TOP ACTIVATIONS
MAX = 15.017

Some people live on y ach ts and travel around the
grabbed a handful and happily mun ched away . The popcorn
, Sam the se ah orse . Fin said
They both grabbed their lun ches . Ell a had
happy and proud of his discovery . <|endoftext|> Once upon a
to eat . The bear mun ched the juicy green sa
on one of the y ach ts . He knew he
feeling very pleased by his discovery . <|endoftext|> Once there was
started to eat . They mun ched and cr un ched
was so proud of his discovery and hurried back to his
to have made this intelligent discovery . <|endoftext|> Once there was
to have made this exciting discovery . She ran back home
was so happy with her discovery and for the rest of
loved to watch the y ach ts on the water .
so proud of her new discovery and she wanted to keep
, thankful for her incredible discovery . <|endoftext|> M ummy was
. The cater pillar happily mun ched on the mushroom ,
played tag and shared their lun ches . Molly had fair
girl was overwhelmed with the discovery . She protected the nest
little girl was thrilled and mun ched away happily .

MIN ACTIVATIONS
MIN = -15.501

a broom and a dust pan and start to clean the
m op and a dust pan and cleaned up the dough
a broom and a dust pan . You have to clean
of paper and a dust pan and they cleaned up the
her little broom and dust pan , trying to get all
a broom and a dust pan . " Can
a broom and a dust pan . They help him sweep
a broom and a dust pan to clean up the mess
word : pin . He decides not to play with pins
for the elephant . She decides to teach him some things
judge is a person who decides who is right and who
a bad friend . She decides to teach him a lesson
is uncomfortable , so she decides to stay in her bed
red dress , but she decides to t uck the cord
a little better . He decides to try . He pushes
One day , Sara decides to make the box into
back . He decides to look for a real
best book ever . She decides to read it again tomorrow
under the couch . She decides to be nice and help
." L ily decides to show Ben how to

INTERVAL 7.387 - 15.017
CONTAINS 1.373%

After the nap , the baby felt much
to play . <|endoftext|> Once upon a time , in a
Thank you , Billy !" Tim my said . " You
explore . One day , Joe went for a walk in
sleep well . Tim my did not believe Mom

INTERVAL -0.242 - 7.387
CONTAINS 58.154%

to see my book ? It is about animals . I
Ben says , cl apping his hands . " And I
for you !" The little boy was so excited
prisoner now !" it said . J ill was
be flexible and do different things for fun . That 's

INTERVAL -7.872 - -0.242
CONTAINS 39.084%

have fun ." " By e , mom .
moment . He was very glad he noticed his wife .
there was a silver thing far away . So the mouse
And maybe later , we can play dress up with your
ama bear said yes . She was a kind , obedient

INTERVAL -15.501 - -7.872
CONTAINS 1.389%

asked her mom , " Can you show me some animals
Tom hugged her back and said , " It
and laughed . They cut out their favorite pictures and glued
They went to the store and found a pretty pink
brave cat , so he slowly opened the box .
Token Some
Token ID2773
Feature activation-5.87e+00

Pos logit contributions
orse+0.049
oc+0.037
 weapon+0.036
 bone+0.035
 Carl+0.034
Neg logit contributions
 groom-0.056
 register-0.052
 roses-0.051
 decides-0.049
 ponies-0.049
Token people
Token ID661
Feature activation-2.96e+00

Pos logit contributions
 groom+0.270
 roses+0.251
 decides+0.237
 register+0.232
 ponies+0.229
Neg logit contributions
orse-0.422
oc-0.348
 weapon-0.346
uddy-0.343
 Carl-0.336
Token live
Token ID2107
Feature activation+4.04e+00

Pos logit contributions
 groom+0.148
 roses+0.135
 register+0.130
 decides+0.129
 ponies+0.123
Neg logit contributions
orse-0.202
 weapon-0.164
oc-0.163
 bone-0.156
uddy-0.156
Token on
Token ID319
Feature activation-2.27e+00

Pos logit contributions
orse+0.252
 weapon+0.200
oc+0.197
 bone+0.189
oy+0.188
Neg logit contributions
 groom-0.226
 register-0.205
 roses-0.205
 decides-0.197
 ponies-0.193
Token y
Token ID331
Feature activation+4.41e+00

Pos logit contributions
 groom+0.122
 register+0.113
 roses+0.110
 decides+0.109
 ponies+0.102
Neg logit contributions
orse-0.144
 weapon-0.115
oc-0.114
 bone-0.111
 hockey-0.110
Tokenach
Token ID620
Feature activation+1.36e+01

Pos logit contributions
orse+0.285
 weapon+0.227
oc+0.226
uddy+0.216
ggy+0.216
Neg logit contributions
 groom-0.235
 roses-0.224
 register-0.214
 decides-0.212
 ponies-0.204
Tokents
Token ID912
Feature activation+4.46e+00

Pos logit contributions
orse+0.853
 weapon+0.667
oc+0.665
 bone+0.629
oy+0.628
Neg logit contributions
 groom-0.755
 roses-0.696
 register-0.684
 decides-0.669
 ponies-0.648
Token and
Token ID290
Feature activation+5.43e-01

Pos logit contributions
orse+0.286
 weapon+0.228
oc+0.226
 bone+0.215
uddy+0.215
Neg logit contributions
 groom-0.241
 roses-0.223
 register-0.215
 decides-0.213
 ponies-0.206
Token travel
Token ID3067
Feature activation+2.58e+00

Pos logit contributions
orse+0.034
 weapon+0.027
oc+0.027
 bone+0.025
 Carl+0.025
Neg logit contributions
 groom-0.030
 roses-0.028
 register-0.027
 decides-0.027
 ponies-0.026
Token around
Token ID1088
Feature activation-2.14e+00

Pos logit contributions
orse+0.155
 weapon+0.124
oc+0.123
 bone+0.118
oy+0.116
Neg logit contributions
 groom-0.150
 roses-0.137
 register-0.136
 decides-0.131
 ponies-0.127
Token the
Token ID262
Feature activation+6.77e-01

Pos logit contributions
 groom+0.113
 roses+0.103
 register+0.102
 decides+0.099
 ponies+0.095
Neg logit contributions
orse-0.140
 weapon-0.111
oc-0.111
 bone-0.105
 Carl-0.104
Token grabbed
Token ID13176
Feature activation+1.78e+00

Pos logit contributions
 groom+0.078
 roses+0.070
 register+0.069
 decides+0.068
 ponies+0.065
Neg logit contributions
orse-0.087
 weapon-0.070
oc-0.067
uddy-0.066
 Carl-0.065
Token a
Token ID257
Feature activation+4.59e-01

Pos logit contributions
orse+0.107
oc+0.086
 bone+0.084
 weapon+0.084
 Carl+0.083
Neg logit contributions
 groom-0.099
 register-0.091
 roses-0.091
 decides-0.090
 ponies-0.085
Token handful
Token ID10089
Feature activation+2.61e+00

Pos logit contributions
orse+0.029
 weapon+0.023
 Carl+0.023
 Andy+0.023
uddy+0.022
Neg logit contributions
 groom-0.026
 roses-0.023
 register-0.022
 decides-0.021
 ponies-0.020
Token and
Token ID290
Feature activation+3.75e-01

Pos logit contributions
orse+0.135
 weapon+0.100
oc+0.099
ggy+0.092
 bone+0.092
Neg logit contributions
 groom-0.175
 roses-0.165
 register-0.162
 decides-0.159
 ponies-0.154
Token happily
Token ID18177
Feature activation-1.54e+00

Pos logit contributions
orse+0.024
 weapon+0.020
oc+0.019
uddy+0.019
unch+0.019
Neg logit contributions
 groom-0.020
 roses-0.019
 decides-0.018
 register-0.018
 ponies-0.017
Token mun
Token ID29856
Feature activation+1.33e+01

Pos logit contributions
 groom+0.087
 roses+0.079
 register+0.077
 decides+0.076
 ponies+0.072
Neg logit contributions
orse-0.095
 weapon-0.077
oc-0.075
 bone-0.072
uddy-0.072
Tokenched
Token ID1740
Feature activation+3.05e-03

Pos logit contributions
orse+0.691
oc+0.503
 weapon+0.488
 hockey+0.472
 puck+0.466
Neg logit contributions
 groom-0.887
 roses-0.830
 ponies-0.806
 decides-0.802
 register-0.799
Token away
Token ID1497
Feature activation-2.89e+00

Pos logit contributions
orse+0.000
 weapon+0.000
oc+0.000
 bone+0.000
uddy+0.000
Neg logit contributions
 groom-0.000
 roses-0.000
 register-0.000
 decides-0.000
 ponies-0.000
Token.
Token ID13
Feature activation+8.52e-01

Pos logit contributions
 groom+0.150
 roses+0.139
 register+0.133
 decides+0.128
 ponies+0.127
Neg logit contributions
orse-0.196
 weapon-0.157
oc-0.155
uddy-0.151
 bone-0.148
Token The
Token ID383
Feature activation+3.39e+00

Pos logit contributions
orse+0.045
 weapon+0.033
oc+0.033
 bone+0.031
uddy+0.031
Neg logit contributions
 groom-0.056
 roses-0.053
 register-0.052
 decides-0.051
 ponies-0.050
Token popcorn
Token ID38914
Feature activation+1.57e+00

Pos logit contributions
orse+0.220
 weapon+0.179
oc+0.174
 bone+0.174
 hockey+0.171
Neg logit contributions
 groom-0.175
 roses-0.162
 decides-0.158
 register-0.153
 ponies-0.148
Token,
Token ID11
Feature activation-1.64e-01

Pos logit contributions
orse+0.258
oc+0.220
inations+0.209
 weapon+0.202
unch+0.200
Neg logit contributions
 groom-0.187
 roses-0.181
 her-0.166
 decides-0.166
 register-0.162
Token Sam
Token ID3409
Feature activation+7.25e+00

Pos logit contributions
 groom+0.007
 roses+0.007
 her+0.006
 Angel+0.006
 herself+0.006
Neg logit contributions
oc-0.012
orse-0.011
inations-0.010
oy-0.010
rd-0.010
Token the
Token ID262
Feature activation+5.37e-01

Pos logit contributions
orse+0.458
oc+0.373
 weapon+0.368
unch+0.352
 puck+0.351
Neg logit contributions
 groom-0.392
 roses-0.367
 decides-0.348
 register-0.347
 ponies-0.334
Token se
Token ID384
Feature activation+1.56e+00

Pos logit contributions
orse+0.037
oc+0.033
uddy+0.030
anas+0.029
oy+0.029
Neg logit contributions
 groom-0.028
 roses-0.026
 decides-0.025
 mirror-0.024
 register-0.022
Tokenah
Token ID993
Feature activation+6.28e+00

Pos logit contributions
orse+0.084
 Andy+0.067
 Carl+0.067
 burying+0.065
 puck+0.065
Neg logit contributions
 groom-0.089
 decides-0.084
 register-0.080
 roses-0.078
 ponies-0.075
Tokenorse
Token ID7615
Feature activation+1.33e+01

Pos logit contributions
igsaw+0.314
uddy+0.288
 Timothy+0.278
Johnny+0.272
Jerry+0.270
Neg logit contributions
 roses-0.342
 groom-0.331
 decides-0.316
 rose-0.300
 back-0.295
Token.
Token ID13
Feature activation+9.31e-01

Pos logit contributions
orse+0.869
oc+0.747
 puck+0.715
unch+0.705
 weapon+0.702
Neg logit contributions
 groom-0.641
 roses-0.600
 decides-0.585
 register-0.552
 ponies-0.522
Token
Token ID198
Feature activation+7.06e-01

Pos logit contributions
orse+0.062
inations+0.053
oc+0.051
 weapon+0.051
ggy+0.050
Neg logit contributions
 decides-0.042
 groom-0.039
 roses-0.038
als-0.036
She-0.036
Token
Token ID198
Feature activation+7.23e-01

Pos logit contributions
orse+0.046
 weapon+0.042
 puck+0.039
 bullets+0.039
oc+0.038
Neg logit contributions
 groom-0.028
 roses-0.028
She-0.027
 decides-0.027
 Angel-0.026
TokenFin
Token ID18467
Feature activation+8.77e+00

Pos logit contributions
orse+0.043
inations+0.033
 burying+0.033
 weapon+0.032
unch+0.031
Neg logit contributions
She-0.037
 decides-0.037
 groom-0.037
 roses-0.034
als-0.033
Token said
Token ID531
Feature activation+3.52e+00

Pos logit contributions
orse+0.557
unch+0.489
 weapon+0.465
 importantly+0.452
oc+0.447
Neg logit contributions
 groom-0.447
 decides-0.425
 roses-0.401
 ponies-0.350
 Angel-0.349
Token
Token ID198
Feature activation+6.72e-01

Pos logit contributions
orse+0.037
 weapon+0.030
oc+0.028
 bone+0.027
 puck+0.027
Neg logit contributions
 groom-0.040
 roses-0.038
 decides-0.037
 register-0.036
 ponies-0.035
TokenThey
Token ID2990
Feature activation-7.91e-01

Pos logit contributions
orse+0.040
oc+0.032
 weapon+0.031
ggy+0.030
uddy+0.030
Neg logit contributions
 groom-0.039
 roses-0.036
 register-0.036
 decides-0.035
 ponies-0.034
Token both
Token ID1111
Feature activation+1.66e-01

Pos logit contributions
 groom+0.045
 roses+0.042
 register+0.041
 decides+0.040
 ponies+0.040
Neg logit contributions
orse-0.048
oc-0.038
 weapon-0.038
 bone-0.036
oy-0.036
Token grabbed
Token ID13176
Feature activation+1.97e+00

Pos logit contributions
orse+0.010
 weapon+0.008
oc+0.008
 bone+0.008
uddy+0.007
Neg logit contributions
 groom-0.010
 roses-0.009
 decides-0.009
 register-0.009
 ponies-0.008
Token their
Token ID511
Feature activation+7.79e-01

Pos logit contributions
orse+0.122
 weapon+0.099
 Carl+0.098
oc+0.097
 bone+0.097
Neg logit contributions
 groom-0.107
 register-0.097
 decides-0.096
 roses-0.095
 ponies-0.090
Token lun
Token ID14678
Feature activation+1.32e+01

Pos logit contributions
orse+0.056
oc+0.047
unch+0.045
uddy+0.044
 weapon+0.043
Neg logit contributions
 roses-0.034
 groom-0.033
 decides-0.032
 ponies-0.030
 back-0.029
Tokenches
Token ID2052
Feature activation-5.73e-01

Pos logit contributions
orse+0.871
 weapon+0.698
oc+0.689
 bone+0.660
uddy+0.651
Neg logit contributions
 groom-0.707
 roses-0.652
 register-0.627
 decides-0.623
 ponies-0.602
Token.
Token ID13
Feature activation+9.97e-01

Pos logit contributions
 groom+0.025
 register+0.024
 roses+0.024
 ponies+0.022
 decides+0.021
Neg logit contributions
orse-0.042
oc-0.034
unch-0.032
 weapon-0.032
inations-0.032
Token Ell
Token ID7122
Feature activation+1.46e-01

Pos logit contributions
orse+0.051
oc+0.040
 Carl+0.038
 weapon+0.038
 Andy+0.038
Neg logit contributions
 groom-0.065
 roses-0.060
 register-0.060
 decides-0.058
 ponies-0.057
Tokena
Token ID64
Feature activation+2.20e+00

Pos logit contributions
orse+0.010
oc+0.008
ggy+0.008
 weapon+0.007
uddy+0.007
Neg logit contributions
 groom-0.007
 roses-0.007
 register-0.007
 decides-0.006
 ponies-0.006
Token had
Token ID550
Feature activation+4.48e+00

Pos logit contributions
orse+0.131
 weapon+0.102
oc+0.100
 bone+0.095
uddy+0.094
Neg logit contributions
 groom-0.130
 roses-0.121
 register-0.117
 decides-0.116
 ponies-0.112
Token happy
Token ID3772
Feature activation+4.04e+00

Pos logit contributions
 groom+0.015
 roses+0.015
 register+0.014
 ponies+0.014
 decides+0.014
Neg logit contributions
orse-0.022
oc-0.018
unch-0.017
 weapon-0.017
uddy-0.017
Token and
Token ID290
Feature activation+2.40e+00

Pos logit contributions
orse+0.261
oc+0.215
 weapon+0.210
uddy+0.204
unch+0.200
Neg logit contributions
 groom-0.218
 roses-0.203
 decides-0.190
 ponies-0.187
 register-0.185
Token proud
Token ID6613
Feature activation+1.46e+00

Pos logit contributions
orse+0.146
oc+0.115
 weapon+0.115
uddy+0.108
 bone+0.108
Neg logit contributions
 groom-0.139
 roses-0.128
 decides-0.124
 register-0.124
 ponies-0.119
Token of
Token ID286
Feature activation+3.16e+00

Pos logit contributions
orse+0.094
oc+0.077
 weapon+0.075
uddy+0.073
 puck+0.073
Neg logit contributions
 groom-0.079
 roses-0.076
 ponies-0.070
 decides-0.069
 register-0.069
Token his
Token ID465
Feature activation+5.97e+00

Pos logit contributions
orse+0.244
 weapon+0.202
oc+0.200
 bone+0.194
 Carl+0.193
Neg logit contributions
 groom-0.131
 roses-0.117
 register-0.114
 decides-0.111
 ponies-0.105
Token discovery
Token ID9412
Feature activation+1.32e+01

Pos logit contributions
orse+0.371
oc+0.292
unch+0.286
uddy+0.282
 Carl+0.274
Neg logit contributions
 groom-0.338
 roses-0.319
 ponies-0.301
 decides-0.300
 register-0.299
Token.
Token ID13
Feature activation+1.07e+00

Pos logit contributions
orse+0.908
oc+0.696
unch+0.691
 weapon+0.688
uddy+0.672
Neg logit contributions
 groom-0.638
 register-0.626
 roses-0.615
 ponies-0.585
 decides-0.579
Token<|endoftext|>
Token ID50256
Feature activation+5.84e+00

Pos logit contributions
orse+0.060
 weapon+0.049
ggy+0.045
oy+0.045
inations+0.045
Neg logit contributions
 groom-0.062
 decides-0.059
 roses-0.058
 register-0.057
 Angel-0.057
TokenOnce
Token ID7454
Feature activation+3.95e+00

Pos logit contributions
orse+0.383
 weapon+0.307
oc+0.295
oy+0.287
 puck+0.285
Neg logit contributions
 groom-0.294
 roses-0.282
 decides-0.272
 register-0.272
 ponies-0.262
Token upon
Token ID2402
Feature activation+8.27e+00

Pos logit contributions
orse+0.235
oc+0.199
 weapon+0.188
anas+0.185
 puck+0.184
Neg logit contributions
 groom-0.208
 roses-0.201
 register-0.197
 decides-0.195
 ponies-0.188
Token a
Token ID257
Feature activation+3.34e-01

Pos logit contributions
orse+0.667
oc+0.591
uddy+0.583
 weapon+0.561
oy+0.546
Neg logit contributions
 groom-0.293
 roses-0.261
 herself-0.248
 her-0.245
 ponies-0.242
Token to
Token ID284
Feature activation+9.15e-01

Pos logit contributions
 groom+0.224
 roses+0.211
 decides+0.188
 ponies+0.185
 register+0.180
Neg logit contributions
orse-0.313
oc-0.255
 weapon-0.255
uddy-0.245
 bone-0.241
Token eat
Token ID4483
Feature activation+2.11e+00

Pos logit contributions
orse+0.055
 weapon+0.043
oc+0.043
 bone+0.041
uddy+0.040
Neg logit contributions
 groom-0.053
 roses-0.050
 register-0.048
 decides-0.048
 ponies-0.046
Token.
Token ID13
Feature activation+6.63e-01

Pos logit contributions
orse+0.129
oc+0.103
 weapon+0.103
 bone+0.099
 Carl+0.097
Neg logit contributions
 groom-0.120
 roses-0.109
 register-0.109
 decides-0.107
 ponies-0.103
Token The
Token ID383
Feature activation+3.20e+00

Pos logit contributions
orse+0.037
 weapon+0.029
oc+0.028
 bone+0.027
uddy+0.026
Neg logit contributions
 groom-0.041
 roses-0.039
 register-0.038
 decides-0.037
 ponies-0.036
Token bear
Token ID6842
Feature activation+5.88e-01

Pos logit contributions
orse+0.224
 weapon+0.181
oc+0.179
 bone+0.171
uddy+0.171
Neg logit contributions
 groom-0.158
 roses-0.145
 register-0.139
 decides-0.137
 ponies-0.133
Token mun
Token ID29856
Feature activation+1.32e+01

Pos logit contributions
orse+0.034
 weapon+0.028
unch+0.027
uddy+0.026
 puck+0.026
Neg logit contributions
 groom-0.034
 roses-0.031
 decides-0.031
 register-0.028
 ponies-0.028
Tokenched
Token ID1740
Feature activation-1.19e-01

Pos logit contributions
orse+0.654
oc+0.485
 weapon+0.464
 bone+0.440
unch+0.440
Neg logit contributions
 groom-0.918
 roses-0.852
 register-0.834
 ponies-0.831
 decides-0.822
Token the
Token ID262
Feature activation+3.79e-01

Pos logit contributions
 groom+0.005
 roses+0.005
 register+0.005
 decides+0.005
 ponies+0.004
Neg logit contributions
orse-0.009
 weapon-0.007
oc-0.007
 bone-0.007
uddy-0.007
Token juicy
Token ID35075
Feature activation+1.71e+00

Pos logit contributions
orse+0.025
 weapon+0.019
oc+0.019
 bone+0.018
uddy+0.018
Neg logit contributions
 groom-0.021
 roses-0.019
 register-0.018
 decides-0.018
 ponies-0.018
Token green
Token ID4077
Feature activation-7.70e-01

Pos logit contributions
orse+0.104
oc+0.085
 weapon+0.083
 bone+0.081
 hockey+0.078
Neg logit contributions
 groom-0.097
 register-0.088
 decides-0.087
 roses-0.086
 ponies-0.083
Token sa
Token ID473
Feature activation-1.16e-01

Pos logit contributions
 groom+0.042
 roses+0.038
 register+0.038
 decides+0.038
 ponies+0.036
Neg logit contributions
orse-0.049
oc-0.039
 weapon-0.039
 bone-0.037
oy-0.036
Token on
Token ID319
Feature activation-2.73e+00

Pos logit contributions
orse+0.435
oc+0.346
 weapon+0.339
uddy+0.335
unch+0.331
Neg logit contributions
 groom-0.338
 roses-0.312
 register-0.295
 decides-0.293
 ponies-0.287
Token one
Token ID530
Feature activation-4.44e+00

Pos logit contributions
 groom+0.119
 roses+0.114
 ponies+0.103
 decides+0.100
 register+0.098
Neg logit contributions
orse-0.206
uddy-0.171
oc-0.171
 weapon-0.164
unch-0.164
Token of
Token ID286
Feature activation+1.87e+00

Pos logit contributions
 groom+0.229
 roses+0.212
 register+0.203
 decides+0.194
 ponies+0.191
Neg logit contributions
orse-0.287
oc-0.233
 weapon-0.227
uddy-0.227
unch-0.223
Token the
Token ID262
Feature activation+1.51e-01

Pos logit contributions
orse+0.125
 weapon+0.100
oc+0.100
 bone+0.095
uddy+0.094
Neg logit contributions
 groom-0.098
 roses-0.090
 register-0.087
 decides-0.086
 ponies-0.083
Token y
Token ID331
Feature activation+3.99e+00

Pos logit contributions
orse+0.010
oc+0.008
uddy+0.008
 weapon+0.008
unch+0.008
Neg logit contributions
 groom-0.008
 roses-0.008
 register-0.007
 decides-0.007
 ponies-0.007
Tokenach
Token ID620
Feature activation+1.32e+01

Pos logit contributions
orse+0.226
 weapon+0.172
oc+0.171
uddy+0.166
ggy+0.165
Neg logit contributions
 groom-0.238
 roses-0.234
 register-0.220
 decides-0.217
 ponies-0.213
Tokents
Token ID912
Feature activation+4.05e+00

Pos logit contributions
orse+0.697
oc+0.585
uddy+0.582
 weapon+0.571
unch+0.554
Neg logit contributions
 groom-0.841
 roses-0.784
 decides-0.732
 register-0.725
 ponies-0.718
Token.
Token ID13
Feature activation+5.39e-01

Pos logit contributions
orse+0.264
oc+0.220
 weapon+0.217
uddy+0.211
 Carl+0.209
Neg logit contributions
 groom-0.207
 roses-0.188
 register-0.184
 ponies-0.177
 decides-0.174
Token He
Token ID679
Feature activation+5.17e+00

Pos logit contributions
orse+0.036
inations+0.030
 weapon+0.028
unch+0.028
beard+0.028
Neg logit contributions
 decides-0.024
 Angel-0.023
 groom-0.023
 She-0.022
 her-0.022
Token knew
Token ID2993
Feature activation-2.44e+00

Pos logit contributions
orse+0.341
unch+0.294
 weapon+0.284
uddy+0.279
oc+0.279
Neg logit contributions
 groom-0.267
 decides-0.240
 roses-0.227
 register-0.208
 nurses-0.206
Token he
Token ID339
Feature activation+6.20e+00

Pos logit contributions
 groom+0.159
 roses+0.155
 ponies+0.147
 register+0.147
 nurses+0.142
Neg logit contributions
orse-0.124
oc-0.107
unch-0.092
uddy-0.092
 weapon-0.089
Token feeling
Token ID4203
Feature activation+6.52e+00

Pos logit contributions
orse+0.121
oc+0.095
 weapon+0.095
uddy+0.089
 bone+0.089
Neg logit contributions
 groom-0.118
 roses-0.110
 register-0.105
 decides-0.104
 ponies-0.102
Token very
Token ID845
Feature activation-7.60e-01

Pos logit contributions
orse+0.382
 weapon+0.289
 hockey+0.280
 Benny+0.277
oc+0.277
Neg logit contributions
 groom-0.390
 register-0.364
 roses-0.355
 decides-0.346
 ponies-0.340
Token pleased
Token ID10607
Feature activation+4.30e+00

Pos logit contributions
 groom+0.046
 roses+0.043
 register+0.042
 decides+0.041
 ponies+0.040
Neg logit contributions
orse-0.044
 weapon-0.034
oc-0.033
 bone-0.032
ggy-0.032
Token by
Token ID416
Feature activation+9.14e+00

Pos logit contributions
orse+0.293
 weapon+0.242
oc+0.242
uddy+0.239
 puck+0.235
Neg logit contributions
 groom-0.212
 roses-0.206
 ponies-0.181
 register-0.181
 decides-0.176
Token his
Token ID465
Feature activation+5.75e+00

Pos logit contributions
orse+0.667
oc+0.558
 weapon+0.553
uddy+0.534
 bone+0.526
Neg logit contributions
 groom-0.424
 roses-0.394
 register-0.360
 decides-0.354
 ponies-0.349
Token discovery
Token ID9412
Feature activation+1.31e+01

Pos logit contributions
orse+0.360
oc+0.282
 weapon+0.274
unch+0.271
uddy+0.270
Neg logit contributions
 groom-0.327
 roses-0.307
 register-0.289
 decides-0.288
 ponies-0.285
Token.
Token ID13
Feature activation+9.40e-01

Pos logit contributions
orse+0.893
oc+0.723
uddy+0.703
unch+0.699
 weapon+0.691
Neg logit contributions
 groom-0.616
 roses-0.597
 register-0.591
 ponies-0.548
 decides-0.540
Token<|endoftext|>
Token ID50256
Feature activation+5.72e+00

Pos logit contributions
orse+0.053
 weapon+0.044
ggy+0.040
oy+0.040
inations+0.040
Neg logit contributions
 groom-0.053
 roses-0.050
 decides-0.049
 register-0.049
 Angel-0.049
TokenOnce
Token ID7454
Feature activation+3.87e+00

Pos logit contributions
orse+0.414
 weapon+0.338
oc+0.326
oy+0.319
 puck+0.317
Neg logit contributions
 groom-0.250
 roses-0.240
 decides-0.231
 register-0.229
 ponies-0.217
Token there
Token ID612
Feature activation+1.50e+00

Pos logit contributions
orse+0.232
oc+0.195
 weapon+0.186
 puck+0.182
anas+0.181
Neg logit contributions
 groom-0.202
 roses-0.197
 register-0.192
 decides-0.191
 ponies-0.182
Token was
Token ID373
Feature activation+2.05e+00

Pos logit contributions
orse+0.095
 weapon+0.078
inations+0.076
 bullets+0.075
oc+0.074
Neg logit contributions
 groom-0.076
 roses-0.074
 decides-0.072
 register-0.071
 her-0.070
Token started
Token ID2067
Feature activation-4.78e+00

Pos logit contributions
 groom+0.026
 roses+0.024
 register+0.023
 decides+0.023
 ponies+0.022
Neg logit contributions
orse-0.029
 weapon-0.023
oc-0.023
 bone-0.022
uddy-0.021
Token to
Token ID284
Feature activation+7.85e-01

Pos logit contributions
 groom+0.282
 roses+0.263
 register+0.251
 decides+0.249
 ponies+0.243
Neg logit contributions
orse-0.287
oc-0.225
 weapon-0.225
 bone-0.210
uddy-0.210
Token eat
Token ID4483
Feature activation+1.98e+00

Pos logit contributions
orse+0.048
 weapon+0.038
oc+0.037
 bone+0.035
uddy+0.035
Neg logit contributions
 groom-0.045
 roses-0.042
 register-0.041
 decides-0.040
 ponies-0.039
Token.
Token ID13
Feature activation+5.39e-01

Pos logit contributions
orse+0.127
 weapon+0.101
oc+0.101
 bone+0.097
 Carl+0.095
Neg logit contributions
 groom-0.108
 roses-0.098
 register-0.097
 decides-0.095
 ponies-0.092
Token They
Token ID1119
Feature activation+1.28e+00

Pos logit contributions
orse+0.027
 Andy+0.021
 Carl+0.021
 Benny+0.021
 Joe+0.020
Neg logit contributions
 groom-0.036
 register-0.034
 decides-0.032
 ponies-0.032
 roses-0.031
Token mun
Token ID29856
Feature activation+1.30e+01

Pos logit contributions
orse+0.068
oc+0.049
 weapon+0.049
 bone+0.047
 Carl+0.047
Neg logit contributions
 groom-0.083
 roses-0.079
 register-0.079
 decides-0.076
 ponies-0.075
Tokenched
Token ID1740
Feature activation-2.55e-01

Pos logit contributions
orse+0.687
oc+0.508
 weapon+0.485
unch+0.470
 bone+0.470
Neg logit contributions
 groom-0.867
 roses-0.801
 register-0.792
 decides-0.784
 ponies-0.775
Token and
Token ID290
Feature activation+1.60e-01

Pos logit contributions
 groom+0.012
 roses+0.011
 register+0.011
 decides+0.011
 ponies+0.010
Neg logit contributions
orse-0.018
 weapon-0.015
oc-0.014
unch-0.014
uddy-0.014
Token cr
Token ID1067
Feature activation+5.19e+00

Pos logit contributions
orse+0.009
 weapon+0.008
oc+0.008
uddy+0.007
unch+0.007
Neg logit contributions
 groom-0.009
 roses-0.009
 decides-0.008
 register-0.008
 ponies-0.008
Tokenun
Token ID403
Feature activation+4.11e+00

Pos logit contributions
orse+0.315
 weapon+0.252
oc+0.248
 bone+0.230
 hockey+0.228
Neg logit contributions
 groom-0.292
 roses-0.277
 register-0.269
 ponies-0.254
als-0.253
Tokenched
Token ID1740
Feature activation-2.04e-01

Pos logit contributions
orse+0.263
 weapon+0.236
 puck+0.208
 bone+0.205
oc+0.204
Neg logit contributions
 groom-0.207
 roses-0.194
als-0.186
 register-0.178
 ponies-0.173
Token was
Token ID373
Feature activation+2.39e+00

Pos logit contributions
orse+0.417
 weapon+0.335
unch+0.316
uddy+0.316
oc+0.312
Neg logit contributions
 groom-0.419
 decides-0.385
 roses-0.384
 register-0.369
 ponies-0.353
Token so
Token ID523
Feature activation+1.09e+00

Pos logit contributions
orse+0.151
oc+0.122
 weapon+0.122
uddy+0.116
 bone+0.113
Neg logit contributions
 groom-0.133
 roses-0.121
 register-0.118
 decides-0.116
 ponies-0.112
Token proud
Token ID6613
Feature activation+2.13e-01

Pos logit contributions
orse+0.070
 weapon+0.060
uddy+0.059
oc+0.057
 bullets+0.056
Neg logit contributions
 groom-0.058
 decides-0.051
 roses-0.051
 register-0.049
 bride-0.045
Token of
Token ID286
Feature activation+2.33e+00

Pos logit contributions
orse+0.016
gh+0.014
uddy+0.014
oc+0.014
ggies+0.014
Neg logit contributions
 roses-0.008
 her-0.007
 ponies-0.007
 groom-0.007
 flowers-0.006
Token his
Token ID465
Feature activation+5.49e+00

Pos logit contributions
orse+0.126
uddy+0.106
oc+0.101
unch+0.097
 weapon+0.092
Neg logit contributions
 herself-0.140
 roses-0.138
 groom-0.137
 her-0.134
 decides-0.131
Token discovery
Token ID9412
Feature activation+1.30e+01

Pos logit contributions
orse+0.357
oc+0.299
Andy+0.295
uddy+0.293
Joe+0.286
Neg logit contributions
 groom-0.264
 back-0.257
 roses-0.243
 register-0.242
 mirror-0.236
Token and
Token ID290
Feature activation+5.65e-01

Pos logit contributions
orse+1.042
emy+0.852
unch+0.844
inations+0.840
orses+0.838
Neg logit contributions
 register-0.457
 back-0.434
 groom-0.404
 roses-0.395
 her-0.392
Token hurried
Token ID31662
Feature activation-1.17e+00

Pos logit contributions
orse+0.033
uddy+0.029
oc+0.027
unch+0.027
 weapon+0.026
Neg logit contributions
 groom-0.034
 decides-0.031
 roses-0.030
 register-0.028
 ponies-0.027
Token back
Token ID736
Feature activation-8.11e+00

Pos logit contributions
 groom+0.039
 roses+0.034
 register+0.032
 decides+0.031
 ponies+0.029
Neg logit contributions
orse-0.100
 weapon-0.085
oc-0.084
 bone-0.082
uddy-0.081
Token to
Token ID284
Feature activation+1.30e+00

Pos logit contributions
 groom+0.370
 roses+0.335
 register+0.324
 decides+0.318
 ponies+0.305
Neg logit contributions
orse-0.594
 weapon-0.488
oc-0.485
 bone-0.465
uddy-0.460
Token his
Token ID465
Feature activation+5.56e+00

Pos logit contributions
orse+0.067
oc+0.052
uddy+0.051
 weapon+0.050
unch+0.047
Neg logit contributions
 groom-0.088
 roses-0.080
 decides-0.079
 register-0.078
 ponies-0.076
Token to
Token ID284
Feature activation+1.20e+00

Pos logit contributions
orse+0.139
oc+0.113
 weapon+0.111
 puck+0.107
 bone+0.105
Neg logit contributions
 groom-0.105
 roses-0.102
 register-0.095
 decides-0.093
 ponies-0.092
Token have
Token ID423
Feature activation+2.41e+00

Pos logit contributions
orse+0.074
 weapon+0.052
 Carl+0.052
oc+0.051
 Andy+0.051
Neg logit contributions
 groom-0.071
 register-0.069
 roses-0.067
 ponies-0.065
 nurses-0.064
Token made
Token ID925
Feature activation+1.31e+00

Pos logit contributions
orse+0.158
 weapon+0.126
oc+0.126
 bone+0.120
uddy+0.119
Neg logit contributions
 groom-0.128
 roses-0.117
 register-0.114
 decides-0.112
 ponies-0.108
Token this
Token ID428
Feature activation+2.72e+00

Pos logit contributions
orse+0.099
 weapon+0.082
oc+0.081
 bone+0.078
uddy+0.078
Neg logit contributions
 groom-0.056
 roses-0.051
 register-0.049
 decides-0.047
 ponies-0.046
Token intelligent
Token ID12661
Feature activation+2.38e+00

Pos logit contributions
orse+0.160
 weapon+0.123
oc+0.122
 bone+0.115
uddy+0.114
Neg logit contributions
 groom-0.165
 roses-0.154
 register-0.149
 decides-0.147
 ponies-0.143
Token discovery
Token ID9412
Feature activation+1.30e+01

Pos logit contributions
orse+0.162
 weapon+0.130
oc+0.129
 bone+0.123
uddy+0.123
Neg logit contributions
 groom-0.121
 roses-0.111
 register-0.107
 decides-0.106
 ponies-0.102
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
orse+0.758
oc+0.581
 weapon+0.578
 bone+0.541
uddy+0.540
Neg logit contributions
 groom-0.783
 roses-0.737
 register-0.715
 decides-0.699
 ponies-0.685
Token<|endoftext|>
Token ID50256
Feature activation+5.93e+00

Pos logit contributions
orse+0.044
oc+0.032
 Andy+0.031
 His+0.030
uddy+0.030
Neg logit contributions
 groom-0.077
 roses-0.072
 register-0.069
 decides-0.068
 ponies-0.067
TokenOnce
Token ID7454
Feature activation+4.16e+00

Pos logit contributions
orse+0.451
 weapon+0.370
oc+0.363
oy+0.351
ggy+0.350
Neg logit contributions
 groom-0.243
 roses-0.229
 register-0.221
 decides-0.217
 ponies-0.207
Token there
Token ID612
Feature activation+1.90e+00

Pos logit contributions
orse+0.240
oc+0.196
 weapon+0.191
 puck+0.186
 bone+0.181
Neg logit contributions
 groom-0.233
 roses-0.227
 register-0.220
 decides-0.216
 ponies-0.211
Token was
Token ID373
Feature activation+2.52e+00

Pos logit contributions
orse+0.129
 weapon+0.109
inations+0.106
 bullets+0.104
 puck+0.104
Neg logit contributions
 her-0.086
 groom-0.086
 roses-0.085
 decides-0.085
 mirror-0.078
Token to
Token ID284
Feature activation+1.20e+00

Pos logit contributions
orse+0.136
oc+0.118
uddy+0.112
 weapon+0.110
 puck+0.109
Neg logit contributions
 groom-0.091
 roses-0.089
 decides-0.079
 her-0.078
 ponies-0.078
Token have
Token ID423
Feature activation+2.41e+00

Pos logit contributions
orse+0.080
 weapon+0.062
oc+0.060
 Carl+0.058
ggy+0.058
Neg logit contributions
 groom-0.065
 roses-0.061
 register-0.061
 ponies-0.058
 decides-0.056
Token made
Token ID925
Feature activation+1.31e+00

Pos logit contributions
orse+0.165
oc+0.134
 weapon+0.133
uddy+0.127
 bone+0.127
Neg logit contributions
 groom-0.122
 roses-0.112
 register-0.107
 decides-0.106
 ponies-0.102
Token this
Token ID428
Feature activation+2.72e+00

Pos logit contributions
orse+0.095
oc+0.079
uddy+0.077
 weapon+0.076
oy+0.074
Neg logit contributions
 groom-0.060
 roses-0.057
 register-0.053
 decides-0.050
 ponies-0.050
Token exciting
Token ID7895
Feature activation+7.12e+00

Pos logit contributions
orse+0.189
uddy+0.161
unch+0.153
oc+0.151
ggies+0.151
Neg logit contributions
 groom-0.129
 roses-0.127
 decides-0.119
 mirror-0.118
 register-0.112
Token discovery
Token ID9412
Feature activation+1.30e+01

Pos logit contributions
orse+0.487
uddy+0.414
unch+0.388
oc+0.366
emy+0.358
Neg logit contributions
 roses-0.362
 groom-0.350
 mirror-0.339
 decides-0.319
 ponies-0.306
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
orse+0.835
oc+0.656
 weapon+0.637
uddy+0.615
unch+0.609
Neg logit contributions
 groom-0.708
 roses-0.674
 register-0.652
 decides-0.627
 ponies-0.622
Token She
Token ID1375
Feature activation-4.95e+00

Pos logit contributions
orse+0.075
 His+0.066
 weapon+0.066
oc+0.065
 Andy+0.065
Neg logit contributions
 groom-0.044
 roses-0.037
 register-0.036
 bride-0.032
 ponies-0.031
Token ran
Token ID4966
Feature activation-1.09e+00

Pos logit contributions
 groom+0.270
 roses+0.247
 decides+0.239
 register+0.238
 ponies+0.227
Neg logit contributions
orse-0.318
 weapon-0.254
oc-0.252
 bone-0.240
uddy-0.239
Token back
Token ID736
Feature activation-8.09e+00

Pos logit contributions
 groom+0.049
 roses+0.044
 register+0.043
 decides+0.042
 ponies+0.040
Neg logit contributions
orse-0.080
 weapon-0.067
oc-0.065
 bone-0.064
 Carl-0.064
Token home
Token ID1363
Feature activation-4.55e-01

Pos logit contributions
 groom+0.493
 register+0.449
 roses+0.433
 decides+0.431
 ponies+0.404
Neg logit contributions
orse-0.459
 weapon-0.382
 Carl-0.367
 bone-0.360
 Andy-0.360
Token was
Token ID373
Feature activation+2.36e+00

Pos logit contributions
 groom+0.173
 decides+0.161
 roses+0.159
 register+0.146
als+0.141
Neg logit contributions
orse-0.178
 weapon-0.151
uddy-0.149
unch-0.148
 bone-0.143
Token so
Token ID523
Feature activation+1.08e+00

Pos logit contributions
orse+0.144
 weapon+0.113
oc+0.113
 bone+0.107
uddy+0.106
Neg logit contributions
 groom-0.136
 roses-0.126
 register-0.123
 decides-0.121
 ponies-0.117
Token happy
Token ID3772
Feature activation+1.94e+00

Pos logit contributions
orse+0.063
 weapon+0.050
oc+0.049
 bone+0.047
uddy+0.047
Neg logit contributions
 groom-0.065
 roses-0.061
 decides-0.059
 register-0.058
 ponies-0.055
Token with
Token ID351
Feature activation+5.23e+00

Pos logit contributions
orse+0.141
oc+0.120
 weapon+0.116
 puck+0.115
uddy+0.114
Neg logit contributions
 roses-0.087
 groom-0.085
 ponies-0.077
 decides-0.076
 her-0.076
Token her
Token ID607
Feature activation-5.76e+00

Pos logit contributions
orse+0.445
 weapon+0.381
 Carl+0.372
oc+0.369
 bone+0.369
Neg logit contributions
 groom-0.175
 register-0.146
 roses-0.143
 decides-0.139
 ponies-0.125
Token discovery
Token ID9412
Feature activation+1.30e+01

Pos logit contributions
 roses+0.288
 back+0.278
 groom+0.275
 wardrobe+0.261
 mirror+0.256
Neg logit contributions
orse-0.339
unch-0.315
uddy-0.313
Andy-0.301
Jerry-0.298
Token and
Token ID290
Feature activation+5.65e-01

Pos logit contributions
orse+0.902
oc+0.719
 puck+0.693
 weapon+0.690
unch+0.681
Neg logit contributions
 groom-0.617
 roses-0.604
 register-0.593
 ponies-0.556
 decides-0.536
Token for
Token ID329
Feature activation+4.03e+00

Pos logit contributions
orse+0.036
 weapon+0.029
oc+0.028
 Carl+0.027
 bone+0.027
Neg logit contributions
 groom-0.031
 roses-0.028
 register-0.028
 decides-0.027
 ponies-0.027
Token the
Token ID262
Feature activation+6.77e-01

Pos logit contributions
orse+0.251
oc+0.203
uddy+0.196
 weapon+0.196
unch+0.190
Neg logit contributions
 groom-0.229
 roses-0.213
 register-0.202
 decides-0.199
 ponies-0.194
Token rest
Token ID1334
Feature activation+4.30e+00

Pos logit contributions
orse+0.042
unch+0.036
run+0.036
uddy+0.036
oc+0.036
Neg logit contributions
 groom-0.037
 roses-0.037
 register-0.033
 bride-0.032
 mirror-0.032
Token of
Token ID286
Feature activation+2.41e+00

Pos logit contributions
orse+0.242
oc+0.197
 weapon+0.188
 puck+0.183
 bone+0.178
Neg logit contributions
 groom-0.251
 roses-0.248
 register-0.243
 ponies-0.226
 decides-0.221
Token loved
Token ID6151
Feature activation-1.56e+00

Pos logit contributions
 groom+0.012
 roses+0.011
 decides+0.011
 register+0.011
 ponies+0.011
Neg logit contributions
orse-0.010
oc-0.008
 weapon-0.007
uddy-0.007
unch-0.007
Token to
Token ID284
Feature activation+5.40e-01

Pos logit contributions
 groom+0.073
 roses+0.070
 ponies+0.064
 decides+0.059
 nurses+0.054
Neg logit contributions
orse-0.116
oc-0.102
uddy-0.096
 weapon-0.094
ggy-0.093
Token watch
Token ID2342
Feature activation-1.39e+00

Pos logit contributions
orse+0.031
oc+0.025
 weapon+0.024
uddy+0.024
unch+0.023
Neg logit contributions
 groom-0.033
 roses-0.030
 decides-0.029
 register-0.027
 ponies-0.027
Token the
Token ID262
Feature activation-4.98e-02

Pos logit contributions
 groom+0.064
 roses+0.061
 ponies+0.056
 decides+0.054
 register+0.052
Neg logit contributions
orse-0.100
uddy-0.084
oc-0.083
 weapon-0.081
unch-0.080
Token y
Token ID331
Feature activation+3.77e+00

Pos logit contributions
 groom+0.002
 roses+0.002
 decides+0.002
 ponies+0.002
 register+0.002
Neg logit contributions
orse-0.004
oc-0.003
uddy-0.003
 weapon-0.003
ggy-0.003
Tokenach
Token ID620
Feature activation+1.29e+01

Pos logit contributions
orse+0.209
 weapon+0.162
oc+0.154
uddy+0.151
ggy+0.150
Neg logit contributions
 groom-0.233
 roses-0.229
 register-0.215
 decides-0.212
 ponies-0.209
Tokents
Token ID912
Feature activation+3.83e+00

Pos logit contributions
orse+0.805
uddy+0.692
 weapon+0.691
oc+0.674
 bone+0.663
Neg logit contributions
 groom-0.718
 roses-0.672
 decides-0.618
 register-0.607
 ponies-0.603
Token on
Token ID319
Feature activation-2.85e+00

Pos logit contributions
orse+0.242
 weapon+0.196
oc+0.195
uddy+0.190
 bone+0.188
Neg logit contributions
 groom-0.209
 roses-0.194
 register-0.184
 decides-0.183
 ponies-0.179
Token the
Token ID262
Feature activation-9.22e-03

Pos logit contributions
 groom+0.139
 roses+0.129
 decides+0.119
 register+0.118
 ponies+0.117
Neg logit contributions
orse-0.203
 weapon-0.165
oc-0.164
uddy-0.160
unch-0.156
Token water
Token ID1660
Feature activation-3.05e+00

Pos logit contributions
 groom+0.001
 roses+0.000
 register+0.000
 decides+0.000
 ponies+0.000
Neg logit contributions
orse-0.001
oc-0.000
 weapon-0.000
uddy-0.000
unch-0.000
Token.
Token ID13
Feature activation+3.53e-01

Pos logit contributions
 groom+0.176
 roses+0.164
 register+0.158
 decides+0.156
 ponies+0.151
Neg logit contributions
orse-0.185
oc-0.145
 weapon-0.145
uddy-0.138
 bone-0.138
Token so
Token ID523
Feature activation+1.05e+00

Pos logit contributions
orse+0.125
ggy+0.089
 weapon+0.087
 Carl+0.084
unch+0.083
Neg logit contributions
 groom-0.149
 roses-0.144
 register-0.141
 decides-0.140
 ponies-0.136
Token proud
Token ID6613
Feature activation+1.79e-01

Pos logit contributions
orse+0.055
oc+0.040
 weapon+0.040
ggy+0.038
unch+0.037
Neg logit contributions
 groom-0.069
 roses-0.066
 register-0.065
 decides-0.063
 ponies-0.062
Token of
Token ID286
Feature activation+2.31e+00

Pos logit contributions
orse+0.011
oc+0.009
 weapon+0.009
 puck+0.009
uddy+0.009
Neg logit contributions
 roses-0.010
 groom-0.009
 ponies-0.009
 register-0.008
 decides-0.008
Token her
Token ID607
Feature activation-5.78e+00

Pos logit contributions
orse+0.214
 Carl+0.186
 weapon+0.183
 Andy+0.183
ggy+0.180
Neg logit contributions
 groom-0.062
 register-0.046
 decides-0.045
 roses-0.044
 ponies-0.036
Token new
Token ID649
Feature activation+1.50e+00

Pos logit contributions
 groom+0.321
 roses+0.300
 decides+0.273
 bride+0.273
 ponies+0.272
Neg logit contributions
orse-0.352
uddy-0.309
oc-0.304
Andy-0.299
Joe-0.291
Token discovery
Token ID9412
Feature activation+1.29e+01

Pos logit contributions
orse+0.091
uddy+0.074
oc+0.070
inations+0.069
unch+0.068
Neg logit contributions
 groom-0.092
 roses-0.085
 ponies-0.079
 decides-0.079
 bride-0.077
Token and
Token ID290
Feature activation+5.43e-01

Pos logit contributions
orse+0.870
oc+0.677
 weapon+0.673
 puck+0.657
unch+0.651
Neg logit contributions
 groom-0.655
 roses-0.622
 register-0.618
 ponies-0.587
 decides-0.573
Token she
Token ID673
Feature activation-4.35e+00

Pos logit contributions
orse+0.039
 weapon+0.032
oc+0.032
 bone+0.030
uddy+0.030
Neg logit contributions
 groom-0.026
 roses-0.023
 register-0.022
 decides-0.022
 ponies-0.021
Token wanted
Token ID2227
Feature activation+3.39e-01

Pos logit contributions
 groom+0.243
 roses+0.221
 decides+0.215
 register+0.214
 ponies+0.204
Neg logit contributions
orse-0.273
 weapon-0.219
oc-0.217
uddy-0.207
 bone-0.207
Token to
Token ID284
Feature activation+1.29e+00

Pos logit contributions
orse+0.020
 weapon+0.016
oc+0.015
 bone+0.015
 Carl+0.015
Neg logit contributions
 groom-0.020
 roses-0.019
 register-0.018
 decides-0.018
 ponies-0.017
Token keep
Token ID1394
Feature activation+1.49e-01

Pos logit contributions
orse+0.086
 weapon+0.069
oc+0.069
 bone+0.065
uddy+0.065
Neg logit contributions
 groom-0.067
 roses-0.062
 register-0.060
 decides-0.059
 ponies-0.057
Token,
Token ID11
Feature activation-1.23e-01

Pos logit contributions
orse+0.067
 weapon+0.055
oc+0.055
 bone+0.053
uddy+0.052
Neg logit contributions
 groom-0.040
 roses-0.036
 register-0.035
 decides-0.034
 ponies-0.033
Token thankful
Token ID25535
Feature activation+1.21e+00

Pos logit contributions
 groom+0.007
 roses+0.007
 register+0.006
 decides+0.006
 ponies+0.006
Neg logit contributions
orse-0.007
 weapon-0.006
oc-0.006
uddy-0.006
 bone-0.005
Token for
Token ID329
Feature activation+3.96e+00

Pos logit contributions
orse+0.075
oc+0.058
 weapon+0.058
 bone+0.055
uddy+0.054
Neg logit contributions
 groom-0.070
 roses-0.065
 register-0.063
 decides-0.062
 ponies-0.060
Token her
Token ID607
Feature activation-5.78e+00

Pos logit contributions
orse+0.288
 weapon+0.236
 Carl+0.231
 Andy+0.230
oc+0.230
Neg logit contributions
 groom-0.173
 decides-0.159
 roses-0.153
 register-0.148
 ponies-0.140
Token incredible
Token ID8082
Feature activation+4.52e+00

Pos logit contributions
 groom+0.349
 roses+0.340
 register+0.312
 ponies+0.311
 decides+0.309
Neg logit contributions
orse-0.333
oc-0.266
 puck-0.246
 weapon-0.244
uddy-0.243
Token discovery
Token ID9412
Feature activation+1.29e+01

Pos logit contributions
orse+0.209
oc+0.153
 weapon+0.142
uddy+0.136
unch+0.134
Neg logit contributions
 groom-0.329
 roses-0.316
 decides-0.298
 ponies-0.296
 register-0.291
Token.
Token ID13
Feature activation+9.75e-01

Pos logit contributions
orse+0.791
 weapon+0.613
oc+0.613
 puck+0.579
unch+0.572
Neg logit contributions
 groom-0.742
 roses-0.698
 register-0.681
 decides-0.657
 ponies-0.649
Token<|endoftext|>
Token ID50256
Feature activation+5.90e+00

Pos logit contributions
orse+0.052
 weapon+0.040
oc+0.039
 bone+0.037
 puck+0.036
Neg logit contributions
 groom-0.063
 roses-0.059
 register-0.058
 decides-0.057
 ponies-0.056
TokenM
Token ID44
Feature activation-2.34e+00

Pos logit contributions
orse+0.429
 weapon+0.350
oc+0.343
oy+0.329
ggy+0.328
Neg logit contributions
 groom-0.262
 roses-0.246
 register-0.239
 decides-0.234
 ponies-0.225
Tokenummy
Token ID13513
Feature activation+4.64e+00

Pos logit contributions
 groom+0.134
 roses+0.127
 register+0.125
 decides+0.120
 ponies+0.119
Neg logit contributions
orse-0.138
 weapon-0.115
oc-0.112
 puck-0.108
 bone-0.104
Token was
Token ID373
Feature activation+2.49e+00

Pos logit contributions
orse+0.278
 weapon+0.216
oc+0.216
 bone+0.205
 Carl+0.203
Neg logit contributions
 groom-0.267
 roses-0.248
 register-0.245
 decides-0.237
 ponies-0.232
Token.
Token ID13
Feature activation+3.95e-01

Pos logit contributions
orse+0.056
 puck+0.046
 weapon+0.045
unch+0.045
uddy+0.045
Neg logit contributions
 groom-0.040
 roses-0.038
 register-0.036
 decides-0.035
 ponies-0.033
Token The
Token ID383
Feature activation+2.93e+00

Pos logit contributions
orse+0.023
 weapon+0.018
ggy+0.017
oc+0.017
inations+0.017
Neg logit contributions
 groom-0.023
 roses-0.022
 decides-0.022
 register-0.021
 ponies-0.021
Token cater
Token ID20825
Feature activation+3.37e+00

Pos logit contributions
orse+0.170
 weapon+0.132
oc+0.130
 bone+0.124
 Carl+0.122
Neg logit contributions
 groom-0.179
 roses-0.166
 register-0.163
 decides-0.160
 ponies-0.156
Tokenpillar
Token ID41643
Feature activation+8.96e-01

Pos logit contributions
orse+0.204
 weapon+0.160
oc+0.154
 bone+0.151
 puck+0.150
Neg logit contributions
 groom-0.191
 roses-0.180
 register-0.174
 decides-0.172
 ponies-0.167
Token happily
Token ID18177
Feature activation-1.92e+00

Pos logit contributions
orse+0.053
 weapon+0.044
uddy+0.042
unch+0.042
oc+0.041
Neg logit contributions
 groom-0.050
 roses-0.046
 decides-0.045
 register-0.043
 Angel-0.041
Token mun
Token ID29856
Feature activation+1.29e+01

Pos logit contributions
 groom+0.116
 roses+0.107
 decides+0.104
 register+0.102
 ponies+0.097
Neg logit contributions
orse-0.110
 weapon-0.088
oc-0.085
uddy-0.082
 bone-0.081
Tokenched
Token ID1740
Feature activation-3.79e-01

Pos logit contributions
orse+0.646
oc+0.477
 weapon+0.467
 bone+0.439
 Benny+0.436
Neg logit contributions
 groom-0.896
 roses-0.833
 ponies-0.809
 register-0.804
 decides-0.798
Token on
Token ID319
Feature activation-2.73e+00

Pos logit contributions
 groom+0.015
 roses+0.014
 decides+0.013
 register+0.013
 ponies+0.012
Neg logit contributions
orse-0.030
 weapon-0.024
oc-0.024
unch-0.023
uddy-0.023
Token the
Token ID262
Feature activation+1.49e-01

Pos logit contributions
 groom+0.131
 roses+0.123
 decides+0.115
 register+0.109
 her+0.108
Neg logit contributions
orse-0.187
uddy-0.152
 weapon-0.151
oc-0.150
unch-0.148
Token mushroom
Token ID28520
Feature activation+2.80e-01

Pos logit contributions
orse+0.009
oc+0.007
 weapon+0.007
uddy+0.006
unch+0.006
Neg logit contributions
 groom-0.009
 roses-0.008
 register-0.008
 decides-0.008
 ponies-0.008
Token,
Token ID11
Feature activation-5.21e-01

Pos logit contributions
orse+0.019
ggy+0.015
 weapon+0.015
oc+0.015
uddy+0.015
Neg logit contributions
 groom-0.013
 roses-0.013
 register-0.012
 decides-0.011
als-0.011
Token played
Token ID2826
Feature activation+3.08e+00

Pos logit contributions
 groom+0.025
 roses+0.023
 decides+0.022
 ponies+0.022
 register+0.021
Neg logit contributions
orse-0.025
 weapon-0.021
oc-0.021
uddy-0.019
ggy-0.019
Token tag
Token ID7621
Feature activation+1.73e+00

Pos logit contributions
orse+0.195
oc+0.151
 weapon+0.151
uddy+0.148
unch+0.145
Neg logit contributions
 groom-0.169
 roses-0.159
 ponies-0.149
 register-0.147
 decides-0.146
Token and
Token ID290
Feature activation+1.96e-01

Pos logit contributions
orse+0.118
 weapon+0.093
oc+0.091
unch+0.090
uddy+0.087
Neg logit contributions
 groom-0.087
 roses-0.082
 ponies-0.077
 register-0.077
 decides-0.075
Token shared
Token ID4888
Feature activation-1.13e+00

Pos logit contributions
orse+0.011
oc+0.009
 weapon+0.009
unch+0.009
uddy+0.008
Neg logit contributions
 groom-0.012
 roses-0.011
 decides-0.011
 ponies-0.011
 register-0.010
Token their
Token ID511
Feature activation+4.75e-01

Pos logit contributions
 groom+0.061
 roses+0.057
 ponies+0.053
 decides+0.052
 register+0.051
Neg logit contributions
orse-0.075
 weapon-0.060
oc-0.057
uddy-0.057
unch-0.057
Token lun
Token ID14678
Feature activation+1.29e+01

Pos logit contributions
orse+0.030
unch+0.023
 weapon+0.023
oc+0.023
uddy+0.022
Neg logit contributions
 roses-0.027
 groom-0.026
 ponies-0.025
 decides-0.024
 register-0.022
Tokenches
Token ID2052
Feature activation-9.07e-01

Pos logit contributions
orse+0.844
 weapon+0.673
oc+0.669
 bone+0.637
uddy+0.629
Neg logit contributions
 groom-0.694
 roses-0.639
 register-0.621
 decides-0.611
 ponies-0.591
Token.
Token ID13
Feature activation+6.84e-01

Pos logit contributions
 groom+0.048
 roses+0.044
 register+0.043
 ponies+0.042
 decides+0.041
Neg logit contributions
orse-0.060
 weapon-0.047
oc-0.047
unch-0.045
uddy-0.044
Token Molly
Token ID30236
Feature activation+6.48e-01

Pos logit contributions
orse+0.040
 weapon+0.032
oc+0.030
 bone+0.029
 puck+0.029
Neg logit contributions
 groom-0.041
 roses-0.038
 decides-0.038
 register-0.037
 ponies-0.036
Token had
Token ID550
Feature activation+4.16e+00

Pos logit contributions
orse+0.038
 weapon+0.031
oc+0.030
 bone+0.028
unch+0.028
Neg logit contributions
 groom-0.038
 roses-0.035
 decides-0.035
 register-0.034
 ponies-0.033
Token fair
Token ID3148
Feature activation+2.71e-01

Pos logit contributions
orse+0.286
oc+0.240
 weapon+0.230
uddy+0.223
unch+0.222
Neg logit contributions
 groom-0.217
 roses-0.194
 decides-0.188
 register-0.182
 ponies-0.180
Token girl
Token ID2576
Feature activation-3.13e+00

Pos logit contributions
 register+0.041
 groom+0.038
pan+0.038
 Elsa+0.035
Elsa+0.035
Neg logit contributions
orse-0.043
 crocod-0.040
 discovery-0.039
oc-0.039
 weapon-0.035
Token was
Token ID373
Feature activation+2.33e+00

Pos logit contributions
 groom+0.189
 roses+0.176
 decides+0.173
 register+0.168
 ponies+0.163
Neg logit contributions
orse-0.178
 weapon-0.141
oc-0.135
 bone-0.133
uddy-0.132
Token overwhelmed
Token ID20974
Feature activation-4.20e-01

Pos logit contributions
orse+0.134
 weapon+0.101
oc+0.100
ggy+0.096
 Carl+0.095
Neg logit contributions
 groom-0.142
 roses-0.133
 register-0.131
 decides-0.128
 ponies-0.125
Token with
Token ID351
Feature activation+5.19e+00

Pos logit contributions
 groom+0.023
 roses+0.022
 register+0.020
 ponies+0.020
 decides+0.020
Neg logit contributions
orse-0.028
 weapon-0.021
 puck-0.021
oc-0.021
uddy-0.021
Token the
Token ID262
Feature activation+5.57e-01

Pos logit contributions
orse+0.330
 weapon+0.261
oc+0.259
 bone+0.246
uddy+0.244
Neg logit contributions
 groom-0.287
 roses-0.265
 register-0.257
 decides-0.254
 ponies-0.246
Token discovery
Token ID9412
Feature activation+1.29e+01

Pos logit contributions
orse+0.030
 weapon+0.024
 crocod+0.022
oc+0.022
 bone+0.022
Neg logit contributions
 groom-0.033
 register-0.032
 decides-0.030
 roses-0.030
 nurses-0.029
Token.
Token ID13
Feature activation+9.31e-01

Pos logit contributions
orse+0.829
oc+0.650
 weapon+0.642
 puck+0.615
unch+0.614
Neg logit contributions
 groom-0.697
 roses-0.662
 register-0.643
 decides-0.616
 ponies-0.610
Token She
Token ID1375
Feature activation-5.05e+00

Pos logit contributions
orse+0.066
 His+0.058
 Andy+0.058
 Carl+0.058
 Benny+0.057
Neg logit contributions
 groom-0.043
 roses-0.036
 register-0.035
 bride-0.033
 ponies-0.031
Token protected
Token ID6861
Feature activation+3.57e+00

Pos logit contributions
 groom+0.297
 roses+0.275
 register+0.268
 decides+0.265
 ponies+0.256
Neg logit contributions
orse-0.302
 weapon-0.236
oc-0.234
 bone-0.222
uddy-0.219
Token the
Token ID262
Feature activation+6.32e-01

Pos logit contributions
orse+0.255
 Carl+0.218
 weapon+0.218
 Andy+0.216
 Benny+0.211
Neg logit contributions
 groom-0.152
 register-0.137
 decides-0.134
 roses-0.129
 ponies-0.121
Token nest
Token ID16343
Feature activation+2.80e+00

Pos logit contributions
orse+0.034
 weapon+0.026
 crocod+0.026
oc+0.025
 bone+0.025
Neg logit contributions
 register-0.037
 groom-0.037
 decides-0.034
 nurses-0.033
 Elsa-0.033
Token little
Token ID1310
Feature activation+1.75e+00

Pos logit contributions
orse+0.182
 weapon+0.150
oc+0.147
 bone+0.145
ggy+0.140
Neg logit contributions
 groom-0.149
 roses-0.139
 decides-0.137
 register-0.131
 ponies-0.130
Token girl
Token ID2576
Feature activation-3.61e+00

Pos logit contributions
orse+0.119
 weapon+0.107
 bone+0.106
oc+0.105
 crocod+0.102
Neg logit contributions
 groom-0.071
 decides-0.066
 register-0.064
 roses-0.063
 ponies-0.059
Token was
Token ID373
Feature activation+1.83e+00

Pos logit contributions
 groom+0.214
 roses+0.194
 decides+0.193
 register+0.183
 ponies+0.175
Neg logit contributions
orse-0.206
 weapon-0.173
unch-0.160
uddy-0.160
 bone-0.156
Token thrilled
Token ID20536
Feature activation+1.52e+00

Pos logit contributions
orse+0.108
 weapon+0.082
oc+0.082
 bone+0.078
ggy+0.078
Neg logit contributions
 groom-0.109
 roses-0.102
 register-0.100
 decides-0.099
 ponies-0.095
Token and
Token ID290
Feature activation-1.51e-02

Pos logit contributions
orse+0.108
oc+0.089
 weapon+0.086
 puck+0.084
uddy+0.082
Neg logit contributions
 groom-0.074
 roses-0.070
 register-0.067
 decides-0.064
 ponies-0.064
Token mun
Token ID29856
Feature activation+1.29e+01

Pos logit contributions
 groom+0.001
 roses+0.001
 register+0.001
 decides+0.001
 ponies+0.001
Neg logit contributions
orse-0.001
 weapon-0.001
oc-0.001
 bone-0.001
uddy-0.001
Tokenched
Token ID1740
Feature activation-4.13e-01

Pos logit contributions
orse+0.623
oc+0.455
 weapon+0.428
 hockey+0.416
ggy+0.415
Neg logit contributions
 groom-0.903
 roses-0.853
 decides-0.827
 ponies-0.826
 register-0.817
Token away
Token ID1497
Feature activation-3.32e+00

Pos logit contributions
 groom+0.018
 register+0.015
 roses+0.015
 decides+0.015
 ponies+0.014
Neg logit contributions
orse-0.030
oc-0.026
 weapon-0.026
 bone-0.025
 Carl-0.025
Token happily
Token ID18177
Feature activation-1.91e+00

Pos logit contributions
 groom+0.179
 roses+0.164
 register+0.161
 decides+0.160
 ponies+0.152
Neg logit contributions
orse-0.213
 weapon-0.170
oc-0.169
 bone-0.162
 Carl-0.159
Token.
Token ID13
Feature activation+4.54e-01

Pos logit contributions
 groom+0.096
 register+0.088
 roses+0.087
 ponies+0.082
 decides+0.079
Neg logit contributions
orse-0.126
 weapon-0.105
oc-0.101
 puck-0.099
uddy-0.098
Token
Token ID220
Feature activation-4.38e-01

Pos logit contributions
orse+0.027
 His+0.024
 Benny+0.023
 Andy+0.022
oc+0.022
Neg logit contributions
 groom-0.026
 register-0.023
 roses-0.023
pan-0.022
 nurses-0.021
Token a
Token ID257
Feature activation-4.08e-01

Pos logit contributions
 groom+0.217
 decides+0.193
 register+0.193
 roses+0.193
 ponies+0.183
Neg logit contributions
orse-0.304
 hockey-0.257
 weapon-0.253
 fishing-0.253
 Benny-0.249
Token broom
Token ID47085
Feature activation-4.01e+00

Pos logit contributions
 groom+0.022
 roses+0.020
 register+0.019
 decides+0.019
 ponies+0.018
Neg logit contributions
orse-0.027
oc-0.021
 weapon-0.021
oy-0.020
uddy-0.020
Token and
Token ID290
Feature activation-5.38e-01

Pos logit contributions
 groom+0.244
 roses+0.225
 decides+0.223
 register+0.223
 ponies+0.212
Neg logit contributions
orse-0.227
 weapon-0.182
oc-0.179
 bone-0.171
uddy-0.166
Token a
Token ID257
Feature activation-4.17e-01

Pos logit contributions
 groom+0.031
 register+0.031
 roses+0.028
 ponies+0.027
 decides+0.027
Neg logit contributions
orse-0.031
 weapon-0.025
 bone-0.024
 Andy-0.023
 puck-0.023
Token dust
Token ID8977
Feature activation-1.24e+00

Pos logit contributions
 groom+0.021
 roses+0.019
 decides+0.019
 register+0.019
 ponies+0.018
Neg logit contributions
orse-0.028
 weapon-0.023
oc-0.022
 bone-0.022
 hockey-0.021
Tokenpan
Token ID6839
Feature activation-1.55e+01

Pos logit contributions
 groom+0.028
 decides+0.024
 register+0.023
 roses+0.022
 ponies+0.021
Neg logit contributions
orse-0.116
 weapon-0.102
oc-0.099
 bone-0.098
ggy-0.097
Token and
Token ID290
Feature activation-5.47e-01

Pos logit contributions
 groom+0.875
 roses+0.812
 register+0.785
 decides+0.777
 ponies+0.747
Neg logit contributions
orse-0.958
 weapon-0.755
oc-0.752
 bone-0.709
 Carl-0.704
Token start
Token ID923
Feature activation-4.22e+00

Pos logit contributions
 groom+0.033
 register+0.032
 roses+0.029
 ponies+0.029
 decides+0.028
Neg logit contributions
orse-0.031
 weapon-0.025
 bone-0.024
 Andy-0.023
 hockey-0.023
Token to
Token ID284
Feature activation+1.37e-01

Pos logit contributions
 groom+0.224
 roses+0.211
 register+0.198
 decides+0.196
 ponies+0.192
Neg logit contributions
orse-0.277
oc-0.222
 weapon-0.220
uddy-0.208
unch-0.207
Token clean
Token ID3424
Feature activation+3.70e-01

Pos logit contributions
orse+0.009
 weapon+0.007
oc+0.007
 bone+0.007
ggy+0.007
Neg logit contributions
 groom-0.007
 register-0.007
 roses-0.007
 decides-0.006
 ponies-0.006
Token the
Token ID262
Feature activation-4.67e-01

Pos logit contributions
orse+0.026
oc+0.022
 weapon+0.022
 hockey+0.021
 Carl+0.021
Neg logit contributions
 groom-0.017
 register-0.015
 decides-0.015
 roses-0.015
 ponies-0.014
Token m
Token ID285
Feature activation-6.70e+00

Pos logit contributions
 groom+0.021
 roses+0.019
 register+0.019
 decides+0.018
 ponies+0.017
Neg logit contributions
orse-0.029
oc-0.023
 weapon-0.023
oy-0.022
 Carl-0.022
Tokenop
Token ID404
Feature activation+3.56e+00

Pos logit contributions
 groom+0.385
 register+0.380
 roses+0.362
 salon+0.335
 nurses+0.331
Neg logit contributions
orse-0.356
 weapon-0.310
 Benny-0.301
 Carl-0.298
 Freddy-0.293
Token and
Token ID290
Feature activation-5.50e-01

Pos logit contributions
orse+0.210
 weapon+0.167
oc+0.165
 bone+0.158
 Carl+0.154
Neg logit contributions
 groom-0.213
 roses-0.194
 decides-0.190
 register-0.189
 ponies-0.181
Token a
Token ID257
Feature activation-4.18e-01

Pos logit contributions
 groom+0.030
 roses+0.027
 register+0.027
 decides+0.026
 ponies+0.026
Neg logit contributions
orse-0.035
 weapon-0.028
oc-0.027
 bone-0.027
 puck-0.026
Token dust
Token ID8977
Feature activation-1.23e+00

Pos logit contributions
 groom+0.021
 roses+0.019
 register+0.019
 decides+0.018
 ponies+0.017
Neg logit contributions
orse-0.029
oc-0.023
 weapon-0.023
oy-0.022
 Carl-0.022
Tokenpan
Token ID6839
Feature activation-1.55e+01

Pos logit contributions
 groom+0.027
 roses+0.022
 decides+0.021
 register+0.021
 ponies+0.018
Neg logit contributions
orse-0.117
 weapon-0.102
oc-0.101
 bone-0.099
ggy-0.097
Token and
Token ID290
Feature activation-5.29e-01

Pos logit contributions
 groom+0.746
 roses+0.694
 register+0.667
 decides+0.656
 ponies+0.619
Neg logit contributions
orse-1.066
 weapon-0.862
oc-0.858
 Carl-0.822
 puck-0.816
Token cleaned
Token ID20750
Feature activation-1.64e+00

Pos logit contributions
 groom+0.029
 register+0.027
 roses+0.027
 decides+0.026
 ponies+0.026
Neg logit contributions
orse-0.033
 weapon-0.026
oc-0.025
 bone-0.025
 puck-0.024
Token up
Token ID510
Feature activation-5.36e+00

Pos logit contributions
 groom+0.077
 roses+0.068
 register+0.067
 decides+0.065
 ponies+0.063
Neg logit contributions
orse-0.118
oc-0.098
 weapon-0.097
 bone-0.094
 Carl-0.094
Token the
Token ID262
Feature activation-4.27e-01

Pos logit contributions
 groom+0.248
 roses+0.234
 register+0.222
 decides+0.214
 ponies+0.210
Neg logit contributions
orse-0.386
 weapon-0.313
oc-0.308
unch-0.300
uddy-0.298
Token dough
Token ID15756
Feature activation-2.43e-01

Pos logit contributions
 groom+0.025
 roses+0.023
 register+0.023
 decides+0.022
 ponies+0.022
Neg logit contributions
orse-0.025
 weapon-0.020
oc-0.020
 bone-0.019
 hockey-0.019
Token a
Token ID257
Feature activation-4.27e-01

Pos logit contributions
 groom+0.268
 register+0.240
 roses+0.239
 decides+0.232
 ponies+0.232
Neg logit contributions
orse-0.284
 weapon-0.225
 Benny-0.223
 hockey-0.220
oy-0.215
Token broom
Token ID47085
Feature activation-4.02e+00

Pos logit contributions
 groom+0.025
 roses+0.023
 register+0.022
 decides+0.022
 ponies+0.021
Neg logit contributions
orse-0.026
oc-0.020
 weapon-0.020
uddy-0.019
 Carl-0.019
Token and
Token ID290
Feature activation-5.36e-01

Pos logit contributions
 groom+0.250
 roses+0.233
 decides+0.228
 register+0.227
 ponies+0.215
Neg logit contributions
orse-0.221
 weapon-0.181
oc-0.174
 bone-0.169
 hockey-0.162
Token a
Token ID257
Feature activation-4.15e-01

Pos logit contributions
 groom+0.033
 register+0.032
 roses+0.029
 decides+0.029
la+0.029
Neg logit contributions
orse-0.029
 weapon-0.024
 bone-0.023
 Andy-0.022
 hockey-0.022
Token dust
Token ID8977
Feature activation-1.23e+00

Pos logit contributions
 groom+0.021
 decides+0.020
 register+0.020
 roses+0.020
 ponies+0.019
Neg logit contributions
orse-0.027
 weapon-0.023
 bone-0.022
oc-0.021
 hockey-0.021
Tokenpan
Token ID6839
Feature activation-1.55e+01

Pos logit contributions
 groom+0.049
 decides+0.044
 roses+0.043
 register+0.043
 ponies+0.041
Neg logit contributions
orse-0.091
 weapon-0.081
 bone-0.077
oc-0.077
 hockey-0.074
Token.
Token ID13
Feature activation-9.99e-02

Pos logit contributions
 groom+0.894
 roses+0.828
 register+0.808
 decides+0.794
 ponies+0.771
Neg logit contributions
orse-0.938
 weapon-0.735
oc-0.730
 bone-0.693
uddy-0.683
Token You
Token ID921
Feature activation+4.17e+00

Pos logit contributions
 groom+0.007
 register+0.006
 roses+0.006
 ponies+0.006
 decides+0.006
Neg logit contributions
orse-0.005
oc-0.004
 weapon-0.004
 bone-0.003
 Andy-0.003
Token have
Token ID423
Feature activation+1.39e+00

Pos logit contributions
orse+0.280
 weapon+0.232
oc+0.227
 bone+0.222
uddy+0.212
Neg logit contributions
 groom-0.213
 roses-0.196
 register-0.192
 ponies-0.183
 decides-0.177
Token to
Token ID284
Feature activation+1.86e-01

Pos logit contributions
orse+0.075
 weapon+0.058
 bone+0.056
 hockey+0.055
ggy+0.054
Neg logit contributions
 groom-0.087
 register-0.083
 roses-0.080
 decides-0.077
 ponies-0.076
Token clean
Token ID3424
Feature activation+4.07e-01

Pos logit contributions
orse+0.012
 weapon+0.010
oc+0.009
ggy+0.009
 bone+0.009
Neg logit contributions
 groom-0.010
 register-0.009
 roses-0.009
 decides-0.009
 ponies-0.009
Token of
Token ID286
Feature activation+1.30e+00

Pos logit contributions
orse+0.131
oc+0.106
 weapon+0.101
 bone+0.096
ggy+0.096
Neg logit contributions
 groom-0.127
 roses-0.122
 register-0.118
 decides-0.113
 ponies-0.111
Token paper
Token ID3348
Feature activation-3.80e-03

Pos logit contributions
orse+0.091
oc+0.073
 weapon+0.073
uddy+0.070
unch+0.069
Neg logit contributions
 groom-0.064
 roses-0.059
 register-0.056
 decides-0.055
 ponies-0.054
Token and
Token ID290
Feature activation-5.18e-01

Pos logit contributions
 groom+0.000
 roses+0.000
 register+0.000
 decides+0.000
 ponies+0.000
Neg logit contributions
orse-0.000
 weapon-0.000
oc-0.000
 bone-0.000
uddy-0.000
Token a
Token ID257
Feature activation-3.93e-01

Pos logit contributions
 groom+0.028
 register+0.026
 roses+0.026
 decides+0.025
 ponies+0.024
Neg logit contributions
orse-0.033
 weapon-0.027
oc-0.025
 bone-0.025
 Carl-0.024
Token dust
Token ID8977
Feature activation-1.19e+00

Pos logit contributions
 groom+0.021
 roses+0.019
 register+0.019
 decides+0.018
 ponies+0.018
Neg logit contributions
orse-0.026
 weapon-0.021
oc-0.020
 bone-0.020
uddy-0.019
Tokenpan
Token ID6839
Feature activation-1.55e+01

Pos logit contributions
 groom+0.029
 roses+0.023
 decides+0.022
 register+0.022
 ponies+0.020
Neg logit contributions
orse-0.112
 weapon-0.097
oc-0.096
 bone-0.094
ggy-0.092
Token and
Token ID290
Feature activation-4.99e-01

Pos logit contributions
 groom+0.839
 roses+0.787
 register+0.760
 decides+0.742
 ponies+0.716
Neg logit contributions
orse-0.987
oc-0.784
 weapon-0.775
 puck-0.732
 bone-0.730
Token they
Token ID484
Feature activation-4.68e-01

Pos logit contributions
 groom+0.028
 register+0.025
 roses+0.025
 decides+0.024
 ponies+0.024
Neg logit contributions
orse-0.031
 weapon-0.025
oc-0.024
 bone-0.024
 hockey-0.023
Token cleaned
Token ID20750
Feature activation-1.59e+00

Pos logit contributions
 groom+0.029
 roses+0.027
 register+0.027
 decides+0.026
 ponies+0.026
Neg logit contributions
orse-0.026
 weapon-0.020
oc-0.020
 bone-0.019
 Carl-0.018
Token up
Token ID510
Feature activation-5.31e+00

Pos logit contributions
 groom+0.083
 register+0.072
 decides+0.072
 roses+0.072
 ponies+0.069
Neg logit contributions
orse-0.101
oc-0.086
 Carl-0.085
 Andy-0.085
 weapon-0.084
Token the
Token ID262
Feature activation-3.85e-01

Pos logit contributions
 groom+0.290
 roses+0.265
 register+0.259
 decides+0.256
 ponies+0.247
Neg logit contributions
orse-0.339
 weapon-0.270
oc-0.269
 bone-0.256
 Carl-0.254
Token her
Token ID607
Feature activation-6.80e+00

Pos logit contributions
orse+0.306
 Benny+0.280
 Andy+0.277
 Tim+0.275
 weapon+0.275
Neg logit contributions
 groom-0.165
 decides-0.151
 register-0.149
 roses-0.136
 ponies-0.129
Token little
Token ID1310
Feature activation+1.29e+00

Pos logit contributions
 groom+0.269
 roses+0.250
 register+0.225
 ponies+0.220
 decides+0.208
Neg logit contributions
orse-0.550
oc-0.466
 weapon-0.438
unch-0.435
oy-0.432
Token broom
Token ID47085
Feature activation-3.99e+00

Pos logit contributions
orse+0.081
 weapon+0.067
oc+0.064
 bone+0.064
 hockey+0.062
Neg logit contributions
 groom-0.070
 register-0.063
 roses-0.063
 decides-0.062
 ponies-0.058
Token and
Token ID290
Feature activation-4.99e-01

Pos logit contributions
 groom+0.236
 roses+0.217
 register+0.213
 decides+0.212
 ponies+0.203
Neg logit contributions
orse-0.235
 weapon-0.186
oc-0.181
 bone-0.174
uddy-0.172
Token dust
Token ID8977
Feature activation-1.20e+00

Pos logit contributions
 groom+0.028
 register+0.026
 decides+0.026
 roses+0.026
 ponies+0.025
Neg logit contributions
orse-0.030
 weapon-0.024
 Carl-0.023
 Andy-0.022
 Benny-0.022
Tokenpan
Token ID6839
Feature activation-1.55e+01

Pos logit contributions
 groom+0.064
 decides+0.060
 register+0.057
 roses+0.057
 ponies+0.055
Neg logit contributions
orse-0.074
 weapon-0.061
ggy-0.058
 bone-0.057
oc-0.056
Token,
Token ID11
Feature activation-1.07e+00

Pos logit contributions
 groom+0.828
 roses+0.773
 register+0.746
 decides+0.725
 ponies+0.709
Neg logit contributions
orse-1.003
oc-0.799
 weapon-0.790
 bone-0.746
 puck-0.741
Token trying
Token ID2111
Feature activation+3.59e+00

Pos logit contributions
 groom+0.071
 register+0.066
 roses+0.066
 decides+0.065
 ponies+0.063
Neg logit contributions
orse-0.055
 weapon-0.041
oc-0.040
 bone-0.039
 hockey-0.038
Token to
Token ID284
Feature activation+2.18e-01

Pos logit contributions
orse+0.191
 weapon+0.155
 bone+0.144
 hockey+0.142
 Carl+0.141
Neg logit contributions
 groom-0.231
 register-0.212
 decides-0.206
 roses-0.206
 ponies-0.197
Token get
Token ID651
Feature activation-4.60e+00

Pos logit contributions
orse+0.013
 weapon+0.010
ggy+0.010
 Carl+0.009
 bone+0.009
Neg logit contributions
 groom-0.013
 register-0.012
 decides-0.012
 ponies-0.012
 roses-0.012
Token all
Token ID477
Feature activation-3.45e+00

Pos logit contributions
 groom+0.259
 register+0.234
 decides+0.231
 roses+0.227
 ponies+0.225
Neg logit contributions
orse-0.270
 weapon-0.230
 Benny-0.220
 hockey-0.220
 bone-0.214
Token a
Token ID257
Feature activation-3.95e-01

Pos logit contributions
 groom+0.102
 register+0.091
 decides+0.090
 roses+0.089
 ponies+0.085
Neg logit contributions
orse-0.111
 weapon-0.091
 bone-0.088
 Carl-0.086
 hockey-0.086
Token broom
Token ID47085
Feature activation-3.99e+00

Pos logit contributions
 groom+0.022
 roses+0.020
 register+0.020
 decides+0.019
 ponies+0.019
Neg logit contributions
orse-0.025
 weapon-0.020
oc-0.020
 bone-0.019
 puck-0.018
Token and
Token ID290
Feature activation-5.12e-01

Pos logit contributions
 groom+0.239
 roses+0.219
 decides+0.217
 register+0.213
 ponies+0.205
Neg logit contributions
orse-0.229
 weapon-0.187
oc-0.180
 bone-0.175
ggy-0.170
Token a
Token ID257
Feature activation-3.80e-01

Pos logit contributions
 groom+0.029
 register+0.028
 decides+0.026
 roses+0.026
 ponies+0.025
Neg logit contributions
orse-0.030
 weapon-0.024
 bone-0.023
 Andy-0.022
 puck-0.022
Token dust
Token ID8977
Feature activation-1.20e+00

Pos logit contributions
 groom+0.019
 decides+0.018
 register+0.018
 roses+0.018
 ponies+0.017
Neg logit contributions
orse-0.025
 weapon-0.021
 bone-0.020
oc-0.020
 puck-0.019
Tokenpan
Token ID6839
Feature activation-1.55e+01

Pos logit contributions
 groom+0.039
 decides+0.034
 roses+0.033
 register+0.032
 ponies+0.030
Neg logit contributions
orse-0.100
 weapon-0.087
oc-0.085
 bone-0.084
ggy-0.083
Token.
Token ID13
Feature activation-5.91e-02

Pos logit contributions
 groom+0.806
 roses+0.749
 register+0.733
 decides+0.709
 ponies+0.684
Neg logit contributions
orse-1.024
oc-0.814
 weapon-0.806
 Carl-0.770
uddy-0.762
Token
Token ID198
Feature activation-2.78e-01

Pos logit contributions
 groom+0.003
 roses+0.003
 decides+0.003
 register+0.003
 ponies+0.003
Neg logit contributions
orse-0.004
 weapon-0.003
oc-0.003
oy-0.003
ggy-0.003
Token
Token ID198
Feature activation-2.78e-01

Pos logit contributions
 groom+0.014
 roses+0.014
 decides+0.013
 register+0.013
She+0.013
Neg logit contributions
orse-0.017
 weapon-0.014
oy-0.013
oc-0.013
 puck-0.013
Token"
Token ID1
Feature activation-5.21e+00

Pos logit contributions
 groom+0.012
 roses+0.011
 register+0.010
 decides+0.010
 ponies+0.010
Neg logit contributions
orse-0.021
 weapon-0.018
oc-0.018
 bone-0.017
uddy-0.017
TokenCan
Token ID6090
Feature activation-1.07e+01

Pos logit contributions
 groom+0.225
 register+0.216
 roses+0.206
 ponies+0.204
 decides+0.196
Neg logit contributions
orse-0.363
oc-0.297
 puck-0.294
 bone-0.292
ggy-0.292
Token a
Token ID257
Feature activation-3.25e-01

Pos logit contributions
 groom+0.417
 roses+0.374
 register+0.369
 decides+0.366
 ponies+0.347
Neg logit contributions
orse-0.520
 weapon-0.430
 bone-0.417
oc-0.414
 Carl-0.411
Token broom
Token ID47085
Feature activation-3.92e+00

Pos logit contributions
 groom+0.017
 roses+0.016
 register+0.015
 decides+0.015
 ponies+0.015
Neg logit contributions
orse-0.021
 weapon-0.017
oc-0.017
 bone-0.016
uddy-0.016
Token and
Token ID290
Feature activation-4.26e-01

Pos logit contributions
 groom+0.214
 roses+0.199
 register+0.194
 decides+0.188
 ponies+0.184
Neg logit contributions
orse-0.249
 weapon-0.193
oc-0.193
 Carl-0.184
unch-0.184
Token a
Token ID257
Feature activation-3.00e-01

Pos logit contributions
 groom+0.025
 register+0.023
 roses+0.023
 decides+0.022
 ponies+0.021
Neg logit contributions
orse-0.025
 weapon-0.020
 bone-0.020
 hockey-0.019
 puck-0.019
Token dust
Token ID8977
Feature activation-1.10e+00

Pos logit contributions
 groom+0.016
 register+0.015
 decides+0.015
 roses+0.015
 ponies+0.014
Neg logit contributions
orse-0.019
 weapon-0.016
 bone-0.015
oc-0.015
 hockey-0.015
Tokenpan
Token ID6839
Feature activation-1.54e+01

Pos logit contributions
 groom+0.030
 roses+0.026
 decides+0.025
 register+0.025
 ponies+0.022
Neg logit contributions
orse-0.099
 weapon-0.086
oc-0.084
 bone-0.083
 puck-0.082
Token.
Token ID13
Feature activation+2.57e-02

Pos logit contributions
 groom+0.813
 roses+0.757
 register+0.732
 decides+0.721
 ponies+0.688
Neg logit contributions
orse-0.994
oc-0.791
 weapon-0.789
 Carl-0.753
uddy-0.743
Token They
Token ID1119
Feature activation+7.55e-01

Pos logit contributions
orse+0.001
 weapon+0.001
oc+0.001
 bone+0.001
uddy+0.000
Neg logit contributions
 groom-0.002
 roses-0.002
 register-0.002
 decides-0.002
 ponies-0.002
Token help
Token ID1037
Feature activation-3.26e+00

Pos logit contributions
orse+0.041
 weapon+0.034
oc+0.033
 bone+0.033
 Carl+0.031
Neg logit contributions
 groom-0.045
 register-0.042
 roses-0.041
 ponies-0.040
 decides-0.039
Token him
Token ID683
Feature activation+3.37e+00

Pos logit contributions
 groom+0.157
 roses+0.141
 decides+0.141
 register+0.140
 ponies+0.132
Neg logit contributions
orse-0.215
 Carl-0.180
ggy-0.177
 hockey-0.176
 bone-0.175
Token sweep
Token ID16085
Feature activation-2.93e+00

Pos logit contributions
orse+0.202
 weapon+0.162
oc+0.157
 bone+0.154
ggy+0.154
Neg logit contributions
 groom-0.198
 register-0.180
 roses-0.178
 ponies-0.174
 decides-0.173
Token a
Token ID257
Feature activation-1.84e-01

Pos logit contributions
 groom+0.252
 roses+0.224
 decides+0.223
 ponies+0.217
 register+0.214
Neg logit contributions
orse-0.249
 Tim-0.224
 Benny-0.221
 weapon-0.215
 Andy-0.215
Token broom
Token ID47085
Feature activation-3.76e+00

Pos logit contributions
 groom+0.010
 roses+0.009
 register+0.009
 decides+0.008
 ponies+0.008
Neg logit contributions
orse-0.012
oc-0.010
 weapon-0.009
oy-0.009
 Carl-0.009
Token and
Token ID290
Feature activation-2.88e-01

Pos logit contributions
 groom+0.237
 roses+0.221
 decides+0.218
 register+0.213
 ponies+0.204
Neg logit contributions
orse-0.205
 weapon-0.168
oc-0.164
 bone-0.159
 hockey-0.149
Token a
Token ID257
Feature activation-1.69e-01

Pos logit contributions
 groom+0.018
 register+0.017
 roses+0.016
 decides+0.016
 ponies+0.016
Neg logit contributions
orse-0.015
 weapon-0.013
 bone-0.012
 Andy-0.012
 hockey-0.012
Token dust
Token ID8977
Feature activation-9.66e-01

Pos logit contributions
 groom+0.008
 roses+0.008
 register+0.008
 decides+0.008
 ponies+0.007
Neg logit contributions
orse-0.011
 weapon-0.009
oc-0.009
 bone-0.009
uddy-0.009
Tokenpan
Token ID6839
Feature activation-1.52e+01

Pos logit contributions
 groom+0.023
 decides+0.022
 roses+0.019
 register+0.018
 ponies+0.017
Neg logit contributions
orse-0.087
 weapon-0.079
 bone-0.076
oc-0.076
 hockey-0.074
Token to
Token ID284
Feature activation+4.40e-01

Pos logit contributions
 groom+0.953
 roses+0.883
 register+0.863
 decides+0.852
 ponies+0.830
Neg logit contributions
orse-0.849
 weapon-0.654
oc-0.648
 bone-0.620
ggy-0.606
Token clean
Token ID3424
Feature activation+6.76e-01

Pos logit contributions
orse+0.028
 weapon+0.023
oc+0.022
 bone+0.022
ggy+0.022
Neg logit contributions
 groom-0.024
 register-0.022
 decides-0.022
 roses-0.022
 ponies-0.021
Token up
Token ID510
Feature activation-5.07e+00

Pos logit contributions
orse+0.036
oc+0.030
 weapon+0.030
 bone+0.029
 hockey+0.029
Neg logit contributions
 groom-0.042
 decides-0.037
 register-0.037
 roses-0.036
 ponies-0.036
Token the
Token ID262
Feature activation-1.36e-01

Pos logit contributions
 groom+0.306
 roses+0.280
 register+0.275
 decides+0.274
 ponies+0.262
Neg logit contributions
orse-0.296
 weapon-0.232
oc-0.231
 bone-0.220
 Carl-0.216
Token mess
Token ID2085
Feature activation+4.02e+00

Pos logit contributions
 groom+0.008
 roses+0.007
 register+0.007
 decides+0.007
 ponies+0.006
Neg logit contributions
orse-0.009
 weapon-0.007
oc-0.007
 bone-0.007
 hockey-0.006
Token word
Token ID1573
Feature activation+7.63e-01

Pos logit contributions
orse+0.030
unch+0.023
orses+0.023
oy+0.022
inations+0.022
Neg logit contributions
 groom-0.023
 roses-0.021
 mirror-0.020
 decides-0.020
 ponies-0.019
Token:
Token ID25
Feature activation-3.63e+00

Pos logit contributions
orse+0.042
 weapon+0.033
oc+0.032
 bone+0.031
ggy+0.030
Neg logit contributions
 groom-0.048
 roses-0.044
 register-0.043
 decides-0.043
 ponies-0.041
Token pin
Token ID6757
Feature activation+4.33e+00

Pos logit contributions
 groom+0.210
 roses+0.194
 register+0.190
 decides+0.186
 ponies+0.180
Neg logit contributions
orse-0.220
 weapon-0.172
oc-0.171
 bone-0.162
 Carl-0.160
Token.
Token ID13
Feature activation-1.31e-01

Pos logit contributions
orse+0.244
 weapon+0.191
oc+0.189
 bone+0.178
ggy+0.176
Neg logit contributions
 groom-0.268
 roses-0.248
 register-0.243
 decides-0.237
 ponies-0.232
Token He
Token ID679
Feature activation+4.49e+00

Pos logit contributions
 groom+0.009
 roses+0.008
 decides+0.008
 register+0.008
 Angel+0.008
Neg logit contributions
orse-0.006
 weapon-0.005
oc-0.005
oy-0.004
ggy-0.004
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
orse+0.305
oc+0.252
 weapon+0.252
 bone+0.241
 puck+0.239
Neg logit contributions
 groom-0.222
 register-0.206
 roses-0.204
 ponies-0.188
 nurses-0.181
Token not
Token ID407
Feature activation+2.17e+00

Pos logit contributions
 groom+0.804
 roses+0.748
 decides+0.710
 register+0.705
 ponies+0.690
Neg logit contributions
orse-1.004
oc-0.813
 weapon-0.793
uddy-0.769
unch-0.762
Token to
Token ID284
Feature activation+1.40e-01

Pos logit contributions
orse+0.157
oc+0.135
uddy+0.125
oy+0.124
ggy+0.124
Neg logit contributions
 groom-0.102
 decides-0.094
 roses-0.092
 ponies-0.085
 register-0.080
Token play
Token ID711
Feature activation+2.30e+00

Pos logit contributions
orse+0.009
 weapon+0.007
oc+0.007
 bone+0.007
uddy+0.007
Neg logit contributions
 groom-0.007
 roses-0.007
 register-0.007
 decides-0.006
 ponies-0.006
Token with
Token ID351
Feature activation+4.17e+00

Pos logit contributions
orse+0.123
 weapon+0.091
oc+0.091
uddy+0.086
 bone+0.085
Neg logit contributions
 groom-0.151
 roses-0.141
 register-0.138
 decides-0.136
 ponies-0.132
Token pins
Token ID20567
Feature activation+1.02e+00

Pos logit contributions
orse+0.262
oc+0.205
 weapon+0.203
unch+0.195
uddy+0.195
Neg logit contributions
 groom-0.232
 roses-0.218
 register-0.208
 decides-0.205
 ponies-0.200
Token for
Token ID329
Feature activation+2.91e+00

Pos logit contributions
 groom+0.257
 roses+0.241
 register+0.234
 decides+0.231
 ponies+0.224
Neg logit contributions
orse-0.277
 weapon-0.215
oc-0.215
 bone-0.203
ggy-0.201
Token the
Token ID262
Feature activation-4.77e-01

Pos logit contributions
orse+0.193
 weapon+0.155
oc+0.153
 bone+0.147
 Carl+0.146
Neg logit contributions
 groom-0.151
 roses-0.138
 register-0.135
 decides-0.133
 ponies-0.128
Token elephant
Token ID20950
Feature activation-6.58e-01

Pos logit contributions
 groom+0.024
 roses+0.022
 register+0.021
 decides+0.021
 ponies+0.021
Neg logit contributions
orse-0.034
unch-0.026
oc-0.026
 weapon-0.025
 puck-0.025
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
 groom+0.031
 register+0.029
 roses+0.029
 ponies+0.028
 decides+0.027
Neg logit contributions
orse-0.045
unch-0.035
 weapon-0.035
 puck-0.035
oy-0.035
Token She
Token ID1375
Feature activation-6.11e+00

Pos logit contributions
 groom+0.008
 roses+0.008
 register+0.008
 decides+0.007
 ponies+0.007
Neg logit contributions
orse-0.007
oc-0.005
 weapon-0.005
 bone-0.005
 Carl-0.005
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.310
 register+0.288
 roses+0.282
pan+0.259
 ponies+0.257
Neg logit contributions
orse-0.404
 weapon-0.344
oc-0.335
 bone-0.332
 puck-0.316
Token to
Token ID284
Feature activation+1.54e-01

Pos logit contributions
 groom+0.854
 roses+0.792
 register+0.765
 decides+0.757
 ponies+0.734
Neg logit contributions
orse-0.956
 weapon-0.754
oc-0.753
 bone-0.711
uddy-0.705
Token teach
Token ID4545
Feature activation-2.77e+00

Pos logit contributions
orse+0.011
 weapon+0.009
oc+0.008
 bone+0.008
uddy+0.008
Neg logit contributions
 groom-0.008
 roses-0.007
 register-0.007
 decides-0.007
 ponies-0.006
Token him
Token ID683
Feature activation+3.21e+00

Pos logit contributions
 groom+0.172
 roses+0.158
 register+0.157
 decides+0.154
 ponies+0.147
Neg logit contributions
orse-0.154
 weapon-0.118
oc-0.116
 bone-0.114
 Carl-0.113
Token some
Token ID617
Feature activation-4.07e+00

Pos logit contributions
orse+0.208
 weapon+0.167
oc+0.165
 bone+0.159
ggy+0.157
Neg logit contributions
 groom-0.172
 roses-0.156
 register-0.154
 decides-0.150
 ponies-0.144
Token things
Token ID1243
Feature activation+1.71e+00

Pos logit contributions
 groom+0.216
 roses+0.208
 ponies+0.194
 register+0.192
 decides+0.192
Neg logit contributions
orse-0.270
oc-0.209
 weapon-0.202
uddy-0.200
unch-0.197
Token judge
Token ID5052
Feature activation-1.47e+00

Pos logit contributions
 groom+0.005
 roses+0.004
 register+0.004
 decides+0.004
 ponies+0.004
Neg logit contributions
orse-0.006
oc-0.005
 weapon-0.005
unch-0.005
uddy-0.005
Token is
Token ID318
Feature activation-2.55e+00

Pos logit contributions
 groom+0.093
 roses+0.087
 register+0.085
 decides+0.084
 ponies+0.082
Neg logit contributions
orse-0.081
 weapon-0.061
oc-0.061
 bone-0.057
uddy-0.057
Token a
Token ID257
Feature activation-4.28e-01

Pos logit contributions
 groom+0.144
 roses+0.135
 register+0.131
 decides+0.131
 ponies+0.124
Neg logit contributions
orse-0.155
 weapon-0.123
oc-0.119
 bone-0.117
ggy-0.115
Token person
Token ID1048
Feature activation-1.73e+00

Pos logit contributions
 groom+0.024
 roses+0.022
 register+0.021
 decides+0.021
 ponies+0.020
Neg logit contributions
orse-0.027
oc-0.021
 weapon-0.021
unch-0.020
uddy-0.020
Token who
Token ID508
Feature activation-3.45e-01

Pos logit contributions
 groom+0.091
 roses+0.084
 register+0.082
 ponies+0.079
 decides+0.078
Neg logit contributions
orse-0.113
 weapon-0.090
oc-0.089
unch-0.086
uddy-0.086
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.020
 roses+0.019
 decides+0.018
 register+0.018
 ponies+0.017
Neg logit contributions
orse-0.021
 weapon-0.016
oc-0.016
unch-0.015
uddy-0.015
Token who
Token ID508
Feature activation-3.56e-01

Pos logit contributions
 groom+0.872
 roses+0.806
 register+0.789
 decides+0.774
 ponies+0.749
Neg logit contributions
orse-0.927
 weapon-0.729
oc-0.720
 bone-0.688
ggy-0.676
Token is
Token ID318
Feature activation-2.56e+00

Pos logit contributions
 groom+0.020
 roses+0.019
 register+0.019
 decides+0.018
 ponies+0.018
Neg logit contributions
orse-0.022
 weapon-0.017
oc-0.017
 bone-0.016
uddy-0.016
Token right
Token ID826
Feature activation+3.26e-01

Pos logit contributions
 groom+0.148
 roses+0.140
 register+0.136
 decides+0.134
 ponies+0.128
Neg logit contributions
orse-0.150
 weapon-0.118
oc-0.114
 bone-0.112
ggy-0.111
Token and
Token ID290
Feature activation-5.58e-01

Pos logit contributions
orse+0.014
 weapon+0.012
oc+0.011
 bone+0.011
 hockey+0.011
Neg logit contributions
 groom-0.023
 roses-0.021
 decides-0.020
 register-0.020
 ponies-0.020
Token who
Token ID508
Feature activation-3.64e-01

Pos logit contributions
 groom+0.031
 roses+0.029
 register+0.028
 decides+0.026
 ponies+0.026
Neg logit contributions
orse-0.034
 weapon-0.028
oc-0.027
 bone-0.026
 hockey-0.026
Token a
Token ID257
Feature activation-4.40e-01

Pos logit contributions
 groom+0.031
 roses+0.029
 register+0.029
 decides+0.028
 ponies+0.027
Neg logit contributions
orse-0.034
 weapon-0.027
oc-0.026
 bone-0.025
 Carl-0.025
Token bad
Token ID2089
Feature activation-1.10e+00

Pos logit contributions
 groom+0.025
 roses+0.023
 register+0.023
 decides+0.022
 ponies+0.022
Neg logit contributions
orse-0.027
 weapon-0.022
oc-0.021
 bone-0.020
 puck-0.020
Token friend
Token ID1545
Feature activation+2.91e+00

Pos logit contributions
 groom+0.058
 roses+0.053
 register+0.052
 decides+0.051
 ponies+0.049
Neg logit contributions
orse-0.073
oc-0.058
 weapon-0.058
 bone-0.055
unch-0.054
Token.
Token ID13
Feature activation-1.34e-01

Pos logit contributions
orse+0.162
 weapon+0.126
oc+0.125
 bone+0.118
ggy+0.116
Neg logit contributions
 groom-0.182
 roses-0.169
 register-0.164
 decides-0.161
 ponies-0.156
Token She
Token ID1375
Feature activation-6.10e+00

Pos logit contributions
 groom+0.005
 register+0.005
 roses+0.005
 decides+0.004
 ponies+0.004
Neg logit contributions
orse-0.011
oc-0.009
 weapon-0.009
 Carl-0.009
uddy-0.009
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.324
 roses+0.295
 register+0.294
 ponies+0.269
pan+0.269
Neg logit contributions
orse-0.381
 weapon-0.323
oc-0.319
 bone-0.310
 puck-0.305
Token to
Token ID284
Feature activation+1.46e-01

Pos logit contributions
 groom+0.892
 roses+0.823
 register+0.811
 decides+0.792
 ponies+0.766
Neg logit contributions
orse-0.916
 weapon-0.717
oc-0.703
 bone-0.676
ggy-0.666
Token teach
Token ID4545
Feature activation-2.79e+00

Pos logit contributions
orse+0.010
oc+0.008
 weapon+0.008
unch+0.008
uddy+0.008
Neg logit contributions
 groom-0.007
 roses-0.007
 decides-0.006
 register-0.006
 ponies-0.006
Token him
Token ID683
Feature activation+3.21e+00

Pos logit contributions
 groom+0.159
 roses+0.149
 register+0.143
 decides+0.142
 ponies+0.138
Neg logit contributions
orse-0.172
oc-0.135
 weapon-0.134
 bone-0.126
unch-0.125
Token a
Token ID257
Feature activation-4.33e-01

Pos logit contributions
orse+0.225
oc+0.181
 weapon+0.180
uddy+0.172
unch+0.172
Neg logit contributions
 groom-0.156
 roses-0.144
 register-0.139
 decides-0.138
 ponies-0.133
Token lesson
Token ID11483
Feature activation+5.36e-01

Pos logit contributions
 groom+0.027
 roses+0.025
 decides+0.024
 ponies+0.023
 register+0.023
Neg logit contributions
orse-0.025
oc-0.019
oy-0.018
unch-0.018
 burying-0.017
Token is
Token ID318
Feature activation-2.56e+00

Pos logit contributions
 groom+0.359
 register+0.350
 roses+0.317
pan+0.305
 ponies+0.298
Neg logit contributions
orse-0.372
 weapon-0.289
oc-0.281
 Carl-0.274
 bone-0.272
Token uncomfortable
Token ID12916
Feature activation+3.22e+00

Pos logit contributions
 groom+0.166
 register+0.160
 decides+0.156
 roses+0.155
als+0.147
Neg logit contributions
orse-0.129
 weapon-0.095
 burying-0.094
ggy-0.092
 Andy-0.092
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
orse+0.197
oc+0.152
 weapon+0.150
 puck+0.141
 bone+0.140
Neg logit contributions
 groom-0.185
 roses-0.177
 register-0.170
 decides-0.166
 ponies-0.165
Token so
Token ID523
Feature activation+3.01e-02

Pos logit contributions
 groom+0.076
 roses+0.072
 decides+0.068
 register+0.068
 ponies+0.067
Neg logit contributions
orse-0.060
oc-0.045
 weapon-0.044
uddy-0.042
oy-0.041
Token she
Token ID673
Feature activation-5.47e+00

Pos logit contributions
orse+0.002
 Andy+0.002
 he+0.002
ggy+0.002
 weapon+0.002
Neg logit contributions
 groom-0.001
 register-0.001
 decides-0.001
 roses-0.001
pan-0.001
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.315
 register+0.309
 roses+0.289
 ponies+0.272
pan+0.268
Neg logit contributions
orse-0.322
 weapon-0.257
 bone-0.238
 puck-0.235
ggy-0.235
Token to
Token ID284
Feature activation+1.35e-01

Pos logit contributions
 groom+1.003
 register+0.965
 decides+0.910
 roses+0.904
 ponies+0.864
Neg logit contributions
orse-0.780
 weapon-0.584
 bone-0.546
ggy-0.543
oc-0.524
Token stay
Token ID2652
Feature activation+5.22e-02

Pos logit contributions
orse+0.009
 weapon+0.007
oc+0.007
 bone+0.007
ggy+0.007
Neg logit contributions
 groom-0.007
 register-0.006
 roses-0.006
 decides-0.006
 ponies-0.006
Token in
Token ID287
Feature activation+9.48e-01

Pos logit contributions
orse+0.003
 weapon+0.003
oc+0.003
 hockey+0.003
 bone+0.003
Neg logit contributions
 groom-0.003
 register-0.003
 roses-0.003
 decides-0.003
 ponies-0.002
Token her
Token ID607
Feature activation-6.84e+00

Pos logit contributions
orse+0.063
 weapon+0.051
oc+0.050
 bone+0.049
 hockey+0.048
Neg logit contributions
 groom-0.049
 register-0.045
 roses-0.044
 decides-0.044
 ponies-0.041
Token bed
Token ID3996
Feature activation+1.68e+00

Pos logit contributions
 groom+0.403
 register+0.369
 roses+0.361
 decides+0.359
 ponies+0.337
Neg logit contributions
orse-0.407
 weapon-0.332
oc-0.320
 bone-0.318
ggy-0.305
Token red
Token ID2266
Feature activation-1.74e+00

Pos logit contributions
 groom+0.351
 register+0.324
 roses+0.312
 decides+0.312
 ponies+0.285
Neg logit contributions
orse-0.452
 weapon-0.380
 bone-0.365
ggy-0.354
 hockey-0.353
Token dress
Token ID6576
Feature activation-2.75e+00

Pos logit contributions
 groom+0.104
 register+0.097
 decides+0.093
 roses+0.091
 nurses+0.085
Neg logit contributions
orse-0.095
 weapon-0.087
 bone-0.086
 hockey-0.082
oc-0.081
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
 groom+0.171
 roses+0.159
 decides+0.155
 register+0.155
 ponies+0.148
Neg logit contributions
orse-0.151
 weapon-0.121
oc-0.117
 bone-0.115
ggy-0.112
Token but
Token ID475
Feature activation+4.28e+00

Pos logit contributions
 groom+0.073
 roses+0.070
 decides+0.065
 ponies+0.065
 register+0.062
Neg logit contributions
orse-0.061
oc-0.048
 weapon-0.046
oy-0.045
uddy-0.044
Token she
Token ID673
Feature activation-5.47e+00

Pos logit contributions
orse+0.316
 weapon+0.260
 bone+0.253
 Carl+0.252
 hockey+0.248
Neg logit contributions
 groom-0.185
 register-0.168
 roses-0.163
 decides-0.157
 ponies-0.150
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.274
 roses+0.249
 register+0.246
 ponies+0.228
 decides+0.226
Neg logit contributions
orse-0.372
 weapon-0.303
oc-0.302
 bone-0.293
 Carl-0.286
Token to
Token ID284
Feature activation+1.60e-01

Pos logit contributions
 groom+1.006
 register+0.986
 roses+0.914
 decides+0.910
 nurses+0.879
Neg logit contributions
orse-0.761
 weapon-0.555
ggy-0.534
 bone-0.531
 hockey-0.530
Token t
Token ID256
Feature activation-5.47e+00

Pos logit contributions
orse+0.011
 weapon+0.008
oc+0.008
 bone+0.008
uddy+0.008
Neg logit contributions
 groom-0.008
 roses-0.008
 register-0.007
 decides-0.007
 ponies-0.007
Tokenuck
Token ID1347
Feature activation-1.30e+00

Pos logit contributions
 groom+0.249
 roses+0.229
 decides+0.218
 register+0.216
 ponies+0.205
Neg logit contributions
orse-0.399
oc-0.325
 weapon-0.323
unch-0.316
ggy-0.314
Token the
Token ID262
Feature activation-4.61e-01

Pos logit contributions
 groom+0.062
 register+0.058
 decides+0.056
 ponies+0.053
 heavens+0.050
Neg logit contributions
 he-0.070
orse-0.069
 Benny-0.069
 Tim-0.069
 Carl-0.068
Token cord
Token ID15050
Feature activation-2.73e+00

Pos logit contributions
 groom+0.026
 register+0.024
 decides+0.024
 roses+0.023
 ponies+0.022
Neg logit contributions
orse-0.026
 weapon-0.023
 bone-0.023
 puck-0.021
 hockey-0.021
Token a
Token ID257
Feature activation-4.29e-01

Pos logit contributions
 groom+0.277
 roses+0.256
 register+0.249
 decides+0.245
 ponies+0.238
Neg logit contributions
orse-0.304
 weapon-0.240
oc-0.237
 bone-0.226
 Carl-0.223
Token little
Token ID1310
Feature activation+1.27e+00

Pos logit contributions
 groom+0.024
 roses+0.022
 decides+0.021
 register+0.021
 ponies+0.020
Neg logit contributions
orse-0.026
 weapon-0.020
oc-0.020
oy-0.019
uddy-0.019
Token better
Token ID1365
Feature activation-7.19e+00

Pos logit contributions
orse+0.086
oc+0.068
 weapon+0.067
uddy+0.066
oy+0.066
Neg logit contributions
 groom-0.065
 roses-0.059
 decides-0.058
 register-0.057
 ponies-0.054
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
 groom+0.359
 roses+0.311
 register+0.304
 decides+0.302
 bride+0.279
Neg logit contributions
orse-0.478
 Andy-0.395
uddy-0.393
 Carl-0.390
unch-0.387
Token He
Token ID679
Feature activation+4.49e+00

Pos logit contributions
 groom+0.009
 roses+0.009
 decides+0.009
 register+0.008
 ponies+0.008
Neg logit contributions
orse-0.006
inations-0.004
 weapon-0.004
oy-0.004
oc-0.004
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
orse+0.321
 weapon+0.269
oc+0.264
 bone+0.258
 puck+0.255
Neg logit contributions
 groom-0.211
 register-0.190
 roses-0.188
 ponies-0.172
 nurses-0.167
Token to
Token ID284
Feature activation+1.42e-01

Pos logit contributions
 groom+0.752
 roses+0.713
 decides+0.669
 register+0.657
 ponies+0.650
Neg logit contributions
orse-1.032
oc-0.858
 weapon-0.819
unch-0.810
uddy-0.795
Token try
Token ID1949
Feature activation-1.54e+00

Pos logit contributions
orse+0.010
oc+0.008
 weapon+0.008
unch+0.008
uddy+0.008
Neg logit contributions
 groom-0.007
 roses-0.006
 decides-0.006
 register-0.006
 ponies-0.006
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
 groom+0.088
 roses+0.080
 register+0.080
 decides+0.078
 ponies+0.075
Neg logit contributions
orse-0.095
 weapon-0.076
oc-0.073
 bone-0.072
 hockey-0.071
Token He
Token ID679
Feature activation+4.48e+00

Pos logit contributions
 groom+0.009
 roses+0.009
 decides+0.009
 register+0.008
 Angel+0.008
Neg logit contributions
orse-0.005
 weapon-0.004
inations-0.004
oc-0.003
oy-0.003
Token pushes
Token ID20070
Feature activation-3.91e+00

Pos logit contributions
orse+0.302
 puck+0.258
 weapon+0.255
oc+0.253
 bone+0.250
Neg logit contributions
 groom-0.215
 register-0.203
 roses-0.191
 ponies-0.176
 nurses-0.175
Token
Token ID198
Feature activation-3.48e-01

Pos logit contributions
 groom+0.021
 roses+0.021
 decides+0.020
 register+0.020
 ponies+0.019
Neg logit contributions
orse-0.019
 weapon-0.015
oc-0.015
 puck-0.014
 bone-0.014
TokenOne
Token ID3198
Feature activation-4.34e+00

Pos logit contributions
 groom+0.018
 roses+0.016
 register+0.016
 decides+0.015
 ponies+0.015
Neg logit contributions
orse-0.024
oc-0.019
 weapon-0.019
ggy-0.019
uddy-0.018
Token day
Token ID1110
Feature activation+2.68e+00

Pos logit contributions
 groom+0.244
 roses+0.241
 decides+0.221
 nurses+0.221
 register+0.216
Neg logit contributions
orse-0.251
unch-0.197
 bullets-0.196
 puck-0.194
 weapon-0.194
Token,
Token ID11
Feature activation-1.14e+00

Pos logit contributions
orse+0.129
 weapon+0.095
 Carl+0.092
oy+0.091
ggy+0.090
Neg logit contributions
 groom-0.189
 register-0.172
 decides-0.172
 roses-0.172
 ponies-0.166
Token Sara
Token ID24799
Feature activation-4.27e+00

Pos logit contributions
 groom+0.055
 register+0.050
 decides+0.050
 roses+0.050
 ponies+0.046
Neg logit contributions
orse-0.078
 weapon-0.064
 Carl-0.063
 bone-0.062
oc-0.062
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.220
 roses+0.200
 register+0.193
 ponies+0.185
 Angel+0.179
Neg logit contributions
orse-0.288
 weapon-0.238
oc-0.236
 bone-0.222
 puck-0.216
Token to
Token ID284
Feature activation+1.40e-01

Pos logit contributions
 groom+0.926
 register+0.857
 roses+0.842
 decides+0.828
 ponies+0.791
Neg logit contributions
orse-0.875
 weapon-0.686
oc-0.651
 bone-0.646
ggy-0.638
Token make
Token ID787
Feature activation-1.00e+00

Pos logit contributions
orse+0.009
 weapon+0.007
oc+0.007
 bone+0.007
uddy+0.007
Neg logit contributions
 groom-0.007
 roses-0.007
 register-0.007
 decides-0.006
 ponies-0.006
Token the
Token ID262
Feature activation-4.75e-01

Pos logit contributions
 groom+0.055
 roses+0.050
 register+0.049
 decides+0.049
 ponies+0.047
Neg logit contributions
orse-0.064
 weapon-0.051
oc-0.050
 bone-0.049
ggy-0.048
Token box
Token ID3091
Feature activation+3.47e-01

Pos logit contributions
 groom+0.023
 roses+0.021
 decides+0.021
 register+0.021
 ponies+0.020
Neg logit contributions
orse-0.032
 weapon-0.027
oc-0.026
 bone-0.026
 puck-0.025
Token into
Token ID656
Feature activation-2.77e+00

Pos logit contributions
orse+0.019
 weapon+0.015
oc+0.015
 bone+0.014
ggy+0.014
Neg logit contributions
 groom-0.021
 roses-0.020
 decides-0.019
 register-0.019
 ponies-0.019
Token back
Token ID736
Feature activation-9.27e+00

Pos logit contributions
 groom+0.040
 register+0.035
 roses+0.034
 ponies+0.030
 decides+0.030
Neg logit contributions
orse-0.089
 weapon-0.078
oc-0.076
 bone-0.075
oy-0.073
Token.
Token ID13
Feature activation-1.21e-01

Pos logit contributions
 groom+0.602
 roses+0.555
 register+0.547
 decides+0.524
 ponies+0.516
Neg logit contributions
orse-0.505
 weapon-0.395
oc-0.394
 bone-0.372
oy-0.359
Token
Token ID198
Feature activation-3.37e-01

Pos logit contributions
 groom+0.007
 decides+0.007
 roses+0.007
 register+0.006
 Angel+0.006
Neg logit contributions
orse-0.007
 weapon-0.005
inations-0.005
oc-0.005
oy-0.005
Token
Token ID198
Feature activation-3.46e-01

Pos logit contributions
 decides+0.015
 roses+0.015
She+0.015
 groom+0.015
 Angel+0.014
Neg logit contributions
orse-0.021
 weapon-0.018
oy-0.017
 puck-0.017
oc-0.017
TokenHe
Token ID1544
Feature activation+2.10e+00

Pos logit contributions
 groom+0.018
 decides+0.017
She+0.017
 register+0.017
 roses+0.017
Neg logit contributions
orse-0.021
 weapon-0.017
 Carl-0.017
unch-0.016
 bone-0.016
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
orse+0.135
 weapon+0.119
 puck+0.119
 che+0.116
oc+0.115
Neg logit contributions
 groom-0.102
 register-0.095
 roses-0.087
 ponies-0.084
pan-0.080
Token to
Token ID284
Feature activation+1.64e-01

Pos logit contributions
 groom+0.736
 roses+0.692
 decides+0.656
 register+0.629
 ponies+0.624
Neg logit contributions
orse-1.047
oc-0.880
 weapon-0.840
unch-0.832
uddy-0.824
Token look
Token ID804
Feature activation+8.64e-01

Pos logit contributions
orse+0.011
 weapon+0.009
oc+0.009
 bone+0.008
 Carl+0.008
Neg logit contributions
 groom-0.009
 roses-0.008
 register-0.008
 decides-0.007
 ponies-0.007
Token for
Token ID329
Feature activation+2.93e+00

Pos logit contributions
orse+0.042
 weapon+0.034
oc+0.033
 bone+0.032
 hockey+0.031
Neg logit contributions
 groom-0.061
 roses-0.055
 register-0.054
 ponies-0.051
 salon-0.051
Token a
Token ID257
Feature activation-4.10e-01

Pos logit contributions
orse+0.203
oc+0.166
 weapon+0.164
uddy+0.158
unch+0.157
Neg logit contributions
 groom-0.144
 roses-0.133
 register-0.127
 decides-0.125
 ponies-0.120
Token real
Token ID1103
Feature activation-3.79e+00

Pos logit contributions
 groom+0.024
 roses+0.022
 decides+0.021
 register+0.021
 ponies+0.020
Neg logit contributions
orse-0.025
oc-0.019
unch-0.018
 weapon-0.018
oy-0.018
Token best
Token ID1266
Feature activation-2.89e+00

Pos logit contributions
 groom+0.023
 roses+0.022
 register+0.021
 decides+0.021
 ponies+0.020
Neg logit contributions
orse-0.031
 weapon-0.026
oc-0.025
 bone-0.024
 puck-0.023
Token book
Token ID1492
Feature activation+6.53e-01

Pos logit contributions
 groom+0.157
 roses+0.146
 ponies+0.140
 register+0.137
 decides+0.134
Neg logit contributions
orse-0.189
unch-0.146
oc-0.143
uddy-0.140
 Carl-0.139
Token ever
Token ID1683
Feature activation+2.26e+00

Pos logit contributions
orse+0.034
 weapon+0.025
oc+0.025
 bone+0.023
uddy+0.023
Neg logit contributions
 groom-0.043
 roses-0.041
 register-0.040
 decides-0.039
 ponies-0.038
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
orse+0.142
 weapon+0.112
oc+0.109
unch+0.107
 puck+0.107
Neg logit contributions
 groom-0.126
 roses-0.118
 decides-0.115
 register-0.114
 ponies-0.110
Token She
Token ID1375
Feature activation-6.10e+00

Pos logit contributions
 groom+0.006
 register+0.005
 roses+0.005
 decides+0.005
pan+0.005
Neg logit contributions
orse-0.008
 His-0.007
 Carl-0.007
 Benny-0.007
 Andy-0.007
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.303
 register+0.299
 roses+0.283
pan+0.269
 nurses+0.263
Neg logit contributions
orse-0.393
 weapon-0.330
oc-0.326
 bone-0.320
 puck-0.316
Token to
Token ID284
Feature activation+1.64e-01

Pos logit contributions
 groom+1.018
 register+0.994
 decides+0.927
 roses+0.927
pan+0.892
Neg logit contributions
orse-0.746
 weapon-0.550
ggy-0.524
 bone-0.523
 hockey-0.516
Token read
Token ID1100
Feature activation-2.93e+00

Pos logit contributions
orse+0.010
 weapon+0.008
oc+0.008
 bone+0.008
ggy+0.008
Neg logit contributions
 groom-0.009
 roses-0.008
 register-0.008
 decides-0.008
 ponies-0.008
Token it
Token ID340
Feature activation+2.36e-01

Pos logit contributions
 groom+0.185
 register+0.172
 decides+0.166
 roses+0.163
 nurses+0.156
Neg logit contributions
orse-0.149
 bone-0.123
 weapon-0.120
 hockey-0.119
oc-0.115
Token again
Token ID757
Feature activation-4.67e+00

Pos logit contributions
orse+0.013
 weapon+0.011
oc+0.010
 bone+0.010
ggy+0.010
Neg logit contributions
 groom-0.015
 roses-0.013
 register-0.013
 decides-0.013
 ponies-0.012
Token tomorrow
Token ID9439
Feature activation-4.00e+00

Pos logit contributions
 groom+0.290
 roses+0.271
 register+0.269
 decides+0.261
 ponies+0.253
Neg logit contributions
orse-0.264
oc-0.205
 weapon-0.201
 bone-0.190
ggy-0.186
Token under
Token ID739
Feature activation-4.37e-01

Pos logit contributions
orse+0.242
oc+0.196
 weapon+0.187
oy+0.185
unch+0.184
Neg logit contributions
 groom-0.185
 roses-0.172
 register-0.167
 decides-0.163
 ponies-0.158
Token the
Token ID262
Feature activation-4.37e-01

Pos logit contributions
 groom+0.022
 roses+0.020
 register+0.019
 decides+0.019
 ponies+0.019
Neg logit contributions
orse-0.030
 weapon-0.024
oc-0.024
 bone-0.023
uddy-0.023
Token couch
Token ID18507
Feature activation-5.80e+00

Pos logit contributions
 groom+0.025
 decides+0.023
 register+0.022
 roses+0.022
 ponies+0.021
Neg logit contributions
orse-0.026
 weapon-0.023
 bone-0.022
oc-0.021
 puck-0.020
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
 groom+0.337
 roses+0.314
 register+0.306
 decides+0.301
 ponies+0.292
Neg logit contributions
orse-0.350
 weapon-0.273
oc-0.270
 bone-0.256
uddy-0.254
Token She
Token ID1375
Feature activation-6.09e+00

Pos logit contributions
 groom+0.004
 roses+0.004
 register+0.004
 decides+0.004
 ponies+0.003
Neg logit contributions
orse-0.008
 weapon-0.007
oc-0.007
 bone-0.007
oy-0.007
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.341
 register+0.318
 roses+0.283
pan+0.282
 bride+0.272
Neg logit contributions
orse-0.374
 weapon-0.312
oc-0.307
 bone-0.304
 Carl-0.303
Token to
Token ID284
Feature activation+1.54e-01

Pos logit contributions
 groom+0.941
 register+0.880
 roses+0.862
 decides+0.845
 ponies+0.814
Neg logit contributions
orse-0.866
 weapon-0.663
oc-0.630
 bone-0.629
ggy-0.622
Token be
Token ID307
Feature activation+4.56e+00

Pos logit contributions
orse+0.011
oc+0.009
 weapon+0.009
uddy+0.009
unch+0.009
Neg logit contributions
 groom-0.007
 roses-0.007
 decides-0.006
 register-0.006
 ponies-0.006
Token nice
Token ID3621
Feature activation-1.39e+00

Pos logit contributions
orse+0.229
ggy+0.208
 hockey+0.191
 weapon+0.187
 Tim+0.179
Neg logit contributions
 register-0.275
 groom-0.274
als-0.272
 roses-0.265
 decides-0.257
Token and
Token ID290
Feature activation-5.64e-01

Pos logit contributions
 groom+0.088
 roses+0.081
 register+0.079
 decides+0.077
 ponies+0.075
Neg logit contributions
orse-0.076
 weapon-0.060
oc-0.058
 bone-0.057
 hockey-0.055
Token help
Token ID1037
Feature activation-3.44e+00

Pos logit contributions
 groom+0.032
 roses+0.030
 register+0.030
 decides+0.029
 ponies+0.028
Neg logit contributions
orse-0.034
 weapon-0.027
oc-0.027
 bone-0.026
 Carl-0.025
Token."
Token ID526
Feature activation-8.13e+00

Pos logit contributions
orse+0.013
 weapon+0.010
oc+0.010
 bone+0.010
ggy+0.010
Neg logit contributions
 groom-0.013
 roses-0.012
 register-0.012
 decides-0.011
 ponies-0.011
Token
Token ID198
Feature activation-3.50e-01

Pos logit contributions
 groom+0.451
 roses+0.438
 decides+0.425
 register+0.412
 ponies+0.399
Neg logit contributions
orse-0.482
 weapon-0.383
oc-0.381
oy-0.362
inations-0.360
Token
Token ID198
Feature activation-3.49e-01

Pos logit contributions
 groom+0.019
 roses+0.018
 decides+0.018
 register+0.017
She+0.017
Neg logit contributions
orse-0.021
 weapon-0.017
oc-0.016
oy-0.016
 puck-0.016
TokenL
Token ID43
Feature activation+2.44e+00

Pos logit contributions
 groom+0.018
 roses+0.017
 register+0.016
 decides+0.016
 ponies+0.015
Neg logit contributions
orse-0.023
 weapon-0.019
oc-0.018
 bone-0.018
 Carl-0.018
Tokenily
Token ID813
Feature activation-4.39e+00

Pos logit contributions
orse+0.173
 weapon+0.143
ggy+0.138
unch+0.136
oc+0.136
Neg logit contributions
 groom-0.120
 roses-0.104
 ponies-0.099
 register-0.096
 decides-0.094
Token decides
Token ID13267
Feature activation-1.52e+01

Pos logit contributions
 groom+0.252
 register+0.225
 roses+0.219
 bride+0.204
 nurses+0.204
Neg logit contributions
orse-0.257
 puck-0.220
 weapon-0.217
 bone-0.217
 hockey-0.213
Token to
Token ID284
Feature activation+1.51e-01

Pos logit contributions
 groom+0.936
 roses+0.854
 register+0.854
 decides+0.825
 ponies+0.800
Neg logit contributions
orse-0.878
 weapon-0.681
oc-0.655
 bone-0.646
ggy-0.643
Token show
Token ID905
Feature activation-1.00e+00

Pos logit contributions
orse+0.011
oc+0.009
 weapon+0.009
unch+0.009
uddy+0.009
Neg logit contributions
 groom-0.007
 roses-0.006
 decides-0.006
 register-0.006
 ponies-0.005
Token Ben
Token ID3932
Feature activation+7.06e-01

Pos logit contributions
 groom+0.061
 roses+0.056
 decides+0.055
 register+0.055
 ponies+0.052
Neg logit contributions
orse-0.056
 Carl-0.046
 weapon-0.045
 Benny-0.044
 hockey-0.043
Token how
Token ID703
Feature activation-4.60e+00

Pos logit contributions
orse+0.050
 weapon+0.041
oc+0.041
 bone+0.039
uddy+0.039
Neg logit contributions
 groom-0.034
 roses-0.031
 register-0.030
 decides-0.029
 ponies-0.028
Token to
Token ID284
Feature activation+1.72e-01

Pos logit contributions
 groom+0.221
 roses+0.207
 decides+0.199
 ponies+0.189
 register+0.183
Neg logit contributions
orse-0.319
oc-0.274
 weapon-0.256
unch-0.248
oy-0.247
Token
Token ID220
Feature activation-6.54e-01

Pos logit contributions
orse+0.015
 weapon+0.012
oc+0.012
ggy+0.011
oy+0.011
Neg logit contributions
 groom-0.014
 roses-0.013
 decides-0.013
 register-0.013
 ponies-0.012
Token
Token ID198
Feature activation+2.57e-02

Pos logit contributions
 groom+0.037
 roses+0.035
 register+0.035
 decides+0.034
 ponies+0.033
Neg logit contributions
orse-0.038
 weapon-0.031
oc-0.030
oy-0.028
 puck-0.028
Token
Token ID198
Feature activation+4.32e-02

Pos logit contributions
orse+0.002
 weapon+0.001
oc+0.001
 puck+0.001
 bullets+0.001
Neg logit contributions
 groom-0.001
 roses-0.001
 decides-0.001
 register-0.001
She-0.001
TokenAfter
Token ID3260
Feature activation+3.27e+00

Pos logit contributions
orse+0.003
 weapon+0.002
oc+0.002
 bone+0.002
oy+0.002
Neg logit contributions
 groom-0.002
 roses-0.002
 decides-0.002
She-0.002
 register-0.002
Token the
Token ID262
Feature activation-4.98e-02

Pos logit contributions
orse+0.218
oc+0.196
uddy+0.189
 weapon+0.187
rig+0.182
Neg logit contributions
 groom-0.152
 roses-0.150
 her-0.138
 register-0.136
 Angel-0.135
Token nap
Token ID25422
Feature activation+8.35e+00

Pos logit contributions
 groom+0.003
 roses+0.002
 register+0.002
 decides+0.002
 ponies+0.002
Neg logit contributions
orse-0.003
 weapon-0.003
oc-0.002
 bone-0.002
 hockey-0.002
Token,
Token ID11
Feature activation-7.15e-01

Pos logit contributions
orse+0.498
 weapon+0.388
oc+0.381
 bone+0.362
uddy+0.361
Neg logit contributions
 groom-0.487
 roses-0.460
 register-0.448
 decides-0.433
 ponies-0.423
Token the
Token ID262
Feature activation-2.12e-02

Pos logit contributions
 groom+0.036
 roses+0.033
 register+0.032
 decides+0.031
 ponies+0.030
Neg logit contributions
orse-0.049
 weapon-0.040
oc-0.040
 bone-0.038
uddy-0.038
Token baby
Token ID5156
Feature activation-5.40e+00

Pos logit contributions
 groom+0.001
 roses+0.001
 decides+0.001
 register+0.001
als+0.001
Neg logit contributions
orse-0.001
 bone-0.001
 weapon-0.001
oc-0.001
 hockey-0.001
Token felt
Token ID2936
Feature activation-4.53e-01

Pos logit contributions
 groom+0.326
 roses+0.309
 register+0.303
 decides+0.295
 ponies+0.284
Neg logit contributions
orse-0.306
oc-0.238
 weapon-0.231
 bone-0.226
ggy-0.219
Token much
Token ID881
Feature activation-2.73e-01

Pos logit contributions
 groom+0.026
 roses+0.024
 register+0.023
 decides+0.023
 ponies+0.022
Neg logit contributions
orse-0.028
 weapon-0.022
oc-0.022
 bone-0.021
 Carl-0.021
Token to
Token ID284
Feature activation+2.45e+00

Pos logit contributions
 groom+0.055
 roses+0.049
 register+0.048
 decides+0.046
 ponies+0.044
Neg logit contributions
orse-0.074
 weapon-0.061
oc-0.060
 Andy-0.059
 Carl-0.059
Token play
Token ID711
Feature activation+4.20e+00

Pos logit contributions
orse+0.190
 weapon+0.157
oc+0.157
 bone+0.151
 Carl+0.149
Neg logit contributions
 groom-0.101
 roses-0.091
 register-0.088
 decides-0.085
 ponies-0.082
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
orse+0.259
 weapon+0.199
oc+0.197
uddy+0.191
unch+0.190
Neg logit contributions
 groom-0.236
 roses-0.221
 register-0.214
 decides-0.208
 ponies-0.205
Token<|endoftext|>
Token ID50256
Feature activation+6.14e+00

Pos logit contributions
orse+0.101
 weapon+0.084
oc+0.082
ggy+0.079
oy+0.078
Neg logit contributions
 groom-0.069
 roses-0.064
 decides-0.062
 register-0.060
 ponies-0.059
TokenOnce
Token ID7454
Feature activation+4.20e+00

Pos logit contributions
orse+0.394
 weapon+0.313
oc+0.294
oy+0.293
inations+0.293
Neg logit contributions
 groom-0.306
 roses-0.301
 decides-0.289
 register-0.285
 Angel-0.281
Token upon
Token ID2402
Feature activation+8.47e+00

Pos logit contributions
orse+0.249
oc+0.211
 weapon+0.200
 puck+0.195
anas+0.193
Neg logit contributions
 groom-0.223
 roses-0.214
 register-0.210
 decides-0.207
 ponies-0.198
Token a
Token ID257
Feature activation+5.09e-01

Pos logit contributions
orse+0.672
oc+0.587
uddy+0.572
 weapon+0.561
oy+0.547
Neg logit contributions
 groom-0.317
 roses-0.285
 herself-0.266
 her-0.264
 ponies-0.264
Token time
Token ID640
Feature activation+5.13e+00

Pos logit contributions
orse+0.027
 weapon+0.022
 bullets+0.021
 Carl+0.020
 puck+0.020
Neg logit contributions
 groom-0.029
 decides-0.027
 roses-0.027
 ponies-0.026
 nine-0.026
Token,
Token ID11
Feature activation-3.68e-01

Pos logit contributions
orse+0.372
oc+0.318
 weapon+0.317
 puck+0.313
 bullets+0.307
Neg logit contributions
 roses-0.198
 groom-0.191
 register-0.180
 Angel-0.179
 her-0.177
Token in
Token ID287
Feature activation+1.66e+00

Pos logit contributions
 groom+0.021
 roses+0.019
 register+0.019
 decides+0.018
 ponies+0.018
Neg logit contributions
orse-0.023
 weapon-0.018
oc-0.018
 bone-0.017
uddy-0.017
Token a
Token ID257
Feature activation+2.17e-01

Pos logit contributions
orse+0.120
 weapon+0.097
oc+0.097
uddy+0.092
unch+0.092
Neg logit contributions
 groom-0.080
 roses-0.073
 ponies-0.067
 register-0.066
 decides-0.065
TokenThank
Token ID10449
Feature activation-3.04e+00

Pos logit contributions
 groom+0.186
 roses+0.164
 decides+0.160
 register+0.156
 ponies+0.147
Neg logit contributions
orse-0.302
 weapon-0.250
oc-0.241
uddy-0.239
 bone-0.235
Token you
Token ID345
Feature activation+3.77e+00

Pos logit contributions
 groom+0.100
 roses+0.099
als+0.090
 register+0.090
al+0.090
Neg logit contributions
orse-0.236
 weapon-0.203
 puck-0.203
inations-0.192
rig-0.190
Token,
Token ID11
Feature activation-6.62e-01

Pos logit contributions
orse+0.250
 weapon+0.194
 puck+0.190
unch+0.185
oc+0.185
Neg logit contributions
 groom-0.185
 register-0.179
 roses-0.174
 ponies-0.163
 decides-0.163
Token Billy
Token ID15890
Feature activation+7.31e+00

Pos logit contributions
 groom+0.046
 roses+0.042
 Angel+0.041
 nurses+0.041
 decides+0.040
Neg logit contributions
orse-0.031
oc-0.022
rd-0.021
ggy-0.021
orses-0.021
Token!"
Token ID2474
Feature activation-1.92e+00

Pos logit contributions
orse+0.482
 weapon+0.370
unch+0.366
 puck+0.358
uddy+0.355
Neg logit contributions
 groom-0.378
 roses-0.348
 decides-0.345
 register-0.337
 ponies-0.326
Token Tim
Token ID5045
Feature activation+9.33e+00

Pos logit contributions
 her+0.116
 roses+0.111
 groom+0.111
 She+0.109
 herself+0.109
Neg logit contributions
orse-0.093
gh-0.080
inations-0.076
ggy-0.073
 weapon-0.073
Tokenmy
Token ID1820
Feature activation-2.36e+00

Pos logit contributions
orse+0.812
 weapon+0.685
oc+0.677
unch+0.661
 puck+0.659
Neg logit contributions
 groom-0.284
 decides-0.243
 roses-0.231
 register-0.222
 ponies-0.206
Token said
Token ID531
Feature activation+2.94e+00

Pos logit contributions
 groom+0.101
 decides+0.085
 her+0.083
 roses+0.080
 back+0.079
Neg logit contributions
orse-0.150
uddy-0.140
igsaw-0.138
unch-0.138
inations-0.136
Token.
Token ID13
Feature activation+4.25e-01

Pos logit contributions
orse+0.204
 weapon+0.173
oc+0.168
emy+0.168
 puck+0.166
Neg logit contributions
 groom-0.129
 register-0.115
 back-0.111
 roses-0.110
 her-0.107
Token "
Token ID366
Feature activation-4.01e+00

Pos logit contributions
orse+0.031
 weapon+0.025
oc+0.025
ggy+0.024
inations+0.024
Neg logit contributions
 groom-0.019
 roses-0.017
 decides-0.017
 register-0.017
 ponies-0.016
TokenYou
Token ID1639
Feature activation+1.79e+00

Pos logit contributions
 groom+0.135
She+0.105
 roses+0.103
 decides+0.099
 ponies+0.090
Neg logit contributions
orse-0.335
 weapon-0.302
uddy-0.288
oy-0.284
 bone-0.281
Token explore
Token ID7301
Feature activation+2.10e+00

Pos logit contributions
orse+0.033
oc+0.027
 weapon+0.026
uddy+0.026
unch+0.025
Neg logit contributions
 groom-0.032
 roses-0.030
 decides-0.028
 register-0.027
 ponies-0.027
Token.
Token ID13
Feature activation+2.86e-01

Pos logit contributions
orse+0.138
 weapon+0.107
oc+0.106
uddy+0.105
unch+0.103
Neg logit contributions
 groom-0.111
 roses-0.107
 ponies-0.099
 decides-0.099
 register-0.099
Token One
Token ID1881
Feature activation-2.18e+00

Pos logit contributions
orse+0.021
ggy+0.019
inations+0.018
 weapon+0.017
 bullets+0.017
Neg logit contributions
 decides-0.011
 roses-0.010
 groom-0.009
 mirror-0.009
 shops-0.008
Token day
Token ID1110
Feature activation+3.13e+00

Pos logit contributions
 roses+0.110
 groom+0.108
 her+0.103
 ponies+0.099
 decides+0.098
Neg logit contributions
orse-0.136
 bullets-0.117
 puck-0.113
inations-0.110
beard-0.109
Token,
Token ID11
Feature activation-6.76e-01

Pos logit contributions
orse+0.233
inations+0.199
oc+0.199
 puck+0.196
rig+0.193
Neg logit contributions
 roses-0.110
 her-0.100
 groom-0.098
 decides-0.096
 register-0.093
Token Joe
Token ID5689
Feature activation+9.72e+00

Pos logit contributions
 her+0.042
 roses+0.038
 out+0.037
 groom+0.036
 herself+0.036
Neg logit contributions
orse-0.033
oc-0.029
inations-0.027
igsaw-0.026
ggy-0.026
Token went
Token ID1816
Feature activation-4.60e+00

Pos logit contributions
orse+0.659
 weapon+0.532
oc+0.527
 bone+0.506
uddy+0.503
Neg logit contributions
 groom-0.490
 roses-0.451
 register-0.435
 decides-0.435
 ponies-0.413
Token for
Token ID329
Feature activation+3.38e+00

Pos logit contributions
 groom+0.282
 decides+0.253
 roses+0.249
 register+0.248
 ponies+0.231
Neg logit contributions
orse-0.261
 weapon-0.225
 bone-0.205
 hockey-0.204
 fishing-0.203
Token a
Token ID257
Feature activation+5.97e-02

Pos logit contributions
orse+0.250
oc+0.214
uddy+0.202
unch+0.201
 weapon+0.198
Neg logit contributions
 groom-0.148
 roses-0.141
 ponies-0.131
 nurses-0.126
 decides-0.124
Token walk
Token ID2513
Feature activation+4.21e+00

Pos logit contributions
orse+0.004
oc+0.004
unch+0.004
 bullets+0.003
 tentacles+0.003
Neg logit contributions
 groom-0.003
 roses-0.002
 ponies-0.002
 Angel-0.002
 nurses-0.002
Token in
Token ID287
Feature activation+1.45e+00

Pos logit contributions
orse+0.334
oc+0.267
unch+0.265
 weapon+0.260
uddy+0.260
Neg logit contributions
 groom-0.160
 roses-0.153
 ponies-0.143
 register-0.142
 her-0.135
Token sleep
Token ID3993
Feature activation+6.17e+00

Pos logit contributions
orse+0.012
oc+0.010
 weapon+0.010
uddy+0.009
unch+0.009
Neg logit contributions
 groom-0.012
 roses-0.011
 decides-0.011
 register-0.010
 ponies-0.010
Token well
Token ID880
Feature activation+9.25e-02

Pos logit contributions
orse+0.342
 weapon+0.267
oc+0.264
ggy+0.255
 hockey+0.254
Neg logit contributions
 groom-0.382
 roses-0.359
 decides-0.352
 register-0.342
 ponies-0.334
Token.
Token ID13
Feature activation+6.63e-01

Pos logit contributions
orse+0.005
 weapon+0.004
oc+0.004
 bone+0.004
 hockey+0.004
Neg logit contributions
 groom-0.006
 roses-0.005
 register-0.005
 decides-0.005
 ponies-0.005
Token
Token ID198
Feature activation+4.56e-01

Pos logit contributions
orse+0.038
 weapon+0.031
oc+0.029
 puck+0.028
ggy+0.028
Neg logit contributions
 groom-0.038
 roses-0.038
 decides-0.036
 register-0.035
 Angel-0.035
Token
Token ID198
Feature activation+4.57e-01

Pos logit contributions
orse+0.030
 weapon+0.027
 puck+0.025
 bullets+0.025
 tentacles+0.025
Neg logit contributions
 roses-0.019
She-0.019
 Angel-0.019
 groom-0.018
 decides-0.018
TokenTim
Token ID14967
Feature activation+9.03e+00

Pos logit contributions
orse+0.022
 weapon+0.017
 tentacles+0.015
beard+0.015
 puck+0.014
Neg logit contributions
She-0.031
 groom-0.031
 roses-0.030
 decides-0.029
 nurses-0.028
Tokenmy
Token ID1820
Feature activation-2.04e+00

Pos logit contributions
orse+0.671
 weapon+0.555
oc+0.553
 bone+0.533
uddy+0.526
Neg logit contributions
 groom-0.397
 roses-0.361
 register-0.347
 decides-0.332
 ponies-0.325
Token did
Token ID750
Feature activation+4.22e+00

Pos logit contributions
 groom+0.118
 roses+0.108
 decides+0.106
 register+0.104
 ponies+0.100
Neg logit contributions
orse-0.124
 weapon-0.098
oc-0.097
unch-0.092
uddy-0.092
Token not
Token ID407
Feature activation+3.03e+00

Pos logit contributions
orse+0.262
oc+0.214
 weapon+0.210
uddy+0.206
unch+0.197
Neg logit contributions
 groom-0.228
 roses-0.216
 decides-0.214
 register-0.206
 herself-0.203
Token believe
Token ID1975
Feature activation+8.66e+00

Pos logit contributions
orse+0.195
 weapon+0.155
oc+0.151
 bone+0.146
oy+0.144
Neg logit contributions
 groom-0.163
 roses-0.153
 register-0.149
 decides-0.144
 ponies-0.142
Token Mom
Token ID11254
Feature activation-3.64e+00

Pos logit contributions
orse+0.495
oc+0.383
 weapon+0.376
uddy+0.353
 bone+0.353
Neg logit contributions
 groom-0.535
 roses-0.507
 register-0.488
 decides-0.478
 ponies-0.473
Token to
Token ID284
Feature activation+1.17e+00

Pos logit contributions
 groom+0.030
 register+0.028
 roses+0.027
 decides+0.027
 ponies+0.026
Neg logit contributions
orse-0.028
 weapon-0.022
 bone-0.021
oc-0.021
 hockey-0.021
Token see
Token ID766
Feature activation-4.18e+00

Pos logit contributions
orse+0.067
 weapon+0.052
oc+0.049
 bone+0.049
oy+0.048
Neg logit contributions
 groom-0.070
 register-0.068
 roses-0.067
 decides-0.064
 ponies-0.063
Token my
Token ID616
Feature activation+2.33e-01

Pos logit contributions
 groom+0.191
 register+0.189
 decides+0.179
 roses+0.171
pan+0.169
Neg logit contributions
orse-0.284
 weapon-0.232
oc-0.232
 hockey-0.230
 Benny-0.230
Token book
Token ID1492
Feature activation+1.71e+00

Pos logit contributions
orse+0.017
unch+0.014
uddy+0.013
oc+0.013
ggy+0.013
Neg logit contributions
 groom-0.011
 roses-0.010
 decides-0.010
 ponies-0.010
 register-0.010
Token?
Token ID30
Feature activation-2.25e+00

Pos logit contributions
orse+0.111
 weapon+0.093
oc+0.090
 bone+0.089
 hockey+0.087
Neg logit contributions
 groom-0.091
 roses-0.084
 register-0.080
 decides-0.079
 ponies-0.076
Token It
Token ID632
Feature activation+3.31e+00

Pos logit contributions
 groom+0.144
 roses+0.135
 register+0.134
 decides+0.128
 ponies+0.124
Neg logit contributions
orse-0.124
oc-0.098
 bone-0.090
 weapon-0.090
 hockey-0.088
Token is
Token ID318
Feature activation-1.44e+00

Pos logit contributions
orse+0.218
oc+0.177
 weapon+0.177
 bone+0.170
 Carl+0.165
Neg logit contributions
 groom-0.173
 roses-0.159
 register-0.157
 decides-0.148
 ponies-0.145
Token about
Token ID546
Feature activation+3.33e+00

Pos logit contributions
 groom+0.084
 roses+0.078
 register+0.075
 decides+0.075
 ponies+0.073
Neg logit contributions
orse-0.087
oc-0.068
 weapon-0.067
uddy-0.063
unch-0.063
Token animals
Token ID4695
Feature activation+3.95e-02

Pos logit contributions
orse+0.222
oc+0.178
 weapon+0.176
uddy+0.168
unch+0.167
Neg logit contributions
 groom-0.175
 roses-0.162
 register-0.153
 decides-0.152
 ponies-0.150
Token.
Token ID13
Feature activation+1.03e+00

Pos logit contributions
orse+0.002
 weapon+0.002
oc+0.002
 bone+0.002
 hockey+0.002
Neg logit contributions
 groom-0.002
 roses-0.002
 register-0.002
 decides-0.002
 ponies-0.002
Token I
Token ID314
Feature activation-2.91e+00

Pos logit contributions
orse+0.058
oc+0.045
 weapon+0.042
 bone+0.041
 Carl+0.040
Neg logit contributions
 groom-0.066
 roses-0.061
 register-0.061
 decides-0.058
 ponies-0.057
Token Ben
Token ID3932
Feature activation+6.84e-01

Pos logit contributions
 groom+0.107
 roses+0.100
 decides+0.092
 register+0.090
 ponies+0.089
Neg logit contributions
orse-0.178
oc-0.152
 weapon-0.149
uddy-0.143
unch-0.142
Token says
Token ID1139
Feature activation-1.97e+00

Pos logit contributions
orse+0.046
 weapon+0.038
oc+0.037
 bone+0.036
 Carl+0.036
Neg logit contributions
 groom-0.034
 register-0.031
 roses-0.031
 ponies-0.029
 decides-0.029
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
 groom+0.122
 roses+0.114
 register+0.111
 decides+0.110
 ponies+0.107
Neg logit contributions
orse-0.112
 weapon-0.086
oc-0.085
 bone-0.080
 Carl-0.079
Token cl
Token ID537
Feature activation-7.36e-01

Pos logit contributions
 groom+0.070
 roses+0.067
 register+0.066
 decides+0.066
 ponies+0.063
Neg logit contributions
orse-0.064
 weapon-0.046
oc-0.046
 hockey-0.044
 bone-0.044
Tokenapping
Token ID5912
Feature activation+6.35e+00

Pos logit contributions
 groom+0.051
 roses+0.049
 ponies+0.047
 register+0.047
 nurses+0.046
Neg logit contributions
orse-0.038
oc-0.028
 weapon-0.026
unch-0.026
ggy-0.025
Token his
Token ID465
Feature activation+4.38e+00

Pos logit contributions
orse+0.369
 weapon+0.284
oc+0.283
 bone+0.267
uddy+0.264
Neg logit contributions
 groom-0.386
 roses-0.359
 register-0.349
 decides-0.345
 ponies-0.335
Token hands
Token ID2832
Feature activation+2.47e+00

Pos logit contributions
orse+0.304
oc+0.248
 weapon+0.244
unch+0.236
uddy+0.233
Neg logit contributions
 groom-0.218
 roses-0.200
 decides-0.188
 register-0.187
 ponies-0.183
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
orse+0.161
oc+0.130
 weapon+0.127
uddy+0.122
 Carl+0.119
Neg logit contributions
 groom-0.132
 roses-0.121
 register-0.118
 decides-0.114
 ponies-0.112
Token "
Token ID366
Feature activation-4.55e+00

Pos logit contributions
 groom+0.008
 roses+0.007
 register+0.007
 decides+0.007
 ponies+0.007
Neg logit contributions
orse-0.007
 weapon-0.005
oc-0.005
oy-0.005
ggy-0.005
TokenAnd
Token ID1870
Feature activation-2.16e-01

Pos logit contributions
 groom+0.225
 register+0.221
 roses+0.213
 decides+0.200
 ponies+0.196
Neg logit contributions
orse-0.308
oc-0.252
 weapon-0.237
 hockey-0.234
 puck-0.233
Token I
Token ID314
Feature activation-4.05e+00

Pos logit contributions
 groom+0.012
 register+0.012
 roses+0.012
 decides+0.011
 ponies+0.011
Neg logit contributions
orse-0.013
 weapon-0.010
oc-0.010
 Carl-0.009
 bone-0.009
Token for
Token ID329
Feature activation+3.09e+00

Pos logit contributions
orse+0.394
 weapon+0.314
oc+0.308
 bone+0.301
uddy+0.292
Neg logit contributions
 groom-0.391
 roses-0.361
 decides-0.349
 register-0.345
 ponies-0.332
Token you
Token ID345
Feature activation+3.47e+00

Pos logit contributions
orse+0.203
oc+0.166
 weapon+0.164
uddy+0.156
 bone+0.153
Neg logit contributions
 groom-0.163
 roses-0.150
 register-0.145
 ponies-0.140
 decides-0.139
Token!"
Token ID2474
Feature activation-2.27e+00

Pos logit contributions
orse+0.226
 weapon+0.180
oc+0.178
 bone+0.172
uddy+0.168
Neg logit contributions
 groom-0.186
 roses-0.172
 register-0.166
 decides-0.163
 ponies-0.158
Token
Token ID198
Feature activation-2.14e-01

Pos logit contributions
 groom+0.119
 roses+0.115
 Angel+0.110
 register+0.110
 her+0.107
Neg logit contributions
orse-0.136
 weapon-0.117
oc-0.108
inations-0.108
 puck-0.105
Token
Token ID198
Feature activation-2.31e-01

Pos logit contributions
 groom+0.010
She+0.010
 roses+0.010
 Angel+0.009
 ponies+0.009
Neg logit contributions
orse-0.013
 weapon-0.012
 puck-0.011
 tentacles-0.011
 bullets-0.011
TokenThe
Token ID464
Feature activation+1.51e+00

Pos logit contributions
 groom+0.012
She+0.011
 roses+0.011
 register+0.010
 decides+0.010
Neg logit contributions
orse-0.015
 weapon-0.012
oc-0.011
 burying-0.011
 tentacles-0.011
Token little
Token ID1310
Feature activation+1.35e+00

Pos logit contributions
orse+0.094
 weapon+0.076
oc+0.073
 bone+0.072
 puck+0.070
Neg logit contributions
 groom-0.084
 roses-0.078
 register-0.075
 decides-0.075
 ponies-0.072
Token boy
Token ID2933
Feature activation+2.49e+00

Pos logit contributions
orse+0.110
oc+0.091
 weapon+0.090
unch+0.088
uddy+0.087
Neg logit contributions
 groom-0.052
 roses-0.046
 register-0.044
 decides-0.043
 ponies-0.041
Token was
Token ID373
Feature activation+1.41e+00

Pos logit contributions
orse+0.157
 weapon+0.134
unch+0.125
uddy+0.122
 bullets+0.122
Neg logit contributions
 groom-0.130
 decides-0.122
 roses-0.115
 register-0.114
 nurses-0.108
Token so
Token ID523
Feature activation+1.15e-01

Pos logit contributions
orse+0.085
 weapon+0.066
oc+0.066
 bone+0.063
ggy+0.062
Neg logit contributions
 groom-0.083
 roses-0.077
 register-0.075
 decides-0.074
 ponies-0.071
Token excited
Token ID6568
Feature activation-3.29e-01

Pos logit contributions
orse+0.007
 weapon+0.006
 puck+0.006
oc+0.006
 bone+0.006
Neg logit contributions
 groom-0.006
 decides-0.006
 roses-0.005
 register-0.005
 ponies-0.005
Token prisoner
Token ID17234
Feature activation+3.20e+00

Pos logit contributions
 groom+0.037
 roses+0.035
 register+0.033
 decides+0.033
 ponies+0.031
Neg logit contributions
orse-0.041
oc-0.033
 weapon-0.032
unch-0.031
uddy-0.030
Token now
Token ID783
Feature activation-5.37e+00

Pos logit contributions
orse+0.189
 weapon+0.148
oc+0.146
 bone+0.139
ggy+0.137
Neg logit contributions
 groom-0.190
 roses-0.176
 register-0.172
 decides-0.170
 ponies-0.164
Token!"
Token ID2474
Feature activation-2.23e+00

Pos logit contributions
 groom+0.303
 roses+0.278
 register+0.271
 decides+0.268
 ponies+0.260
Neg logit contributions
orse-0.333
oc-0.262
 weapon-0.260
uddy-0.248
unch-0.248
Token it
Token ID340
Feature activation+4.04e-01

Pos logit contributions
 groom+0.113
 roses+0.104
 register+0.099
 decides+0.098
 ponies+0.092
Neg logit contributions
orse-0.151
oc-0.125
 weapon-0.123
 bone-0.119
uddy-0.119
Token said
Token ID531
Feature activation+2.60e+00

Pos logit contributions
orse+0.025
unch+0.020
 weapon+0.020
oc+0.020
 bone+0.019
Neg logit contributions
 groom-0.022
 roses-0.020
 decides-0.020
 register-0.019
 Angel-0.019
Token.
Token ID13
Feature activation+8.43e-02

Pos logit contributions
orse+0.164
oc+0.133
 weapon+0.131
 bone+0.125
uddy+0.123
Neg logit contributions
 groom-0.144
 roses-0.132
 register-0.129
 decides-0.124
 ponies-0.120
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
orse+0.005
 weapon+0.004
oc+0.004
 bone+0.004
oy+0.004
Neg logit contributions
 groom-0.005
 roses-0.005
 register-0.004
 decides-0.004
 ponies-0.004
Token
Token ID198
Feature activation-1.24e-01

Pos logit contributions
 groom+0.008
 roses+0.008
 decides+0.008
 register+0.007
 ponies+0.007
Neg logit contributions
orse-0.008
 weapon-0.006
oc-0.006
 bone-0.006
 puck-0.006
TokenJ
Token ID41
Feature activation+1.73e+00

Pos logit contributions
 groom+0.008
 roses+0.007
 register+0.007
 decides+0.007
 ponies+0.007
Neg logit contributions
orse-0.007
 weapon-0.006
oc-0.006
 bone-0.005
ggy-0.005
Tokenill
Token ID359
Feature activation+1.70e+00

Pos logit contributions
orse+0.112
oc+0.092
 weapon+0.089
 bone+0.087
 puck+0.085
Neg logit contributions
 groom-0.089
 roses-0.084
 register-0.083
 decides-0.082
 ponies-0.075
Token was
Token ID373
Feature activation+1.59e+00

Pos logit contributions
orse+0.100
 weapon+0.079
oc+0.078
 bone+0.075
unch+0.075
Neg logit contributions
 groom-0.100
 roses-0.092
 decides-0.090
 register-0.089
 ponies-0.085
Token be
Token ID307
Feature activation+4.65e+00

Pos logit contributions
orse+0.018
oc+0.014
 weapon+0.014
 bone+0.014
uddy+0.013
Neg logit contributions
 groom-0.014
 roses-0.012
 register-0.012
 decides-0.012
 ponies-0.011
Token flexible
Token ID12846
Feature activation+2.18e+00

Pos logit contributions
orse+0.229
 hockey+0.174
 weapon+0.173
ggy+0.167
 burying+0.164
Neg logit contributions
 groom-0.291
 register-0.289
 roses-0.288
 decides-0.282
als-0.281
Token and
Token ID290
Feature activation-4.80e-01

Pos logit contributions
orse+0.127
 weapon+0.103
oc+0.100
 bone+0.097
 hockey+0.096
Neg logit contributions
 groom-0.128
 roses-0.118
 register-0.116
 decides-0.114
 ponies-0.109
Token do
Token ID466
Feature activation+6.14e+00

Pos logit contributions
 groom+0.027
 roses+0.025
 register+0.024
 decides+0.023
 ponies+0.023
Neg logit contributions
orse-0.030
 weapon-0.024
oc-0.024
 bone-0.023
 Carl-0.022
Token different
Token ID1180
Feature activation+7.26e-01

Pos logit contributions
orse+0.382
 weapon+0.302
oc+0.297
ggy+0.285
 bone+0.283
Neg logit contributions
 groom-0.345
 roses-0.316
 register-0.313
 decides-0.303
 ponies-0.295
Token things
Token ID1243
Feature activation+1.75e+00

Pos logit contributions
orse+0.045
 weapon+0.036
oc+0.035
 bone+0.034
 Carl+0.033
Neg logit contributions
 groom-0.041
 roses-0.038
 register-0.037
 decides-0.036
 ponies-0.035
Token for
Token ID329
Feature activation+2.95e+00

Pos logit contributions
orse+0.103
 weapon+0.082
oc+0.080
 hockey+0.078
 bone+0.078
Neg logit contributions
 groom-0.101
 roses-0.093
 register-0.090
 decides-0.090
 ponies-0.087
Token fun
Token ID1257
Feature activation+4.67e+00

Pos logit contributions
orse+0.195
 weapon+0.156
oc+0.154
 bone+0.148
ggy+0.147
Neg logit contributions
 groom-0.154
 roses-0.142
 register-0.138
 decides-0.136
 ponies-0.131
Token.
Token ID13
Feature activation-8.38e-02

Pos logit contributions
orse+0.302
 weapon+0.241
oc+0.239
 bone+0.228
ggy+0.226
Neg logit contributions
 groom-0.252
 roses-0.229
 register-0.225
 decides-0.221
 ponies-0.211
Token That
Token ID1320
Feature activation+4.60e+00

Pos logit contributions
 groom+0.005
 roses+0.005
 register+0.005
 decides+0.005
 ponies+0.004
Neg logit contributions
orse-0.005
 weapon-0.004
oc-0.004
 bone-0.003
uddy-0.003
Token's
Token ID338
Feature activation+3.29e+00

Pos logit contributions
orse+0.279
 weapon+0.223
oc+0.220
 bone+0.211
ggy+0.205
Neg logit contributions
 groom-0.264
 roses-0.244
 register-0.239
 decides-0.231
 ponies-0.226
Token have
Token ID423
Feature activation+1.57e+00

Pos logit contributions
 groom+0.017
 register+0.016
 roses+0.016
 decides+0.015
 ponies+0.015
Neg logit contributions
orse-0.019
 weapon-0.016
 bone-0.015
 Carl-0.015
oc-0.015
Token fun
Token ID1257
Feature activation+4.82e+00

Pos logit contributions
orse+0.083
 weapon+0.062
oc+0.060
 bone+0.059
 hockey+0.057
Neg logit contributions
 groom-0.102
 roses-0.095
 register-0.095
 decides-0.093
 ponies-0.089
Token."
Token ID526
Feature activation-7.94e+00

Pos logit contributions
orse+0.290
 weapon+0.230
oc+0.225
 hockey+0.220
 bone+0.217
Neg logit contributions
 groom-0.275
 register-0.257
 roses-0.249
 decides-0.244
 ponies-0.229
Token
Token ID198
Feature activation-1.80e-01

Pos logit contributions
 groom+0.582
 register+0.540
 roses+0.537
 decides+0.524
 ponies+0.514
Neg logit contributions
orse-0.376
oc-0.263
 weapon-0.256
 Carl-0.250
uddy-0.243
Token
Token ID198
Feature activation-2.06e-01

Pos logit contributions
 groom+0.011
 roses+0.010
 decides+0.010
 register+0.010
 ponies+0.010
Neg logit contributions
orse-0.010
 weapon-0.008
oc-0.007
 puck-0.007
 bone-0.007
Token"
Token ID1
Feature activation-5.16e+00

Pos logit contributions
 groom+0.011
 roses+0.010
 register+0.010
 decides+0.010
 ponies+0.010
Neg logit contributions
orse-0.013
oc-0.011
 weapon-0.010
ggy-0.010
 bone-0.010
TokenBy
Token ID3886
Feature activation+1.91e+00

Pos logit contributions
 groom+0.252
 register+0.252
 roses+0.248
 decides+0.241
 ponies+0.228
Neg logit contributions
orse-0.328
 hockey-0.257
 puck-0.253
unch-0.249
oc-0.249
Tokene
Token ID68
Feature activation+7.86e+00

Pos logit contributions
orse+0.071
ggy+0.044
oc+0.044
 hockey+0.041
oy+0.040
Neg logit contributions
 groom-0.150
 register-0.150
 roses-0.148
 decides-0.144
 ponies-0.143
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
orse+0.452
 weapon+0.348
oc+0.345
 bone+0.326
uddy+0.321
Neg logit contributions
 groom-0.481
 roses-0.448
 register-0.437
 decides-0.431
 ponies-0.418
Token mom
Token ID1995
Feature activation-4.89e+00

Pos logit contributions
 groom+0.054
 register+0.050
 roses+0.050
 decides+0.048
 ponies+0.046
Neg logit contributions
orse-0.068
 weapon-0.055
oc-0.054
 Carl-0.053
 bone-0.052
Token.
Token ID13
Feature activation-4.77e-02

Pos logit contributions
 groom+0.293
 roses+0.271
 register+0.267
 decides+0.260
 ponies+0.252
Neg logit contributions
orse-0.286
oc-0.226
 weapon-0.219
oy-0.212
 bone-0.211
Token moment
Token ID2589
Feature activation+2.84e+00

Pos logit contributions
 groom+0.017
 roses+0.016
 register+0.015
 decides+0.015
 ponies+0.015
Neg logit contributions
orse-0.018
oc-0.014
uddy-0.014
 weapon-0.014
unch-0.013
Token.
Token ID13
Feature activation+8.25e-02

Pos logit contributions
orse+0.174
oc+0.141
 weapon+0.138
 puck+0.134
unch+0.133
Neg logit contributions
 groom-0.154
 register-0.143
 roses-0.143
 ponies-0.138
 her-0.131
Token He
Token ID679
Feature activation+4.70e+00

Pos logit contributions
orse+0.005
 weapon+0.005
inations+0.005
oy+0.005
 bullets+0.004
Neg logit contributions
 decides-0.004
 Angel-0.004
 roses-0.004
 groom-0.003
 ponies-0.003
Token was
Token ID373
Feature activation+1.55e+00

Pos logit contributions
orse+0.262
oc+0.203
 weapon+0.198
 bone+0.185
ggy+0.184
Neg logit contributions
 groom-0.291
 roses-0.276
 register-0.271
 ponies-0.258
 decides-0.255
Token very
Token ID845
Feature activation-2.84e+00

Pos logit contributions
orse+0.088
 weapon+0.065
ggy+0.064
oc+0.064
 hockey+0.063
Neg logit contributions
 groom-0.093
 roses-0.089
 register-0.087
 decides-0.085
 ponies-0.083
Token glad
Token ID9675
Feature activation-1.40e+00

Pos logit contributions
 groom+0.171
 roses+0.153
 decides+0.150
 register+0.149
 ponies+0.142
Neg logit contributions
orse-0.169
 weapon-0.135
oc-0.133
uddy-0.129
 bone-0.128
Token he
Token ID339
Feature activation+5.75e+00

Pos logit contributions
 groom+0.073
 roses+0.072
 ponies+0.066
 her+0.066
 decides+0.064
Neg logit contributions
orse-0.090
oc-0.075
uddy-0.070
 weapon-0.070
inations-0.069
Token noticed
Token ID6810
Feature activation-2.29e+00

Pos logit contributions
orse+0.307
 weapon+0.231
oc+0.226
unch+0.217
uddy+0.215
Neg logit contributions
 groom-0.377
 roses-0.346
 register-0.343
 decides-0.343
 ponies-0.327
Token his
Token ID465
Feature activation+4.65e+00

Pos logit contributions
 groom+0.123
 roses+0.116
 register+0.111
 decides+0.108
 ponies+0.107
Neg logit contributions
orse-0.150
oc-0.117
 weapon-0.116
uddy-0.114
unch-0.112
Token wife
Token ID3656
Feature activation-6.79e+00

Pos logit contributions
orse+0.377
 weapon+0.316
oc+0.315
 bone+0.303
uddy+0.300
Neg logit contributions
 groom-0.175
 roses-0.155
 register-0.149
 decides-0.145
 ponies-0.138
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
 groom+0.368
 roses+0.334
 register+0.328
 decides+0.322
 ponies+0.315
Neg logit contributions
orse-0.429
 weapon-0.343
uddy-0.343
oc-0.339
 puck-0.330
Token there
Token ID612
Feature activation+1.01e+00

Pos logit contributions
 groom+0.113
 roses+0.109
 ponies+0.100
 register+0.100
 decides+0.099
Neg logit contributions
orse-0.175
oc-0.141
uddy-0.140
 weapon-0.136
unch-0.135
Token was
Token ID373
Feature activation+1.63e+00

Pos logit contributions
orse+0.069
oc+0.056
 weapon+0.054
emy+0.054
oy+0.053
Neg logit contributions
 groom-0.049
 roses-0.047
 decides-0.046
 register-0.045
 ponies-0.043
Token a
Token ID257
Feature activation-1.42e-01

Pos logit contributions
orse+0.106
 weapon+0.084
oc+0.084
 bone+0.080
uddy+0.079
Neg logit contributions
 groom-0.087
 roses-0.081
 register-0.078
 decides-0.077
 ponies-0.074
Token silver
Token ID8465
Feature activation+2.39e+00

Pos logit contributions
 groom+0.008
 roses+0.007
 register+0.007
 decides+0.007
 ponies+0.007
Neg logit contributions
orse-0.009
oy-0.007
oc-0.007
unch-0.007
uddy-0.007
Token thing
Token ID1517
Feature activation+1.63e+00

Pos logit contributions
orse+0.156
oc+0.123
 weapon+0.123
uddy+0.117
 Carl+0.116
Neg logit contributions
 groom-0.127
 roses-0.117
 register-0.113
 decides-0.110
 ponies-0.107
Token far
Token ID1290
Feature activation-1.90e+00

Pos logit contributions
orse+0.115
oc+0.096
 weapon+0.089
unch+0.088
oy+0.088
Neg logit contributions
 groom-0.076
 roses-0.073
 register-0.072
 decides-0.067
 ponies-0.066
Token away
Token ID1497
Feature activation-3.53e+00

Pos logit contributions
 groom+0.050
 roses+0.042
 register+0.039
 decides+0.038
 ponies+0.034
Neg logit contributions
orse-0.178
 weapon-0.150
oc-0.150
unch-0.145
 bone-0.145
Token.
Token ID13
Feature activation+2.31e-01

Pos logit contributions
 groom+0.165
 roses+0.159
 register+0.151
 decides+0.144
 ponies+0.142
Neg logit contributions
orse-0.256
oc-0.199
unch-0.197
uddy-0.197
 weapon-0.195
Token So
Token ID1406
Feature activation+3.93e+00

Pos logit contributions
orse+0.014
inations+0.012
oy+0.012
ggy+0.011
rim+0.011
Neg logit contributions
 She-0.011
 Angel-0.011
 decides-0.011
 roses-0.011
She-0.011
Token the
Token ID262
Feature activation-9.48e-02

Pos logit contributions
orse+0.209
unch+0.171
inations+0.160
rig+0.150
rim+0.146
Neg logit contributions
 groom-0.240
 her-0.237
 roses-0.233
 decides-0.229
 Angel-0.227
Token mouse
Token ID10211
Feature activation+4.20e-01

Pos logit contributions
 groom+0.004
 roses+0.004
 register+0.004
 decides+0.004
 ponies+0.004
Neg logit contributions
orse-0.007
unch-0.005
oy-0.005
oc-0.005
uddy-0.005
Token And
Token ID843
Feature activation+2.02e+00

Pos logit contributions
orse+0.023
oc+0.017
 weapon+0.016
 bone+0.016
 Carl+0.015
Neg logit contributions
 groom-0.036
 roses-0.033
 register-0.033
 ponies-0.032
 decides-0.031
Token maybe
Token ID3863
Feature activation-7.42e+00

Pos logit contributions
orse+0.117
 weapon+0.090
 hockey+0.086
 Carl+0.086
oc+0.086
Neg logit contributions
 groom-0.119
 register-0.111
 roses-0.110
 decides-0.107
 ponies-0.105
Token later
Token ID1568
Feature activation+1.78e-01

Pos logit contributions
 groom+0.487
 register+0.460
 roses+0.447
 decides+0.445
 ponies+0.439
Neg logit contributions
orse-0.380
 weapon-0.282
 hockey-0.278
oy-0.271
 bone-0.264
Token,
Token ID11
Feature activation-4.98e-01

Pos logit contributions
orse+0.009
 weapon+0.006
ggy+0.006
 bone+0.006
 hockey+0.006
Neg logit contributions
 groom-0.012
 roses-0.011
 register-0.011
 decides-0.011
 ponies-0.011
Token we
Token ID356
Feature activation+1.81e+00

Pos logit contributions
 groom+0.029
 register+0.027
 roses+0.027
 decides+0.026
 ponies+0.025
Neg logit contributions
orse-0.029
 weapon-0.022
 hockey-0.022
 bone-0.021
oc-0.021
Token can
Token ID460
Feature activation-5.93e+00

Pos logit contributions
orse+0.110
oc+0.091
 weapon+0.089
 bone+0.084
 Carl+0.080
Neg logit contributions
 groom-0.104
 roses-0.099
 ponies-0.094
 register-0.093
 pastor-0.085
Token play
Token ID711
Feature activation+2.98e+00

Pos logit contributions
 groom+0.343
 roses+0.328
 register+0.323
 ponies+0.319
 decides+0.310
Neg logit contributions
orse-0.349
 weapon-0.266
 hockey-0.262
 Carl-0.257
oc-0.254
Token dress
Token ID6576
Feature activation-2.06e+00

Pos logit contributions
orse+0.176
 hockey+0.141
 weapon+0.140
oc+0.135
 puck+0.133
Neg logit contributions
 groom-0.173
 roses-0.162
 register-0.160
 decides-0.158
 ponies-0.152
Token up
Token ID510
Feature activation-4.68e+00

Pos logit contributions
 groom+0.127
 decides+0.118
 register+0.116
 roses+0.116
 ponies+0.108
Neg logit contributions
orse-0.108
 hockey-0.089
ggy-0.087
oc-0.087
 weapon-0.086
Token with
Token ID351
Feature activation+4.89e+00

Pos logit contributions
 groom+0.274
 register+0.252
 roses+0.251
 decides+0.244
 ponies+0.235
Neg logit contributions
orse-0.281
 weapon-0.220
oc-0.219
 bone-0.209
 hockey-0.209
Token your
Token ID534
Feature activation-1.12e+00

Pos logit contributions
orse+0.312
 weapon+0.247
 hockey+0.243
 bone+0.238
oc+0.237
Neg logit contributions
 groom-0.258
 register-0.239
 decides-0.237
 roses-0.236
 ponies-0.222
Tokenama
Token ID1689
Feature activation-7.46e-01

Pos logit contributions
 groom+0.398
 roses+0.379
 register+0.377
 ponies+0.359
 decides+0.354
Neg logit contributions
orse-0.365
 weapon-0.293
 hockey-0.279
 puck-0.277
 bone-0.275
Token bear
Token ID6842
Feature activation-1.83e-01

Pos logit contributions
 groom+0.044
 roses+0.041
 register+0.039
 decides+0.039
 ponies+0.038
Neg logit contributions
orse-0.043
 weapon-0.035
oc-0.035
unch-0.033
 puck-0.032
Token said
Token ID531
Feature activation+2.44e+00

Pos logit contributions
 groom+0.011
 roses+0.010
 decides+0.010
 register+0.009
 ponies+0.009
Neg logit contributions
orse-0.011
 weapon-0.008
oc-0.008
unch-0.008
 puck-0.008
Token yes
Token ID3763
Feature activation-8.25e-01

Pos logit contributions
orse+0.141
oc+0.110
 weapon+0.110
 bone+0.103
uddy+0.102
Neg logit contributions
 groom-0.148
 roses-0.137
 register-0.133
 decides-0.131
 ponies-0.128
Token.
Token ID13
Feature activation-7.00e-02

Pos logit contributions
 groom+0.038
 register+0.037
 decides+0.036
 back+0.035
 roses+0.035
Neg logit contributions
orse-0.058
 puck-0.044
unch-0.044
oc-0.044
 weapon-0.044
Token She
Token ID1375
Feature activation-6.05e+00

Pos logit contributions
 groom+0.004
 roses+0.004
 register+0.004
 decides+0.004
 Angel+0.003
Neg logit contributions
orse-0.004
 weapon-0.003
ggy-0.003
inations-0.003
oc-0.003
Token was
Token ID373
Feature activation+1.40e+00

Pos logit contributions
 groom+0.356
 roses+0.326
 decides+0.314
 register+0.313
 ponies+0.302
Neg logit contributions
orse-0.361
 weapon-0.286
oc-0.283
 bone-0.267
unch-0.266
Token a
Token ID257
Feature activation-3.63e-01

Pos logit contributions
orse+0.082
 weapon+0.062
oc+0.062
 bone+0.059
ggy+0.059
Neg logit contributions
 groom-0.084
 roses-0.079
 register-0.077
 decides-0.076
 ponies-0.073
Token kind
Token ID1611
Feature activation+1.43e-01

Pos logit contributions
 groom+0.021
 roses+0.019
 register+0.018
 decides+0.018
 ponies+0.017
Neg logit contributions
orse-0.022
 weapon-0.017
unch-0.017
uddy-0.017
oc-0.017
Token,
Token ID11
Feature activation-1.06e+00

Pos logit contributions
orse+0.009
 weapon+0.007
oc+0.007
ggy+0.007
 puck+0.007
Neg logit contributions
 groom-0.008
 roses-0.007
 register-0.007
 ponies-0.007
 decides-0.007
Token obedient
Token ID41652
Feature activation+3.51e-01

Pos logit contributions
 groom+0.061
 roses+0.057
 ponies+0.053
 decides+0.052
 nurses+0.051
Neg logit contributions
orse-0.064
oc-0.051
uddy-0.050
unch-0.049
 weapon-0.049
Token asked
Token ID1965
Feature activation-5.05e+00

Pos logit contributions
 groom+0.306
 roses+0.285
 register+0.280
 decides+0.268
 ponies+0.264
Neg logit contributions
orse-0.362
 weapon-0.288
oc-0.283
 bone-0.272
oy-0.268
Token her
Token ID607
Feature activation-6.34e+00

Pos logit contributions
 groom+0.255
 decides+0.241
 register+0.230
 roses+0.217
als+0.215
Neg logit contributions
 Tim-0.303
orse-0.290
 Andy-0.287
 Benny-0.280
 His-0.270
Token mom
Token ID1995
Feature activation-4.50e+00

Pos logit contributions
 groom+0.318
 register+0.284
 roses+0.284
 decides+0.280
 ponies+0.263
Neg logit contributions
orse-0.430
 weapon-0.365
 bone-0.352
oc-0.342
 Carl-0.338
Token,
Token ID11
Feature activation-6.21e-01

Pos logit contributions
 groom+0.330
 roses+0.294
 decides+0.284
 register+0.280
pan+0.277
Neg logit contributions
orse-0.194
 weapon-0.159
 bone-0.152
 Carl-0.149
 Benny-0.147
Token "
Token ID366
Feature activation-4.01e+00

Pos logit contributions
 groom+0.040
 decides+0.037
 roses+0.037
 register+0.037
 ponies+0.035
Neg logit contributions
orse-0.033
 weapon-0.025
 Carl-0.025
 bone-0.024
 Andy-0.024
TokenCan
Token ID6090
Feature activation-1.02e+01

Pos logit contributions
 register+0.182
 roses+0.180
 groom+0.179
pan+0.175
 ponies+0.172
Neg logit contributions
orse-0.234
oc-0.229
Tim-0.210
Joe-0.204
 bone-0.198
Token you
Token ID345
Feature activation+3.85e+00

Pos logit contributions
 groom+0.710
 register+0.667
 roses+0.648
 decides+0.639
 ponies+0.618
Neg logit contributions
orse-0.518
 weapon-0.379
 Carl-0.361
 bone-0.358
 Andy-0.354
Token show
Token ID905
Feature activation-4.69e-01

Pos logit contributions
orse+0.279
oc+0.228
 weapon+0.224
uddy+0.220
unch+0.218
Neg logit contributions
 groom-0.177
 roses-0.157
 decides-0.150
 register-0.149
 ponies-0.140
Token me
Token ID502
Feature activation-2.45e+00

Pos logit contributions
 register+0.026
 decides+0.025
 groom+0.025
pan+0.024
 salon+0.023
Neg logit contributions
orse-0.025
 Benny-0.022
 Carl-0.022
 Andy-0.022
 Sammy-0.021
Token some
Token ID617
Feature activation-3.49e+00

Pos logit contributions
 groom+0.144
 register+0.134
 decides+0.131
 roses+0.127
 ponies+0.125
Neg logit contributions
orse-0.148
 weapon-0.120
 Carl-0.112
 bone-0.110
 hockey-0.109
Token animals
Token ID4695
Feature activation-5.15e-01

Pos logit contributions
 groom+0.187
 roses+0.182
 decides+0.168
 ponies+0.165
 register+0.165
Neg logit contributions
orse-0.225
oc-0.174
uddy-0.171
 weapon-0.169
unch-0.168
Token
Token ID198
Feature activation-8.46e-02

Pos logit contributions
 groom+0.111
 roses+0.106
 decides+0.101
 register+0.100
 ponies+0.096
Neg logit contributions
orse-0.140
oc-0.114
 weapon-0.113
oy-0.108
uddy-0.108
Token
Token ID198
Feature activation-8.44e-02

Pos logit contributions
 groom+0.005
 roses+0.005
 register+0.005
 decides+0.005
 ponies+0.005
Neg logit contributions
orse-0.004
 weapon-0.003
oc-0.003
 bone-0.003
uddy-0.003
TokenTom
Token ID13787
Feature activation+3.79e+00

Pos logit contributions
 groom+0.005
 roses+0.005
 register+0.005
 decides+0.005
 ponies+0.004
Neg logit contributions
orse-0.005
oc-0.004
 weapon-0.004
ggy-0.004
 bone-0.004
Token hugged
Token ID41130
Feature activation-5.19e+00

Pos logit contributions
orse+0.245
 weapon+0.196
oc+0.195
unch+0.187
 hockey+0.182
Neg logit contributions
 groom-0.201
 decides-0.185
 roses-0.183
 register-0.175
 Angel-0.165
Token her
Token ID607
Feature activation-6.55e+00

Pos logit contributions
 groom+0.361
 register+0.333
 roses+0.327
 decides+0.308
 ponies+0.304
Neg logit contributions
orse-0.240
 Tim-0.204
 weapon-0.202
 Benny-0.202
 His-0.198
Token back
Token ID736
Feature activation-8.97e+00

Pos logit contributions
 groom+0.378
 roses+0.343
 register+0.336
 decides+0.331
 ponies+0.312
Neg logit contributions
orse-0.399
 weapon-0.338
 bone-0.328
oc-0.321
 hockey-0.308
Token and
Token ID290
Feature activation-2.49e-01

Pos logit contributions
 groom+0.570
 roses+0.524
 register+0.515
 decides+0.504
 ponies+0.485
Neg logit contributions
orse-0.505
 weapon-0.394
oc-0.393
 bone-0.370
uddy-0.362
Token said
Token ID531
Feature activation+2.71e+00

Pos logit contributions
 groom+0.015
 roses+0.014
 register+0.013
 decides+0.013
 ponies+0.013
Neg logit contributions
orse-0.015
 weapon-0.011
oc-0.011
 bone-0.011
uddy-0.011
Token,
Token ID11
Feature activation-8.08e-01

Pos logit contributions
orse+0.156
 weapon+0.120
oc+0.118
 bone+0.112
ggy+0.111
Neg logit contributions
 groom-0.168
 roses-0.156
 register-0.152
 decides-0.150
 ponies-0.146
Token "
Token ID366
Feature activation-4.22e+00

Pos logit contributions
 groom+0.043
 roses+0.040
 register+0.039
 decides+0.038
 ponies+0.037
Neg logit contributions
orse-0.052
 weapon-0.042
oc-0.042
 bone-0.040
uddy-0.039
TokenIt
Token ID1026
Feature activation+1.58e+00

Pos logit contributions
 groom+0.155
 roses+0.131
She+0.129
 decides+0.129
 Angel+0.115
Neg logit contributions
orse-0.339
 weapon-0.298
oy-0.288
 burying-0.284
inations-0.282
Token and
Token ID290
Feature activation-5.46e-01

Pos logit contributions
 groom+0.026
 roses+0.024
 register+0.024
 decides+0.023
 ponies+0.023
Neg logit contributions
orse-0.024
 weapon-0.019
oc-0.018
 bone-0.018
 hockey-0.017
Token laughed
Token ID13818
Feature activation+4.97e+00

Pos logit contributions
 groom+0.032
 roses+0.029
 register+0.029
 decides+0.028
 ponies+0.027
Neg logit contributions
orse-0.033
 weapon-0.026
oc-0.026
 bone-0.024
 Carl-0.024
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
orse+0.262
 weapon+0.199
oc+0.192
 bone+0.189
 hockey+0.188
Neg logit contributions
 groom-0.325
 register-0.301
 roses-0.300
 decides-0.293
 ponies-0.280
Token They
Token ID1119
Feature activation+6.18e-01

Pos logit contributions
 groom+0.008
 register+0.007
 roses+0.007
 decides+0.007
 ponies+0.007
Neg logit contributions
orse-0.005
oc-0.003
 weapon-0.003
 Carl-0.003
 bone-0.003
Token cut
Token ID2005
Feature activation+1.69e-01

Pos logit contributions
orse+0.035
 weapon+0.026
oc+0.026
 bone+0.025
 puck+0.024
Neg logit contributions
 groom-0.038
 roses-0.036
 register-0.036
 decides-0.035
 ponies-0.034
Token out
Token ID503
Feature activation-7.96e+00

Pos logit contributions
orse+0.011
 weapon+0.009
oc+0.009
 Carl+0.009
 bone+0.009
Neg logit contributions
 groom-0.009
 roses-0.008
 register-0.008
 decides-0.008
 ponies-0.008
Token their
Token ID511
Feature activation-2.72e-01

Pos logit contributions
 groom+0.415
 roses+0.375
 register+0.375
 decides+0.368
 ponies+0.350
Neg logit contributions
orse-0.522
 weapon-0.422
oc-0.417
 bone-0.402
 Carl-0.395
Token favorite
Token ID4004
Feature activation+2.68e+00

Pos logit contributions
 groom+0.011
 roses+0.011
 decides+0.009
 ponies+0.009
 register+0.009
Neg logit contributions
orse-0.021
unch-0.018
 Carl-0.017
uddy-0.017
oc-0.017
Token pictures
Token ID5986
Feature activation-2.85e+00

Pos logit contributions
orse+0.186
 weapon+0.150
oc+0.149
uddy+0.143
 bone+0.142
Neg logit contributions
 groom-0.133
 roses-0.122
 register-0.117
 decides-0.115
 ponies-0.111
Token and
Token ID290
Feature activation-5.14e-01

Pos logit contributions
 groom+0.168
 roses+0.156
 register+0.152
 decides+0.149
 ponies+0.145
Neg logit contributions
orse-0.169
 weapon-0.132
oc-0.131
 bone-0.124
uddy-0.123
Token glued
Token ID39783
Feature activation-2.76e+00

Pos logit contributions
 groom+0.028
 roses+0.026
 register+0.025
 decides+0.025
 ponies+0.024
Neg logit contributions
orse-0.033
 weapon-0.026
oc-0.026
 bone-0.025
uddy-0.024
Token
Token ID198
Feature activation+5.10e-01

Pos logit contributions
orse+0.031
 weapon+0.026
 puck+0.024
oy+0.024
 bullets+0.023
Neg logit contributions
 groom-0.025
 roses-0.024
 decides-0.023
She-0.022
 register-0.022
TokenThey
Token ID2990
Feature activation-9.67e-01

Pos logit contributions
orse+0.029
oc+0.023
 weapon+0.022
 bone+0.021
ggy+0.021
Neg logit contributions
 groom-0.032
 roses-0.030
 register-0.029
 decides-0.028
 ponies-0.028
Token went
Token ID1816
Feature activation-4.17e+00

Pos logit contributions
 groom+0.055
 roses+0.053
 decides+0.050
 register+0.050
 ponies+0.050
Neg logit contributions
orse-0.056
oc-0.043
 weapon-0.043
oy-0.042
 bone-0.041
Token to
Token ID284
Feature activation+1.05e+00

Pos logit contributions
 groom+0.275
 decides+0.253
 roses+0.251
 register+0.239
 ponies+0.229
Neg logit contributions
orse-0.209
 weapon-0.169
 fishing-0.169
 hockey-0.166
 bone-0.160
Token the
Token ID262
Feature activation+4.64e-01

Pos logit contributions
orse+0.066
 weapon+0.053
oc+0.052
 bone+0.051
 hockey+0.050
Neg logit contributions
 groom-0.057
 roses-0.053
 register-0.052
 decides-0.051
 ponies-0.049
Token store
Token ID3650
Feature activation-8.35e+00

Pos logit contributions
 bone+0.026
 hockey+0.025
 golf+0.025
 weapon+0.025
orse+0.023
Neg logit contributions
 groom-0.022
 roses-0.021
la-0.021
 decides-0.021
pan-0.020
Token and
Token ID290
Feature activation+3.86e-01

Pos logit contributions
 groom+0.453
 roses+0.420
 register+0.414
 decides+0.401
 ponies+0.389
Neg logit contributions
orse-0.537
 weapon-0.425
oc-0.420
 bone-0.399
 Carl-0.398
Token found
Token ID1043
Feature activation+1.27e+00

Pos logit contributions
orse+0.022
 weapon+0.016
oc+0.016
 Carl+0.016
 Benny+0.016
Neg logit contributions
 groom-0.024
 roses-0.022
 register-0.021
 decides-0.021
 ponies-0.021
Token a
Token ID257
Feature activation+5.40e-01

Pos logit contributions
orse+0.065
 weapon+0.055
 bone+0.055
 Carl+0.054
 Benny+0.053
Neg logit contributions
 groom-0.080
 decides-0.073
 roses-0.070
 register-0.068
 ponies-0.068
Token pretty
Token ID2495
Feature activation+1.13e+00

Pos logit contributions
orse+0.031
 weapon+0.024
oc+0.024
 bone+0.023
 puck+0.022
Neg logit contributions
 groom-0.033
 roses-0.030
 register-0.030
 decides-0.030
 ponies-0.029
Token pink
Token ID11398
Feature activation-3.44e+00

Pos logit contributions
orse+0.069
 weapon+0.058
oc+0.055
 bone+0.055
 hockey+0.052
Neg logit contributions
 groom-0.062
 register-0.057
 decides-0.057
 roses-0.056
 ponies-0.054
Token brave
Token ID14802
Feature activation-1.43e+00

Pos logit contributions
 groom+0.024
 roses+0.021
 decides+0.020
 register+0.020
 nurses+0.019
Neg logit contributions
orse-0.027
unch-0.022
oy-0.021
uddy-0.020
oc-0.020
Token cat
Token ID3797
Feature activation+1.76e-03

Pos logit contributions
 groom+0.071
 roses+0.062
 register+0.061
 decides+0.060
 nurses+0.059
Neg logit contributions
orse-0.098
unch-0.079
inations-0.078
orses-0.076
oc-0.074
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
orse+0.000
inations+0.000
unch+0.000
emo+0.000
 puck+0.000
Neg logit contributions
 groom-0.000
 roses-0.000
 register-0.000
 ponies-0.000
al-0.000
Token so
Token ID523
Feature activation+3.37e-02

Pos logit contributions
 groom+0.062
 roses+0.058
 decides+0.056
 register+0.054
 ponies+0.053
Neg logit contributions
orse-0.074
oc-0.059
 weapon-0.058
uddy-0.055
unch-0.055
Token he
Token ID339
Feature activation+5.50e+00

Pos logit contributions
orse+0.001
unch+0.001
inations+0.001
uddy+0.001
 weapon+0.001
Neg logit contributions
 groom-0.002
 her-0.002
 decides-0.002
 roses-0.002
 ponies-0.002
Token slowly
Token ID6364
Feature activation-9.37e+00

Pos logit contributions
orse+0.353
 weapon+0.280
oc+0.280
 bone+0.266
unch+0.265
Neg logit contributions
 groom-0.301
 roses-0.275
 register-0.265
 decides-0.264
 ponies-0.253
Token opened
Token ID4721
Feature activation-8.01e-02

Pos logit contributions
 groom+0.517
 roses+0.475
 register+0.466
 decides+0.457
 ponies+0.444
Neg logit contributions
orse-0.596
 weapon-0.472
oc-0.468
 bone-0.444
oy-0.438
Token the
Token ID262
Feature activation-4.74e-01

Pos logit contributions
 groom+0.005
 roses+0.005
 register+0.005
 decides+0.005
 ponies+0.004
Neg logit contributions
orse-0.005
 weapon-0.003
oc-0.003
uddy-0.003
 bone-0.003
Token box
Token ID3091
Feature activation+3.38e-01

Pos logit contributions
 groom+0.027
 roses+0.024
 decides+0.023
 ponies+0.023
 register+0.022
Neg logit contributions
orse-0.027
 weapon-0.026
 bone-0.025
oc-0.024
 hockey-0.022
Token.
Token ID13
Feature activation-1.34e-01

Pos logit contributions
orse+0.024
oc+0.019
 weapon+0.019
ggy+0.018
emy+0.018
Neg logit contributions
 groom-0.015
 register-0.015
 roses-0.015
 decides-0.014
 ponies-0.013
Token
Token ID198
Feature activation-3.47e-01

Pos logit contributions
 groom+0.006
 roses+0.006
 decides+0.006
 Angel+0.006
 register+0.006
Neg logit contributions
orse-0.009
 weapon-0.007
inations-0.007
oc-0.007
oy-0.007