg logit contributions
tails-0.048
Fel-0.044
Bet-0.043
 buzzing-0.041
June-0.041
Token,
Token ID11
Feature activation-2.33e-01

Pos logit contributions
Fel+0.265
tails+0.259
Bet+0.254
 buzzing+0.240
June+0.240
Neg logit contributions
 officer-0.179
 ma-0.143
 salon-0.143
 sir-0.140
ily-0.134
Token the
Token ID262
Feature activation+9.90e-02

Pos logit contributions
 officer+0.012
 Dad+0.012
 ma+0.011
iza+0.011
 dad+0.011
Neg logit contributions
tails-0.024
Fel-0.024
Bet-0.023
June-0.022
 buzzing-0.021
Token ceiling
Token ID13387
Feature activation-5.65e+00

Pos logit contributions
Fel+0.008
tails+0.008
 webs+0.008
 buzzing+0.008
 Louise+0.008
Neg logit contributions
 officer-0.007
iza-0.006
 sir-0.006
line-0.005
 ma-0.005
Token learned
Token ID4499
Feature activation-1.86e+00

Pos logit contributions
Fel+0.065
tails+0.064
Bet+0.063
June+0.059
 buzzing+0.059
Neg logit contributions
 officer-0.039
 ma-0.032
 salon-0.031
 sir-0.031
ily-0.029
Token to
Token ID284
Feature activation-5.07e-01

Pos logit contributions
 officer+0.105
 ma+0.083
 salon+0.081
 sir+0.079
ily+0.077
Neg logit contributions
Fel-0.191
tails-0.189
Bet-0.185
June-0.176
 buzzing-0.175
Token be
Token ID307
Feature activation-1.88e+00

Pos logit contributions
 officer+0.031
 salon+0.024
 ma+0.024
 sir+0.024
iza+0.024
Neg logit contributions
tails-0.050
Fel-0.048
Bet-0.048
 buzzing-0.045
June-0.045
Token more
Token ID517
Feature activation+1.57e+00

Pos logit contributions
 officer+0.116
 ma+0.094
 salon+0.092
 sir+0.090
ily+0.088
Neg logit contributions
Fel-0.183
tails-0.181
Bet-0.176
June-0.167
 buzzing-0.166
Token careful
Token ID8161
Feature activation-4.21e-01

Pos logit contributions
Fel+0.154
tails+0.152
Bet+0.148
June+0.141
 buzzing+0.140
Neg logit contributions
 officer-0.096
 ma-0.078
 salon-0.076
 sir-0.075
ily-0.073
Token and
Token ID290
Feature activation-3.92e-01

Pos logit contributions
 officer+0.028
 ma+0.023
 salon+0.022
 sir+0.022
iza+0.022
Neg logit contributions
tails-0.039
Fel-0.038
Bet-0.037
 buzzing-0.036
June-0.036
Token to
Token ID284
Feature activation-5.18e-01

Pos logit contributions
 officer+0.024
 ma+0.019
 salon+0.019
 sir+0.019
iza+0.018
Neg logit contributions
tails-0.038
Fel-0.037
Bet-0.037
 buzzing-0.035
June-0.035
Token always
Token ID1464
Feature activation-2.73e+00

Pos logit contributions
 officer+0.030
 ma+0.024
 salon+0.024
 sir+0.023
ily+0.023
Neg logit contributions
tails-0.051
Fel-0.051
Bet-0.050
 buzzing-0.047
June-0.047
Token look
Token ID804
Feature activation-4.06e+00

Pos logit contributions
 officer+0.170
 salon+0.140
ily+0.139
 ma+0.137
iza+0.136
Neg logit contributions
tails-0.262
Fel-0.250
Bet-0.246
 buzzing-0.237
June-0.233
Token out
Token ID503
Feature activation+2.74e+00

Pos logit contributions
 officer+0.262
 ma+0.215
 salon+0.210
 sir+0.207
ily+0.202
Neg logit contributions
Fel-0.380
tails-0.376
Bet-0.367
June-0.347
 buzzing-0.344
Token for
Token ID329
Feature activation+1.78e+00

Pos logit contributions
Fel+0.258
tails+0.254
Bet+0.248
June+0.235
 buzzing+0.234
Neg logit contributions
 officer-0.176
 ma-0.144
 salon-0.142
 sir-0.139
ily-0.135
Token little
Token ID1310
Feature activation-2.13e+00

Pos logit contributions
Fel+0.085
tails+0.084
Bet+0.084
June+0.080
 buzzing+0.079
Neg logit contributions
 officer-0.031
 ma-0.024
 salon-0.023
 kids-0.022
 sir-0.022
Token sister
Token ID6621
Feature activation+1.91e-01

Pos logit contributions
 officer+0.108
 ma+0.083
 salon+0.081
 sir+0.079
ily+0.076
Neg logit contributions
Fel-0.230
tails-0.227
Bet-0.223
June-0.212
 buzzing-0.211
Token watched
Token ID7342
Feature activation+8.90e-01

Pos logit contributions
Fel+0.019
tails+0.018
Bet+0.018
June+0.017
 buzzing+0.017
Neg logit contributions
 officer-0.012
 ma-0.009
 salon-0.009
 sir-0.009
ily-0.009
Token in
Token ID287
Feature activation-2.13e+00

Pos logit contributions
Fel+0.083
tails+0.082
Bet+0.080
June+0.076
 buzzing+0.075
Neg logit contributions
 officer-0.058
 ma-0.048
 salon-0.047
 sir-0.046
ily-0.045
Token amaz
Token ID40642
Feature activation+1.10e+00

Pos logit contributions
 officer+0.134
 ma+0.110
 salon+0.106
 kids+0.105
 sir+0.104
Neg logit contributions
Fel-0.204
tails-0.203
Bet-0.199
June-0.188
 buzzing-0.183
Tokenement
Token ID972
Feature activation-3.17e+00

Pos logit contributions
Fel+0.079
tails+0.075
 Louise+0.073
 webs+0.073
June+0.072
Neg logit contributions
 officer-0.093
 sir-0.078
 ma-0.075
line-0.073
 buy-0.073
Token.
Token ID13
Feature activation-6.17e-01

Pos logit contributions
 officer+0.196
 ma+0.156
 salon+0.152
 sir+0.150
iza+0.146
Neg logit contributions
tails-0.307
Fel-0.303
Bet-0.290
 buzzing-0.286
 Louise-0.279
Token She
Token ID1375
Feature activation+4.96e-01

Pos logit contributions
 officer+0.042
 ma+0.035
 salon+0.034
 sir+0.033
ily+0.033
Neg logit contributions
Fel-0.056
tails-0.055
Bet-0.054
June-0.051
 buzzing-0.050
Token climbed
Token ID19952
Feature activation-2.29e+00

Pos logit contributions
Fel+0.052
tails+0.052
Bet+0.051
June+0.048
 buzzing+0.047
Neg logit contributions
 officer-0.026
 ma-0.021
 salon-0.020
 sir-0.019
ily-0.019
Token up
Token ID510
Feature activation+1.96e+00

Pos logit contributions
 officer+0.102
 right+0.100
ily+0.087
 boy+0.083
 kids+0.082
Neg logit contributions
tails-0.236
Fel-0.234
Bet-0.234
June-0.220
oing-0.213
Token the
Token ID262
Feature activation-2.75e-01

Pos logit contributions
Fel+0.209
tails+0.208
Bet+0.203
June+0.194
 buzzing+0.187
Neg logit contributions
 officer-0.098
 salon-0.077
 ma-0.076
 accident-0.073
ily-0.072
Token friends
Token ID2460
Feature activation+2.33e+00

Pos logit contributions
Fel+0.169
tails+0.166
Bet+0.163
June+0.154
 buzzing+0.152
Neg logit contributions
 officer-0.109
 ma-0.089
 salon-0.086
 kids-0.086
 sir-0.086
Token and
Token ID290
Feature activation-2.43e-01

Pos logit contributions
Fel+0.227
tails+0.226
Bet+0.215
 buzzing+0.214
 Louise+0.208
Neg logit contributions
 officer-0.138
 ma-0.111
 salon-0.108
 sir-0.106
iza-0.103
Token new
Token ID649
Feature activation+1.74e+00

Pos logit contributions
 officer+0.016
 ma+0.013
 salon+0.013
 sir+0.013
iza+0.013
Neg logit contributions
tails-0.022
Fel-0.022
Bet-0.021
 buzzing-0.020
June-0.020
Token drawings
Token ID23388
Feature activation+1.13e-02

Pos logit contributions
Fel+0.167
tails+0.164
Bet+0.162
June+0.153
 buzzing+0.151
Neg logit contributions
 officer-0.109
 ma-0.088
 salon-0.086
 kids-0.086
 sir-0.085
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
tails+0.001
Fel+0.001
Bet+0.001
 buzzing+0.001
June+0.001
Neg logit contributions
 officer-0.001
 ma-0.001
 salon-0.001
 sir-0.001
iza-0.001
Token They
Token ID1119
Feature activation+9.24e-01

Pos logit contributions
 officer+0.015
 salon+0.013
 ma+0.013
 sir+0.012
 accident+0.012
Neg logit contributions
Fel-0.016
tails-0.016
Bet-0.015
June-0.014
 Louise-0.014
Token hold
Token ID1745
Feature activation+1.08e+00

Pos logit contributions
tails+0.081
Fel+0.079
Bet+0.074
 buzzing+0.072
 Louise+0.071
Neg logit contributions
 officer-0.061
 ma-0.052
 sir-0.052
ople-0.051
 salon-0.051
Token hands
Token ID2832
Feature activation+1.87e+00

Pos logit contributions
Fel+0.098
tails+0.096
Bet+0.094
June+0.089
 buzzing+0.088
Neg logit contributions
 officer-0.073
 ma-0.061
 salon-0.059
 sir-0.059
ily-0.056
Token and
Token ID290
Feature activation-2.21e-01

Pos logit contributions
Fel+0.188
tails+0.187
Bet+0.182
June+0.173
 buzzing+0.173
Neg logit contributions
 officer-0.106
 ma-0.085
 salon-0.083
 sir-0.081
ily-0.079
Token follow
Token ID1061
Feature activation-1.07e+00

Pos logit contributions
 officer+0.015
 ma+0.013
 salon+0.012
 sir+0.012
ily+0.012
Neg logit contributions
tails-0.020
Fel-0.020
Bet-0.019
 buzzing-0.018
June-0.018
Token the
Token ID262
Feature activation-2.48e-02

Pos logit contributions
 officer+0.064
 ma+0.051
 salon+0.050
 sir+0.049
 kids+0.048
Neg logit contributions
Fel-0.106
tails-0.104
Bet-0.102
June-0.097
 buzzing-0.096
Token catch
Token ID4929
Feature activation+4.38e+00

Pos logit contributions
 officer+0.040
 ma+0.033
 salon+0.032
 sir+0.032
 kids+0.031
Neg logit contributions
Fel-0.051
tails-0.050
Bet-0.049
June-0.046
 buzzing-0.046
Token flies
Token ID17607
Feature activation+3.88e+00

Pos logit contributions
Fel+0.454
tails+0.447
Bet+0.437
June+0.419
 Louise+0.409
Neg logit contributions
 officer-0.244
 kids-0.198
 ma-0.187
 sir-0.184
ily-0.183
Token and
Token ID290
Feature activation-4.73e-01

Pos logit contributions
Fel+0.405
tails+0.398
Bet+0.389
June+0.372
 Louise+0.366
Neg logit contributions
 officer-0.211
 ma-0.165
 sir-0.160
 salon-0.158
 kids-0.155
Token name
Token ID1438
Feature activation+2.53e+00

Pos logit contributions
 officer+0.032
 ma+0.026
 salon+0.026
 sir+0.025
 kids+0.025
Neg logit contributions
Fel-0.044
tails-0.042
Bet-0.041
June-0.039
 Louise-0.038
Token them
Token ID606
Feature activation-7.39e-01

Pos logit contributions
Fel+0.247
tails+0.244
Bet+0.239
June+0.226
 buzzing+0.224
Neg logit contributions
 officer-0.153
 ma-0.124
 salon-0.120
 sir-0.119
ily-0.115
Token.
Token ID13
Feature activation-3.79e-01

Pos logit contributions
 officer+0.035
 ma+0.027
 sir+0.026
 kids+0.026
 salon+0.024
Neg logit contributions
Fel-0.082
tails-0.080
Bet-0.080
June-0.076
 buzzing-0.075
Token But
Token ID887
Feature activation+9.44e-02

Pos logit contributions
 officer+0.026
 ma+0.022
 sir+0.022
 salon+0.021
 kids+0.021
Neg logit contributions
Fel-0.034
tails-0.033
Bet-0.032
June-0.030
 buzzing-0.030
Token it
Token ID340
Feature activation+9.38e-01

Pos logit contributions
Fel+0.008
tails+0.008
Bet+0.008
 buzzing+0.008
 Louise+0.008
Neg logit contributions
 officer-0.006
 salon-0.005
iza-0.005
 ma-0.005
ily-0.005
Token's
Token ID338
Feature activation+2.05e+00

Pos logit contributions
Fel+0.091
Bet+0.088
tails+0.087
June+0.083
 buzzing+0.078
Neg logit contributions
 officer-0.058
 kids-0.050
 ma-0.047
 sir-0.047
 accident-0.046
Token not
Token ID407
Feature activation-1.07e+00

Pos logit contributions
Fel+0.228
tails+0.221
Bet+0.215
June+0.206
 Louise+0.202
Neg logit contributions
 officer-0.100
 ma-0.080
 accident-0.078
ily-0.077
 kids-0.076
Token nice
Token ID3621
Feature activation-1.37e+00

Pos logit contributions
 officer+0.062
 ma+0.051
 sir+0.048
 salon+0.048
 kids+0.047
Neg logit contributions
Fel-0.108
tails-0.106
Bet-0.104
June-0.098
 Louise-0.097
Token
Token ID220
Feature activation-6.40e-01

Pos logit contributions
 officer+0.037
 salon+0.031
 ma+0.031
 sir+0.030
 accident+0.029
Neg logit contributions
Fel-0.043
tails-0.041
Bet-0.041
June-0.039
 Louise-0.038
Token
Token ID198
Feature activation+2.93e-01

Pos logit contributions
 officer+0.043
 ma+0.037
 sir+0.036
ily+0.035
 salon+0.035
Neg logit contributions
Fel-0.057
tails-0.057
Bet-0.055
 buzzing-0.053
June-0.052
Token
Token ID198
Feature activation+2.82e-01

Pos logit contributions
tails+0.027
Fel+0.026
Bet+0.025
 buzzing+0.024
June+0.024
Neg logit contributions
 officer-0.020
 ma-0.016
ily-0.016
 sir-0.016
 salon-0.016
TokenSetup
Token ID40786
Feature activation+2.18e+00

Pos logit contributions
tails+0.024
Fel+0.023
Bet+0.022
 buzzing+0.021
June+0.021
Neg logit contributions
 officer-0.021
 ma-0.018
 salon-0.017
 sir-0.017
ily-0.017
Token and
Token ID290
Feature activation-6.65e-01

Pos logit contributions
Fel+0.197
tails+0.196
Bet+0.187
 buzzing+0.180
 Louise+0.178
Neg logit contributions
 officer-0.145
 salon-0.122
 ma-0.121
 sir-0.114
iza-0.114
Token Pay
Token ID7119
Feature activation-1.01e+00

Pos logit contributions
 officer+0.043
 salon+0.036
 ma+0.035
 sir+0.035
ily+0.035
Neg logit contributions
tails-0.060
Fel-0.060
Bet-0.058
 Louise-0.056
June-0.055
Tokenoff
Token ID2364
Feature activation-5.24e+00

Pos logit contributions
 officer+0.073
 salon+0.065
 ma+0.063
 accident+0.059
 sir+0.059
Neg logit contributions
tails-0.085
Fel-0.081
Bet-0.075
 Louise-0.074
ches-0.074
Token:
Token ID25
Feature activation-1.38e-01

Pos logit contributions
 officer+0.341
 salon+0.287
 ma+0.284
 sir+0.272
ily+0.270
Neg logit contributions
tails-0.477
Fel-0.474
Bet-0.453
 buzzing-0.437
 Louise-0.432
Token The
Token ID383
Feature activation-8.99e-01

Pos logit contributions
 officer+0.009
 ma+0.008
 salon+0.007
 sir+0.007
ily+0.007
Neg logit contributions
Fel-0.013
tails-0.012
Bet-0.012
 buzzing-0.012
June-0.011
Token setup
Token ID9058
Feature activation-3.07e+00

Pos logit contributions
 officer+0.060
 salon+0.050
 ma+0.050
ily+0.049
iza+0.049
Neg logit contributions
tails-0.078
Fel-0.077
Bet-0.075
 buzzing-0.074
June-0.071
Token was
Token ID373
Feature activation+1.33e+00

Pos logit contributions
 officer+0.205
 ma+0.171
 salon+0.170
 sir+0.167
iza+0.161
Neg logit contributions
Fel-0.269
tails-0.268
Bet-0.256
 buzzing-0.250
June-0.245
Token sad
Token ID6507
Feature activation-1.99e+00

Pos logit contributions
tails+0.345
Fel+0.340
Bet+0.329
 buzzing+0.325
June+0.309
Neg logit contributions
 officer-0.224
 salon-0.185
 ma-0.184
 sir-0.175
ily-0.171
Token.
Token ID13
Feature activation+8.17e-02

Pos logit contributions
 officer+0.128
 salon+0.107
 ma+0.106
iza+0.103
 sir+0.101
Neg logit contributions
Fel-0.181
tails-0.180
 buzzing-0.175
Bet-0.173
 Louise-0.164
Token They
Token ID1119
Feature activation+1.01e+00

Pos logit contributions
Fel+0.007
tails+0.007
Bet+0.007
June+0.006
 buzzing+0.006
Neg logit contributions
 officer-0.006
 salon-0.005
 ma-0.005
 sir-0.005
iza-0.005
Token liked
Token ID8288
Feature activation-1.62e+00

Pos logit contributions
tails+0.095
Fel+0.094
Bet+0.090
 buzzing+0.088
June+0.085
Neg logit contributions
 officer-0.061
 salon-0.056
 ma-0.055
 sir-0.055
iza-0.050
Token the
Token ID262
Feature activation+1.18e-02

Pos logit contributions
 officer+0.109
 ma+0.089
 salon+0.088
iza+0.086
 sir+0.086
Neg logit contributions
tails-0.146
Fel-0.145
Bet-0.142
 buzzing-0.137
June-0.133
Token penny
Token ID26369
Feature activation-6.11e+00

Pos logit contributions
 buzzing+0.001
tails+0.001
 leaping+0.001
 flying+0.001
 snowball+0.001
Neg logit contributions
nes-0.001
ily-0.001
iza-0.001
ople-0.001
gan-0.001
Token.
Token ID13
Feature activation+1.04e-01

Pos logit contributions
 officer+0.334
 ma+0.264
 salon+0.257
 sir+0.252
ily+0.244
Neg logit contributions
Fel-0.633
tails-0.626
Bet-0.613
June-0.583
 buzzing-0.579
Token It
Token ID632
Feature activation-5.09e-01

Pos logit contributions
Fel+0.009
tails+0.009
Bet+0.009
June+0.008
 buzzing+0.008
Neg logit contributions
 officer-0.008
 ma-0.006
 salon-0.006
 sir-0.006
ily-0.006
Token was
Token ID373
Feature activation+1.82e+00

Pos logit contributions
 officer+0.031
 ma+0.024
ily+0.023
 salon+0.023
 accident+0.023
Neg logit contributions
Fel-0.051
tails-0.050
Bet-0.049
June-0.046
 Louise-0.046
Token shiny
Token ID22441
Feature activation-8.36e-01

Pos logit contributions
Fel+0.179
tails+0.178
Bet+0.174
 buzzing+0.165
June+0.165
Neg logit contributions
 officer-0.109
 ma-0.088
 salon-0.086
 sir-0.084
ily-0.081
Token and
Token ID290
Feature activation-5.75e-02

Pos logit contributions
 officer+0.071
iza+0.067
 salon+0.064
 ma+0.064
 sir+0.061
Neg logit contributions
 buzzing-0.054
 webs-0.052
tails-0.050
Fel-0.047
ches-0.047
Token follow
Token ID1061
Feature activation-9.59e-01

Pos logit contributions
 officer+0.025
 salon+0.021
 cubes+0.020
ople+0.020
 ma+0.019
Neg logit contributions
tails-0.035
Bet-0.033
Fel-0.032
 buzzing-0.031
 Louise-0.030
Token the
Token ID262
Feature activation+2.79e-01

Pos logit contributions
 officer+0.055
 ma+0.044
 salon+0.043
 sir+0.043
 kids+0.043
Neg logit contributions
Fel-0.096
tails-0.095
Bet-0.094
June-0.088
 buzzing-0.087
Token rules
Token ID3173
Feature activation-5.44e+00

Pos logit contributions
Fel+0.028
tails+0.027
 buzzing+0.026
Bet+0.026
June+0.026
Neg logit contributions
 officer-0.015
iza-0.013
ople-0.012
ily-0.012
 ma-0.012
Token.
Token ID13
Feature activation+6.17e-02

Pos logit contributions
 officer+0.355
 ma+0.303
 cash+0.291
 salon+0.290
iza+0.284
Neg logit contributions
Fel-0.463
tails-0.460
Bet-0.434
 Louise-0.432
 buzzing-0.431
Token The
Token ID383
Feature activation-3.84e-01

Pos logit contributions
Fel+0.005
Bet+0.005
tails+0.005
 Louise+0.004
June+0.004
Neg logit contributions
 officer-0.005
 salon-0.004
 ma-0.004
 cubes-0.004
 accident-0.004
Token attic
Token ID46113
Feature activation-4.95e+00

Pos logit contributions
 officer+0.023
iza+0.021
ople+0.020
 sir+0.020
line+0.020
Neg logit contributions
Fel-0.034
tails-0.033
 buzzing-0.032
 webs-0.032
Bet-0.032
Token is
Token ID318
Feature activation+1.49e+00

Pos logit contributions
 officer+0.426
 ma+0.379
iza+0.378
 sir+0.366
ily+0.364
Neg logit contributions
tails-0.326
Fel-0.300
 buzzing-0.292
 webs-0.285
Bet-0.283
Token not
Token ID407
Feature activation-9.79e-01

Pos logit contributions
tails+0.138
Fel+0.137
Bet+0.134
 buzzing+0.129
June+0.126
Neg logit contributions
 officer-0.096
 salon-0.078
 ma-0.077
 sir-0.075
iza-0.074
Token a
Token ID257
Feature activation-2.63e-02

Pos logit contributions
 officer+0.073
 salon+0.066
iza+0.064
ople+0.063
 cash+0.062
Neg logit contributions
tails-0.078
 buzzing-0.074
Bet-0.072
Fel-0.070
 Louise-0.069
Token place
Token ID1295
Feature activation+5.99e-01

Pos logit contributions
 officer+0.002
 ma+0.001
 salon+0.001
 sir+0.001
 kids+0.001
Neg logit contributions
Fel-0.002
tails-0.002
Bet-0.002
June-0.002
 buzzing-0.002
Token for
Token ID329
Feature activation+1.87e+00

Pos logit contributions
tails+0.048
 buzzing+0.046
Fel+0.045
Bet+0.044
 webs+0.044
Neg logit contributions
 officer-0.042
 cash-0.035
 ma-0.035
 salon-0.035
iza-0.035
Token One
Token ID1881
Feature activation-9.22e-01

Pos logit contributions
 officer+0.006
 ma+0.005
 sir+0.005
 salon+0.005
ily+0.005
Neg logit contributions
tails-0.008
Fel-0.008
Bet-0.008
 buzzing-0.007
June-0.007
Token day
Token ID1110
Feature activation+5.97e-01

Pos logit contributions
 officer+0.067
 salon+0.056
 ma+0.055
 sir+0.053
ily+0.052
Neg logit contributions
Fel-0.078
tails-0.077
Bet-0.076
 buzzing-0.074
 Louise-0.072
Token he
Token ID339
Feature activation-1.08e+00

Pos logit contributions
tails+0.063
Fel+0.062
Bet+0.061
June+0.059
 buzzing+0.058
Neg logit contributions
 officer-0.031
 ma-0.025
 sir-0.024
 kids-0.024
ily-0.023
Token saw
Token ID2497
Feature activation+1.04e+00

Pos logit contributions
 officer+0.070
 salon+0.061
 ma+0.060
 sir+0.057
ily+0.055
Neg logit contributions
Fel-0.098
tails-0.097
Bet-0.095
 buzzing-0.091
 Louise-0.089
Token a
Token ID257
Feature activation-1.97e-01

Pos logit contributions
Fel+0.096
tails+0.094
Bet+0.092
 buzzing+0.088
 Louise+0.087
Neg logit contributions
 officer-0.068
 ma-0.057
 salon-0.057
 sir-0.054
iza-0.052
Token wreck
Token ID15228
Feature activation-6.89e+00

Pos logit contributions
 officer+0.013
 ma+0.011
 sir+0.011
 salon+0.010
 kids+0.010
Neg logit contributions
Fel-0.019
tails-0.018
Bet-0.018
June-0.017
 Louise-0.017
Token that
Token ID326
Feature activation-5.30e-01

Pos logit contributions
 officer+0.450
 ma+0.392
 salon+0.373
 sir+0.371
iza+0.359
Neg logit contributions
tails-0.599
Fel-0.599
 buzzing-0.598
Bet-0.574
 leaping-0.546
Token was
Token ID373
Feature activation+1.46e+00

Pos logit contributions
 officer+0.039
 salon+0.034
 ma+0.033
 sir+0.032
iza+0.031
Neg logit contributions
Fel-0.044
tails-0.043
Bet-0.042
 buzzing-0.041
 Louise-0.040
Token underwater
Token ID21258
Feature activation+1.30e+00

Pos logit contributions
 buzzing+0.108
tails+0.107
Fel+0.106
Bet+0.102
 leaping+0.098
Neg logit contributions
 officer-0.116
 salon-0.102
 ma-0.102
ople-0.101
ily-0.099
Token.
Token ID13
Feature activation-3.20e-01

Pos logit contributions
Fel+0.116
tails+0.116
Bet+0.112
 buzzing+0.110
June+0.104
Neg logit contributions
 officer-0.088
 ma-0.073
 salon-0.073
 sir-0.069
ily-0.069
Token He
Token ID679
Feature activation-1.36e+00

Pos logit contributions
 officer+0.019
 salon+0.015
 ma+0.015
 sir+0.015
ily+0.014
Neg logit contributions
Fel-0.032
tails-0.031
Bet-0.031
June-0.029
 Louise-0.029
Token,
Token ID11
Feature activation-3.56e-01

Pos logit contributions
 officer+0.249
 ma+0.206
 salon+0.202
 sir+0.199
iza+0.198
Neg logit contributions
tails-0.318
Fel-0.316
Bet-0.306
 Louise-0.292
 buzzing-0.291
Token she
Token ID673
Feature activation+1.55e+00

Pos logit contributions
 officer+0.027
 ma+0.023
 sir+0.023
 salon+0.022
ople+0.022
Neg logit contributions
Fel-0.030
tails-0.029
Bet-0.028
 buzzing-0.026
 Louise-0.026
Token saw
Token ID2497
Feature activation+9.08e-01

Pos logit contributions
Fel+0.168
tails+0.166
Bet+0.163
June+0.156
 buzzing+0.154
Neg logit contributions
 officer-0.077
 ma-0.058
 salon-0.056
 kids-0.055
 sir-0.054
Token a
Token ID257
Feature activation-3.44e-01

Pos logit contributions
Fel+0.096
tails+0.094
Bet+0.092
June+0.087
 buzzing+0.086
Neg logit contributions
 officer-0.049
 ma-0.038
 kids-0.037
ily-0.037
 salon-0.037
Token kindly
Token ID26820
Feature activation-9.09e-01

Pos logit contributions
 officer+0.021
 ma+0.017
 salon+0.017
 sir+0.017
 kids+0.016
Neg logit contributions
Fel-0.034
tails-0.034
Bet-0.033
June-0.031
 Louise-0.031
Token old
Token ID1468
Feature activation-5.11e+00

Pos logit contributions
 officer+0.047
ily+0.038
 salon+0.037
 ma+0.037
ople+0.037
Neg logit contributions
tails-0.091
Fel-0.090
Bet-0.088
 buzzing-0.087
 Louise-0.084
Token man
Token ID582
Feature activation-3.35e+00

Pos logit contributions
 officer+0.262
ily+0.222
iza+0.217
 ma+0.213
ople+0.211
Neg logit contributions
tails-0.520
Fel-0.505
Bet-0.497
 buzzing-0.493
 Louise-0.475
Token.
Token ID13
Feature activation-5.87e-01

Pos logit contributions
 officer+0.233
 ma+0.195
 salon+0.191
 sir+0.189
ily+0.184
Neg logit contributions
Fel-0.296
tails-0.292
Bet-0.285
June-0.269
 buzzing-0.267
Token He
Token ID679
Feature activation-1.64e+00

Pos logit contributions
 officer+0.039
 salon+0.034
 accident+0.033
ople+0.033
ateful+0.032
Neg logit contributions
Fel-0.053
tails-0.051
Bet-0.050
 Louise-0.047
 buzzing-0.046
Token wanted
Token ID2227
Feature activation-2.34e+00

Pos logit contributions
 officer+0.092
 ma+0.070
 sir+0.066
 kids+0.065
 salon+0.065
Neg logit contributions
Fel-0.170
tails-0.167
Bet-0.164
June-0.155
 buzzing-0.154
Token to
Token ID284
Feature activation-6.64e-01

Pos logit contributions
 officer+0.145
 ma+0.123
 salon+0.120
 sir+0.117
iza+0.115
Neg logit contributions
tails-0.218
Fel-0.218
Bet-0.213
June-0.202
 Louise-0.201
Token great
Token ID1049
Feature activation+3.67e+00

Pos logit contributions
 officer+0.015
 ma+0.013
 salon+0.013
 kids+0.013
 boy+0.013
Neg logit contributions
tails-0.015
Fel-0.014
Bet-0.014
June-0.013
 Louise-0.013
Token time
Token ID640
Feature activation-3.04e-01

Pos logit contributions
Fel+0.369
tails+0.364
Bet+0.356
June+0.338
 buzzing+0.336
Neg logit contributions
 officer-0.214
 ma-0.173
 salon-0.168
 sir-0.165
ily-0.160
Token.
Token ID13
Feature activation-9.01e-02

Pos logit contributions
 officer+0.018
 ma+0.015
 kids+0.014
 salon+0.014
 sir+0.014
Neg logit contributions
Fel-0.030
tails-0.030
Bet-0.029
June-0.028
 Louise-0.027
Token<|endoftext|>
Token ID50256
Feature activation+7.76e-01

Pos logit contributions
 officer+0.007
 salon+0.006
 ma+0.006
 sir+0.006
iza+0.006
Neg logit contributions
Fel-0.007
Bet-0.007
tails-0.007
June-0.006
 Louise-0.006
TokenL
Token ID43
Feature activation-2.93e+00

Pos logit contributions
tails+0.068
Fel+0.067
Bet+0.065
June+0.061
 buzzing+0.061
Neg logit contributions
 officer-0.054
 ma-0.045
ily-0.045
 kids-0.044
 salon-0.044
Tokenily
Token ID813
Feature activation-5.93e+00

Pos logit contributions
 officer+0.206
 ma+0.171
 sir+0.171
nam+0.167
 salon+0.165
Neg logit contributions
Fel-0.232
tails-0.227
Bet-0.223
ches-0.220
 Louise-0.215
Token and
Token ID290
Feature activation-4.50e-01

Pos logit contributions
 officer+0.395
 sir+0.332
 ma+0.327
 salon+0.322
iza+0.298
Neg logit contributions
tails-0.531
Fel-0.530
Bet-0.513
 buzzing-0.488
 Louise-0.487
Token Tom
Token ID4186
Feature activation-1.54e+00

Pos logit contributions
 officer+0.032
 salon+0.029
line+0.027
 ma+0.027
 sir+0.027
Neg logit contributions
tails-0.038
Bet-0.037
Fel-0.036
 Louise-0.035
June-0.035
Token were
Token ID547
Feature activation-2.17e+00

Pos logit contributions
 officer+0.103
 salon+0.093
 sir+0.091
 ma+0.088
line+0.085
Neg logit contributions
tails-0.135
Fel-0.130
Bet-0.129
 buzzing-0.118
June-0.117
Token twins
Token ID20345
Feature activation-2.01e+00

Pos logit contributions
 officer+0.159
 ma+0.134
 salon+0.131
 sir+0.130
ily+0.126
Neg logit contributions
Fel-0.185
tails-0.183
Bet-0.178
June-0.167
 buzzing-0.167
Token.
Token ID13
Feature activation-3.54e-01

Pos logit contributions
 officer+0.133
 ma+0.116
ily+0.115
 sir+0.111
ateful+0.109
Neg logit contributions
tails-0.175
Fel-0.164
 buzzing-0.163
Bet-0.158
elope-0.152