TOP ACTIVATIONS
MAX = 0.272

did not like the f auc et . The f auc
auc et . The f auc et was scary . It
quickly turned off the f auc et and tried to hide
to turn off the f auc et after washing her hands
Tim found a magic f auc et in his yard .
She turned on the f auc et and filled the sink
look at the pretty f auc et !" Lily called out
They turn on the f auc et . They put soap
kept skipping around the f auc et . Faster and faster
she skipped until the f auc et was a blur of
she saw a beautiful f auc et .
and turned off the f auc et for her . Lily
They turned on the f auc et and ran some water
. They opened the f auc et and put their letters
she turned on the f auc et , no water came
other plants ." The f auc et said , " Yes
careful with spiders and f auc ets . She
him , with many f auc ets and a big knob
of water from the f auc et . When
the stove and the f auc et . She picked up

MIN ACTIVATIONS
MIN = -0.315

quickly grabbed a band - aid and helped Tim my put
gave Lily a band - aid for her knee . She
doctor put a band - aid on her arm . He
He liked the band - aid and the dinosaur . He
bird felt the band - aid was sticky and cool .
'll put a band - aid on your hand and then
gave Jack a band - aid for his knee and a
inside and put a band aid on it ," she said
gave them a band - aid and moved a little to
and put a band - aid on it . They kissed
can put a band - aid on it ." Lily felt
to get a band - aid and a cookie . They
gave Lily a band - aid for her knee . They
Ben put the band - aid on Lily 's knee .
back with the band - aid , Lily was smiling and
She put a band - aid on it . She hugged
asked for a band - aid . Miss Lee gave them
quickly got a band - aid to make it better .
They put a band - aid on Anna 's finger .
and put some band - aid s on them . Then

INTERVAL 0.125 - 0.272
CONTAINS 1.825%

So Murray turned the dish washer on and started enjoying it
were watching a big box with a lot of lights and
suggested . So Jack and Jane parted the branches
and Papa looked at them with love . They said ,
. The old man looked at her and smiled . He

INTERVAL -0.022 - 0.125
CONTAINS 66.174%

, no !" Mom says . " What happened here ?"
." L ily felt happy that she helped
and everyone had fun dancing . The end . <|endoftext|> Once
had to be very special . She thanked Sam again and
her dress . She saw the hole . She was sad

INTERVAL -0.169 - -0.022
CONTAINS 31.537%

eager to play with her friends . One day , Lily
at night . The monster stayed under his bed , and
much fun at the park ." Her mom smiled and said
win that she kept the trophy in her room . Every
to pay for food , clothes , rent and other things

INTERVAL -0.315 - -0.169
CONTAINS 0.464%

loved it ! " Can I have my own
!" Lily said with a smile . They carefully
put on their hats and scar ves and got their pots
: You should share and respect others who need help .
can help you . I know how to repair cars ,"
Token did
Token ID750
Feature activation-4.63e-02

Pos logit contributions
 site+0.151
room+0.149
tub+0.148
 port+0.144
 factory+0.143
Neg logit contributions
aid-0.116
 tighter-0.090
 reins-0.088
 brid-0.083
 scar-0.080
Token not
Token ID407
Feature activation-2.83e-02

Pos logit contributions
aid+0.091
 reins+0.079
 tighter+0.074
 brid+0.072
Sleep+0.066
Neg logit contributions
tub-0.075
 site-0.075
room-0.075
 factory-0.073
 port-0.073
Token like
Token ID588
Feature activation-5.07e-02

Pos logit contributions
aid+0.045
 reins+0.042
 tighter+0.038
 brid+0.037
 swollen+0.033
Neg logit contributions
room-0.055
 port-0.055
tub-0.054
 nation-0.053
 factory-0.053
Token the
Token ID262
Feature activation-9.28e-03

Pos logit contributions
aid+0.060
 tighter+0.047
 reins+0.046
 scar+0.043
 care+0.040
Neg logit contributions
room-0.112
 site-0.111
apped-0.109
tub-0.109
 Fourth-0.107
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.019
 reins+0.017
 tighter+0.016
 brid+0.015
 scar+0.015
Neg logit contributions
room-0.014
 site-0.014
tub-0.013
 factory-0.013
 port-0.013
Tokenauc
Token ID14272
Feature activation+2.34e-01

Pos logit contributions
 port+0.099
 site+0.094
 nation+0.082
 factory+0.079
 Fourth+0.079
Neg logit contributions
aid-0.394
ache-0.312
paste-0.302
 bleed-0.301
 reins-0.299
Tokenet
Token ID316
Feature activation+5.97e-02

Pos logit contributions
 port+0.357
 site+0.341
tub+0.340
 factory+0.327
room+0.320
Neg logit contributions
aid-0.498
 tighter-0.401
 reins-0.396
 care-0.376
 brid-0.372
Token.
Token ID13
Feature activation-1.11e-05

Pos logit contributions
 port+0.106
 site+0.105
tub+0.104
room+0.102
 factory+0.101
Neg logit contributions
aid-0.101
 reins-0.083
 tighter-0.082
 brid-0.075
 scar-0.073
Token The
Token ID383
Feature activation+1.10e-02

Pos logit contributions
aid+0.000
 tighter+0.000
 reins+0.000
Do+0.000
Sleep+0.000
Neg logit contributions
 site-0.000
tub-0.000
 port-0.000
 factory-0.000
iggle-0.000
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
room+0.016
 site+0.015
tub+0.015
 factory+0.015
 port+0.015
Neg logit contributions
aid-0.023
 reins-0.020
 tighter-0.019
 brid-0.018
 scar-0.018
Tokenauc
Token ID14272
Feature activation+2.34e-01

Pos logit contributions
 port+0.117
 Fourth+0.098
 site+0.098
 nation+0.094
 structure+0.088
Neg logit contributions
aid-0.394
paste-0.292
ache-0.292
 bleed-0.282
 care-0.280
Tokenauc
Token ID14272
Feature activation+2.34e-01

Pos logit contributions
 port+0.099
 site+0.094
 nation+0.082
 factory+0.079
 Fourth+0.079
Neg logit contributions
aid-0.394
ache-0.312
paste-0.302
 bleed-0.301
 reins-0.299
Tokenet
Token ID316
Feature activation+5.97e-02

Pos logit contributions
 port+0.357
 site+0.341
tub+0.340
 factory+0.327
room+0.320
Neg logit contributions
aid-0.498
 tighter-0.401
 reins-0.396
 care-0.376
 brid-0.372
Token.
Token ID13
Feature activation-1.11e-05

Pos logit contributions
 port+0.106
 site+0.105
tub+0.104
room+0.102
 factory+0.101
Neg logit contributions
aid-0.101
 reins-0.083
 tighter-0.082
 brid-0.075
 scar-0.073
Token The
Token ID383
Feature activation+1.10e-02

Pos logit contributions
aid+0.000
 tighter+0.000
 reins+0.000
Do+0.000
Sleep+0.000
Neg logit contributions
 site-0.000
tub-0.000
 port-0.000
 factory-0.000
iggle-0.000
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
room+0.016
 site+0.015
tub+0.015
 factory+0.015
 port+0.015
Neg logit contributions
aid-0.023
 reins-0.020
 tighter-0.019
 brid-0.018
 scar-0.018
Tokenauc
Token ID14272
Feature activation+2.34e-01

Pos logit contributions
 port+0.117
 Fourth+0.098
 site+0.098
 nation+0.094
 structure+0.088
Neg logit contributions
aid-0.394
paste-0.292
ache-0.292
 bleed-0.282
 care-0.280
Tokenet
Token ID316
Feature activation+5.99e-02

Pos logit contributions
 port+0.366
tub+0.345
 site+0.341
 factory+0.330
room+0.325
Neg logit contributions
aid-0.497
 tighter-0.398
 reins-0.392
 brid-0.370
 bleed-0.368
Token was
Token ID373
Feature activation+1.02e-01

Pos logit contributions
 port+0.097
 site+0.091
room+0.090
 Fourth+0.090
tub+0.089
Neg logit contributions
aid-0.111
 tighter-0.088
 scar-0.086
 reins-0.084
 brid-0.084
Token scary
Token ID14343
Feature activation+2.85e-02

Pos logit contributions
room+0.191
 site+0.185
tub+0.184
 factory+0.181
 port+0.181
Neg logit contributions
aid-0.171
 tighter-0.144
 reins-0.141
 brid-0.131
 scar-0.128
Token.
Token ID13
Feature activation-4.01e-04

Pos logit contributions
 port+0.058
tub+0.057
 site+0.057
room+0.057
 Fourth+0.056
Neg logit contributions
aid-0.039
 tighter-0.032
 reins-0.031
 scar-0.028
 brid-0.027
Token It
Token ID632
Feature activation-1.52e-02

Pos logit contributions
aid+0.001
 reins+0.001
 tighter+0.001
Do+0.000
Sleep+0.000
Neg logit contributions
 port-0.001
tub-0.001
 site-0.001
 factory-0.001
iggle-0.001
Token quickly
Token ID2952
Feature activation+6.58e-03

Pos logit contributions
aid+0.079
 tighter+0.066
 reins+0.066
 brid+0.061
 scar+0.058
Neg logit contributions
tub-0.083
 site-0.081
room-0.081
 factory-0.078
 port-0.078
Token turned
Token ID2900
Feature activation+1.20e-02

Pos logit contributions
tub+0.012
room+0.012
 site+0.011
 factory+0.011
 port+0.011
Neg logit contributions
aid-0.012
 tighter-0.010
 reins-0.010
 brid-0.009
 scar-0.009
Token off
Token ID572
Feature activation-5.81e-02

Pos logit contributions
tub+0.019
room+0.019
 site+0.019
 factory+0.018
 port+0.018
Neg logit contributions
aid-0.024
 reins-0.021
 tighter-0.020
 brid-0.019
 scar-0.018
Token the
Token ID262
Feature activation+1.60e-04

Pos logit contributions
aid+0.113
 reins+0.099
 tighter+0.092
 brid+0.091
Sleep+0.084
Neg logit contributions
tub-0.094
room-0.093
 site-0.092
 port-0.092
 factory-0.092
Token f
Token ID277
Feature activation+1.38e-01

Pos logit contributions
tub+0.000
room+0.000
 site+0.000
 port+0.000
 factory+0.000
Neg logit contributions
aid-0.000
 reins-0.000
 tighter-0.000
 brid-0.000
Sleep-0.000
Tokenauc
Token ID14272
Feature activation+2.34e-01

Pos logit contributions
 port+0.083
 nation+0.081
 site+0.078
 Fourth+0.072
 factory+0.070
Neg logit contributions
aid-0.420
 tighter-0.348
 reins-0.341
ache-0.329
 bleed-0.326
Tokenet
Token ID316
Feature activation+6.23e-02

Pos logit contributions
 port+0.310
tub+0.308
 site+0.303
room+0.302
 factory+0.297
Neg logit contributions
aid-0.525
 reins-0.449
 tighter-0.446
 brid-0.420
 scar-0.397
Token and
Token ID290
Feature activation-1.51e-02

Pos logit contributions
 site+0.117
 port+0.116
tub+0.115
 factory+0.114
room+0.114
Neg logit contributions
aid-0.101
 reins-0.083
 tighter-0.082
 brid-0.074
 scar-0.068
Token tried
Token ID3088
Feature activation-6.76e-02

Pos logit contributions
aid+0.028
 tighter+0.024
 reins+0.024
 brid+0.022
 scar+0.021
Neg logit contributions
room-0.026
tub-0.026
 site-0.026
 factory-0.025
 port-0.025
Token to
Token ID284
Feature activation-3.45e-02

Pos logit contributions
aid+0.126
 reins+0.110
 brid+0.101
 tighter+0.095
Dear+0.092
Neg logit contributions
tub-0.117
 site-0.116
 factory-0.114
room-0.114
 port-0.114
Token hide
Token ID7808
Feature activation+1.32e-01

Pos logit contributions
aid+0.057
 reins+0.048
 tighter+0.046
 brid+0.043
 bleed+0.040
Neg logit contributions
tub-0.066
 site-0.065
room-0.064
 factory-0.064
 port-0.063
Token to
Token ID284
Feature activation-3.91e-02

Pos logit contributions
aid+0.250
 reins+0.211
 tighter+0.201
 brid+0.192
Sleep+0.173
Neg logit contributions
tub-0.276
room-0.273
 site-0.271
 port-0.268
 factory-0.268
Token turn
Token ID1210
Feature activation-2.84e-02

Pos logit contributions
aid+0.072
 reins+0.064
 tighter+0.059
 brid+0.057
Sleep+0.052
Neg logit contributions
room-0.067
 port-0.066
 factory-0.065
 site-0.065
tub-0.065
Token off
Token ID572
Feature activation-6.27e-02

Pos logit contributions
aid+0.057
 reins+0.049
 tighter+0.047
 brid+0.046
Sleep+0.042
Neg logit contributions
tub-0.044
room-0.044
 site-0.043
 port-0.043
 factory-0.043
Token the
Token ID262
Feature activation-7.67e-03

Pos logit contributions
aid+0.111
 reins+0.094
 tighter+0.091
 brid+0.086
 scar+0.079
Neg logit contributions
tub-0.111
room-0.110
 site-0.109
 port-0.108
 factory-0.108
Token f
Token ID277
Feature activation+1.34e-01

Pos logit contributions
aid+0.016
 reins+0.015
 tighter+0.014
 brid+0.013
 scar+0.013
Neg logit contributions
room-0.011
tub-0.011
 site-0.011
 port-0.010
 factory-0.010
Tokenauc
Token ID14272
Feature activation+2.33e-01

Pos logit contributions
 port+0.095
 site+0.089
 nation+0.088
 factory+0.081
 structure+0.077
Neg logit contributions
aid-0.386
 reins-0.316
 tighter-0.312
ache-0.302
Sleep-0.296
Tokenet
Token ID316
Feature activation+5.95e-02

Pos logit contributions
 port+0.338
tub+0.332
 site+0.325
room+0.322
 factory+0.314
Neg logit contributions
aid-0.492
 tighter-0.416
 reins-0.408
 brid-0.377
 care-0.371
Token after
Token ID706
Feature activation+3.13e-02

Pos logit contributions
 site+0.105
 port+0.104
tub+0.103
 nation+0.101
 factory+0.101
Neg logit contributions
aid-0.101
 reins-0.083
 tighter-0.083
 brid-0.075
 scar-0.071
Token washing
Token ID20518
Feature activation+4.29e-02

Pos logit contributions
tub+0.057
 site+0.056
room+0.056
 port+0.055
 factory+0.055
Neg logit contributions
aid-0.051
 reins-0.042
 tighter-0.041
 brid-0.037
 bud-0.036
Token her
Token ID607
Feature activation-7.23e-02

Pos logit contributions
 site+0.075
 nation+0.074
tub+0.073
room+0.073
 port+0.073
Neg logit contributions
aid-0.069
 tighter-0.060
 reins-0.056
 brid-0.052
 care-0.051
Token hands
Token ID2832
Feature activation-3.66e-02

Pos logit contributions
aid+0.139
 reins+0.120
 tighter+0.118
 scar+0.118
 brid+0.112
Neg logit contributions
room-0.107
 site-0.107
ide-0.102
aded-0.102
 port-0.100
Token Tim
Token ID5045
Feature activation+1.42e-01

Pos logit contributions
 site+0.174
tub+0.160
iced+0.155
 port+0.153
uders+0.153
Neg logit contributions
aid-0.228
 listen-0.195
 care-0.193
 reins-0.177
He-0.174
Token found
Token ID1043
Feature activation+6.33e-02

Pos logit contributions
 site+0.248
tub+0.243
 port+0.236
 factory+0.229
room+0.227
Neg logit contributions
aid-0.263
 tighter-0.206
 reins-0.206
 care-0.200
Dear-0.194
Token a
Token ID257
Feature activation-5.22e-03

Pos logit contributions
tub+0.123
 site+0.121
room+0.120
 port+0.119
 factory+0.119
Neg logit contributions
aid-0.105
 reins-0.084
 tighter-0.082
 brid-0.077
Sleep-0.070
Token magic
Token ID5536
Feature activation-6.68e-03

Pos logit contributions
aid+0.010
 reins+0.009
 tighter+0.008
 brid+0.008
 scar+0.008
Neg logit contributions
room-0.008
 site-0.008
tub-0.008
apped-0.008
auc-0.008
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.011
 reins+0.010
 tighter+0.009
 brid+0.009
 scar+0.008
Neg logit contributions
room-0.012
tub-0.012
 site-0.012
 factory-0.012
 port-0.012
Tokenauc
Token ID14272
Feature activation+2.33e-01

Pos logit contributions
 site+0.084
 port+0.074
 factory+0.064
 Fourth+0.064
 nation+0.061
Neg logit contributions
aid-0.413
 reins-0.338
 tighter-0.333
ache-0.323
 bud-0.323
Tokenet
Token ID316
Feature activation+5.97e-02

Pos logit contributions
 port+0.344
 site+0.337
tub+0.331
 factory+0.315
room+0.312
Neg logit contributions
aid-0.506
 tighter-0.405
 reins-0.396
 brid-0.377
 care-0.375
Token in
Token ID287
Feature activation+1.02e-01

Pos logit contributions
tub+0.111
 site+0.110
 port+0.108
room+0.108
 factory+0.106
Neg logit contributions
aid-0.096
 reins-0.081
 tighter-0.077
 brid-0.072
 scar-0.066
Token his
Token ID465
Feature activation-3.05e-02

Pos logit contributions
tub+0.200
room+0.195
 site+0.193
 factory+0.191
 port+0.191
Neg logit contributions
aid-0.164
 reins-0.134
 tighter-0.132
 brid-0.122
Sleep-0.112
Token yard
Token ID12699
Feature activation+5.49e-02

Pos logit contributions
aid+0.051
 scar+0.045
 care+0.043
 tighter+0.043
 reins+0.041
Neg logit contributions
ide-0.052
 site-0.049
room-0.049
auc-0.047
uders-0.046
Token.
Token ID13
Feature activation+2.24e-03

Pos logit contributions
 port+0.128
agically+0.125
unky+0.125
aded+0.122
auc+0.121
Neg logit contributions
aid-0.053
 tighter-0.039
 reins-0.035
 advice-0.031
Are-0.030
Token She
Token ID1375
Feature activation-6.11e-02

Pos logit contributions
room+0.002
tub+0.002
 site+0.002
 factory+0.002
 port+0.002
Neg logit contributions
aid-0.002
 reins-0.002
 tighter-0.001
 brid-0.001
 scar-0.001
Token turned
Token ID2900
Feature activation+9.10e-03

Pos logit contributions
aid+0.107
 tighter+0.086
 brid+0.082
 reins+0.079
 scar+0.079
Neg logit contributions
room-0.117
 port-0.117
tub-0.116
 site-0.114
iggle-0.113
Token on
Token ID319
Feature activation+2.85e-02

Pos logit contributions
tub+0.016
room+0.016
 site+0.016
 factory+0.016
 port+0.016
Neg logit contributions
aid-0.016
 reins-0.014
 tighter-0.013
 brid-0.012
 scar-0.011
Token the
Token ID262
Feature activation-5.67e-03

Pos logit contributions
room+0.045
 site+0.045
 factory+0.044
tub+0.044
 port+0.043
Neg logit contributions
aid-0.057
 reins-0.049
 tighter-0.046
 brid-0.045
Sleep-0.043
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.013
 reins+0.012
 tighter+0.011
 brid+0.011
Sleep+0.010
Neg logit contributions
tub-0.007
room-0.007
 site-0.007
 port-0.007
 factory-0.007
Tokenauc
Token ID14272
Feature activation+2.33e-01

Pos logit contributions
 port+0.063
 site+0.057
 nation+0.056
 factory+0.053
 Fourth+0.047
Neg logit contributions
aid-0.429
 reins-0.371
 tighter-0.365
 brid-0.349
Sleep-0.345
Tokenet
Token ID316
Feature activation+5.94e-02

Pos logit contributions
tub+0.301
 port+0.298
 site+0.294
room+0.292
 factory+0.289
Neg logit contributions
aid-0.530
 reins-0.460
 tighter-0.450
 brid-0.430
 scar-0.405
Token and
Token ID290
Feature activation-1.67e-02

Pos logit contributions
 site+0.113
 port+0.113
tub+0.112
 factory+0.111
 nation+0.110
Neg logit contributions
aid-0.094
 reins-0.077
 tighter-0.075
 brid-0.068
 scar-0.063
Token filled
Token ID5901
Feature activation+9.65e-02

Pos logit contributions
aid+0.031
 tighter+0.026
 reins+0.025
 brid+0.024
 scar+0.023
Neg logit contributions
room-0.030
tub-0.030
 site-0.029
 factory-0.029
 port-0.029
Token the
Token ID262
Feature activation-4.64e-03

Pos logit contributions
tub+0.198
 factory+0.197
 port+0.195
 nation+0.192
 Fourth+0.192
Neg logit contributions
aid-0.141
 tighter-0.117
 reins-0.104
 brid-0.097
What-0.093
Token sink
Token ID14595
Feature activation+9.95e-02

Pos logit contributions
aid+0.010
 reins+0.009
 tighter+0.009
 brid+0.008
Sleep+0.008
Neg logit contributions
room-0.006
 site-0.006
ide-0.006
iggle-0.006
ook-0.005
Token look
Token ID804
Feature activation-3.85e-02

Pos logit contributions
 factory+0.072
 port+0.072
tub+0.072
room+0.072
 site+0.069
Neg logit contributions
aid-0.076
 reins-0.066
 tighter-0.063
 brid-0.059
Sleep-0.055
Token at
Token ID379
Feature activation+1.46e-01

Pos logit contributions
aid+0.080
 reins+0.069
 tighter+0.067
 brid+0.064
 scar+0.062
Neg logit contributions
tub-0.058
room-0.057
 site-0.057
 port-0.055
 factory-0.054
Token the
Token ID262
Feature activation-1.22e-02

Pos logit contributions
tub+0.263
room+0.259
 site+0.255
 port+0.251
 factory+0.248
Neg logit contributions
aid-0.259
 reins-0.218
 tighter-0.207
 brid-0.200
 scar-0.187
Token pretty
Token ID2495
Feature activation+6.15e-03

Pos logit contributions
aid+0.028
 reins+0.024
 tighter+0.023
 brid+0.023
 scar+0.022
Neg logit contributions
room-0.015
 site-0.015
tub-0.014
 port-0.014
 factory-0.014
Token f
Token ID277
Feature activation+1.34e-01

Pos logit contributions
room+0.008
 site+0.008
tub+0.008
 port+0.008
 factory+0.008
Neg logit contributions
aid-0.013
 reins-0.011
 tighter-0.011
 brid-0.010
 scar-0.010
Tokenauc
Token ID14272
Feature activation+2.33e-01

Pos logit contributions
 port+0.073
 site+0.067
 nation+0.064
room+0.057
 structure+0.054
Neg logit contributions
aid-0.410
 reins-0.341
 tighter-0.331
ache-0.323
 bud-0.321
Tokenet
Token ID316
Feature activation+5.83e-02

Pos logit contributions
 port+0.341
tub+0.330
 site+0.325
room+0.322
 nation+0.310
Neg logit contributions
aid-0.495
 reins-0.408
 tighter-0.406
 brid-0.380
 scar-0.368
Token!"
Token ID2474
Feature activation-1.90e-02

Pos logit contributions
tub+0.108
room+0.107
 port+0.107
 site+0.106
 factory+0.105
Neg logit contributions
aid-0.095
 reins-0.081
 tighter-0.076
 brid-0.073
 scar-0.066
Token Lily
Token ID20037
Feature activation+2.54e-02

Pos logit contributions
aid+0.032
 tighter+0.024
 reins+0.022
 brid+0.022
 care+0.022
Neg logit contributions
 port-0.038
 site-0.038
room-0.037
tub-0.037
 factory-0.037
Token called
Token ID1444
Feature activation+1.60e-01

Pos logit contributions
 port+0.057
tub+0.053
 site+0.053
 factory+0.053
room+0.052
Neg logit contributions
aid-0.036
 tighter-0.030
 brid-0.026
 scar-0.026
 bud-0.025
Token out
Token ID503
Feature activation+1.56e-01

Pos logit contributions
 site+0.288
tub+0.286
room+0.280
 factory+0.273
 port+0.273
Neg logit contributions
aid-0.269
 tighter-0.228
 reins-0.223
 brid-0.210
 bleed-0.209
Token They
Token ID1119
Feature activation+2.64e-02

Pos logit contributions
 site+0.001
 factory+0.001
room+0.001
 nation+0.001
 port+0.001
Neg logit contributions
aid-0.001
 reins-0.001
 tighter-0.001
Sleep-0.001
 brid-0.001
Token turn
Token ID1210
Feature activation-2.69e-02

Pos logit contributions
tub+0.049
room+0.049
 site+0.049
 port+0.048
 factory+0.048
Neg logit contributions
aid-0.044
 reins-0.037
 tighter-0.035
 brid-0.034
Sleep-0.031
Token on
Token ID319
Feature activation+3.07e-02

Pos logit contributions
aid+0.050
 reins+0.043
 tighter+0.042
 brid+0.039
 scar+0.036
Neg logit contributions
tub-0.046
room-0.046
 site-0.045
 factory-0.045
 port-0.044
Token the
Token ID262
Feature activation-5.46e-03

Pos logit contributions
tub+0.051
room+0.050
 site+0.050
 port+0.049
 factory+0.049
Neg logit contributions
aid-0.058
 reins-0.050
 tighter-0.048
 brid-0.046
 scar-0.043
Token f
Token ID277
Feature activation+1.36e-01

Pos logit contributions
aid+0.012
 reins+0.011
 tighter+0.010
 brid+0.010
Sleep+0.009
Neg logit contributions
tub-0.007
room-0.007
 site-0.007
 port-0.007
 factory-0.007
Tokenauc
Token ID14272
Feature activation+2.33e-01

Pos logit contributions
 port+0.072
 site+0.069
 factory+0.063
 nation+0.059
tub+0.058
Neg logit contributions
aid-0.431
 reins-0.368
 tighter-0.362
 brid-0.345
Sleep-0.338
Tokenet
Token ID316
Feature activation+6.09e-02

Pos logit contributions
 port+0.312
tub+0.310
 site+0.307
 factory+0.300
room+0.299
Neg logit contributions
aid-0.521
 reins-0.446
 tighter-0.440
 brid-0.417
 scar-0.396
Token.
Token ID13
Feature activation+7.61e-04

Pos logit contributions
 site+0.115
 port+0.115
 factory+0.113
tub+0.113
 nation+0.111
Neg logit contributions
aid-0.097
 reins-0.080
 tighter-0.079
 brid-0.072
 scar-0.067
Token They
Token ID1119
Feature activation+2.65e-02

Pos logit contributions
 site+0.001
 factory+0.001
room+0.001
tub+0.001
 port+0.001
Neg logit contributions
aid-0.001
 reins-0.001
 tighter-0.001
 brid-0.001
Sleep-0.001
Token put
Token ID1234
Feature activation-3.85e-02

Pos logit contributions
tub+0.047
 port+0.047
room+0.047
 factory+0.046
 site+0.045
Neg logit contributions
aid-0.047
 reins-0.040
 tighter-0.038
 brid-0.036
Sleep-0.034
Token soap
Token ID19533
Feature activation-2.82e-02

Pos logit contributions
aid+0.073
 reins+0.061
 tighter+0.061
 brid+0.056
 scar+0.053
Neg logit contributions
tub-0.065
 site-0.065
room-0.064
 factory-0.064
 port-0.063
Token kept
Token ID4030
Feature activation-2.85e-02

Pos logit contributions
tub+0.065
room+0.064
 site+0.063
 port+0.063
 factory+0.062
Neg logit contributions
aid-0.070
 reins-0.061
 tighter-0.057
 brid-0.055
Sleep-0.051
Token skipping
Token ID31017
Feature activation-6.92e-04

Pos logit contributions
aid+0.067
 reins+0.056
 tighter+0.053
ache+0.053
 brid+0.052
Neg logit contributions
 port-0.034
ap-0.033
iggle-0.033
room-0.032
 factory-0.032
Token around
Token ID1088
Feature activation+1.05e-01

Pos logit contributions
aid+0.002
 reins+0.001
 tighter+0.001
Dear+0.001
Sleep+0.001
Neg logit contributions
tub-0.001
room-0.001
 port-0.001
 site-0.001
 factory-0.001
Token the
Token ID262
Feature activation-7.48e-03

Pos logit contributions
tub+0.183
room+0.181
 site+0.180
 port+0.177
 factory+0.177
Neg logit contributions
aid-0.189
 reins-0.162
 tighter-0.156
 brid-0.149
 scar-0.137
Token f
Token ID277
Feature activation+1.34e-01

Pos logit contributions
aid+0.016
 reins+0.013
 tighter+0.013
Are+0.013
 brid+0.013
Neg logit contributions
apped-0.010
iggle-0.009
uders-0.009
uttered-0.009
room-0.009
Tokenauc
Token ID14272
Feature activation+2.33e-01

Pos logit contributions
 port+0.108
 nation+0.099
 Fourth+0.094
 structure+0.090
uders+0.089
Neg logit contributions
aid-0.382
 reins-0.286
 tighter-0.284
ache-0.284
paste-0.274
Tokenet
Token ID316
Feature activation+5.87e-02

Pos logit contributions
 port+0.351
 site+0.338
tub+0.336
 factory+0.327
room+0.326
Neg logit contributions
aid-0.489
 tighter-0.407
 reins-0.401
 brid-0.373
 scar-0.363
Token.
Token ID13
Feature activation-4.42e-03

Pos logit contributions
tub+0.101
 site+0.101
 port+0.099
 factory+0.099
room+0.098
Neg logit contributions
aid-0.106
 reins-0.090
 tighter-0.088
 brid-0.082
 scar-0.076
Token Faster
Token ID38996
Feature activation-1.01e-02

Pos logit contributions
aid+0.008
 reins+0.007
 tighter+0.006
 brid+0.006
Sleep+0.006
Neg logit contributions
tub-0.008
 site-0.008
room-0.008
 port-0.008
 factory-0.007
Token and
Token ID290
Feature activation-2.13e-02

Pos logit contributions
aid+0.017
 reins+0.014
 tighter+0.014
 brid+0.013
 scar+0.012
Neg logit contributions
tub-0.019
room-0.019
 site-0.019
 port-0.018
 factory-0.018
Token faster
Token ID5443
Feature activation-4.71e-02

Pos logit contributions
aid+0.027
 reins+0.021
 tighter+0.019
 brid+0.018
Sleep+0.016
Neg logit contributions
tub-0.049
room-0.049
 site-0.048
 factory-0.048
 port-0.048
Token she
Token ID673
Feature activation-1.66e-02

Pos logit contributions
aid+0.079
 reins+0.065
 tighter+0.063
 brid+0.059
 scar+0.054
Neg logit contributions
tub-0.089
 site-0.087
room-0.087
 port-0.086
 factory-0.086
Token skipped
Token ID26684
Feature activation-5.47e-02

Pos logit contributions
aid+0.028
 reins+0.023
 tighter+0.023
 brid+0.022
 scar+0.020
Neg logit contributions
 site-0.031
tub-0.030
room-0.030
 factory-0.030
 port-0.030
Token until
Token ID1566
Feature activation+1.45e-03

Pos logit contributions
aid+0.117
 reins+0.102
 tighter+0.097
 brid+0.094
Sleep+0.089
Neg logit contributions
tub-0.079
room-0.078
 port-0.076
 site-0.076
 factory-0.075
Token the
Token ID262
Feature activation-6.36e-03

Pos logit contributions
tub+0.003
room+0.003
 port+0.003
 factory+0.003
 site+0.003
Neg logit contributions
aid-0.002
 reins-0.002
 tighter-0.002
 brid-0.002
Sleep-0.002
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.012
 reins+0.010
 tighter+0.010
 advice+0.009
 scar+0.009
Neg logit contributions
room-0.010
ook-0.009
ide-0.009
iggle-0.009
 site-0.009
Tokenauc
Token ID14272
Feature activation+2.33e-01

Pos logit contributions
 port+0.132
 nation+0.125
 structure+0.113
 Fourth+0.111
 site+0.107
Neg logit contributions
aid-0.379
ache-0.271
paste-0.267
Dear-0.261
 bleed-0.260
Tokenet
Token ID316
Feature activation+5.93e-02

Pos logit contributions
 port+0.376
tub+0.353
 site+0.351
 factory+0.342
room+0.333
Neg logit contributions
aid-0.482
 tighter-0.385
 reins-0.375
 care-0.355
 brid-0.353
Token was
Token ID373
Feature activation+1.03e-01

Pos logit contributions
 port+0.091
 site+0.090
 factory+0.088
tub+0.086
 nation+0.085
Neg logit contributions
aid-0.116
 tighter-0.094
 reins-0.093
 brid-0.090
 scar-0.088
Token a
Token ID257
Feature activation-2.07e-03

Pos logit contributions
tub+0.176
room+0.173
 site+0.172
 port+0.171
 factory+0.169
Neg logit contributions
aid-0.192
 reins-0.164
 tighter-0.155
 brid-0.150
Sleep-0.138
Token blur
Token ID23671
Feature activation+6.02e-02

Pos logit contributions
aid+0.004
 reins+0.004
 tighter+0.003
 brid+0.003
Sleep+0.003
Neg logit contributions
tub-0.003
 port-0.003
room-0.003
 site-0.003
 factory-0.003
Token of
Token ID286
Feature activation+9.19e-02

Pos logit contributions
tub+0.100
 site+0.100
room+0.099
 factory+0.097
 port+0.097
Neg logit contributions
aid-0.112
 reins-0.094
 tighter-0.093
 brid-0.087
 scar-0.081
Token she
Token ID673
Feature activation-1.84e-02

Pos logit contributions
 site+0.078
tub+0.078
room+0.078
 factory+0.076
 port+0.076
Neg logit contributions
aid-0.066
 reins-0.054
 tighter-0.052
 brid-0.050
 scar-0.045
Token saw
Token ID2497
Feature activation+8.19e-02

Pos logit contributions
aid+0.024
 scar+0.021
 tighter+0.021
Are+0.019
Don+0.019
Neg logit contributions
 site-0.037
room-0.037
ide-0.035
 factory-0.035
 structure-0.035
Token a
Token ID257
Feature activation-8.31e-03

Pos logit contributions
tub+0.155
 site+0.153
room+0.153
 port+0.150
 factory+0.150
Neg logit contributions
aid-0.139
 reins-0.114
 tighter-0.110
 brid-0.104
Sleep-0.096
Token beautiful
Token ID4950
Feature activation+3.88e-02

Pos logit contributions
aid+0.017
 reins+0.015
 tighter+0.014
 brid+0.014
Sleep+0.013
Neg logit contributions
tub-0.013
room-0.012
 site-0.012
 port-0.012
 factory-0.012
Token f
Token ID277
Feature activation+1.33e-01

Pos logit contributions
room+0.070
tub+0.070
 site+0.070
 port+0.068
 factory+0.068
Neg logit contributions
aid-0.066
 reins-0.056
 tighter-0.053
 brid-0.052
 scar-0.047
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.077
 site+0.077
 nation+0.065
 factory+0.062
uders+0.058
Neg logit contributions
aid-0.412
 reins-0.339
 tighter-0.331
ache-0.325
 brid-0.322
Tokenet
Token ID316
Feature activation+5.70e-02

Pos logit contributions
 port+0.346
tub+0.334
 site+0.332
room+0.318
 factory+0.314
Neg logit contributions
aid-0.500
 reins-0.404
 tighter-0.402
 brid-0.381
 bleed-0.372
Token.
Token ID13
Feature activation-4.14e-03

Pos logit contributions
tub+0.098
room+0.097
 site+0.097
 port+0.096
 factory+0.095
Neg logit contributions
aid-0.103
 reins-0.089
 tighter-0.085
 brid-0.081
 scar-0.074
Token
Token ID220
Feature activation-2.68e-02

Pos logit contributions
aid+0.007
 reins+0.006
 tighter+0.006
 brid+0.005
Sleep+0.005
Neg logit contributions
 site-0.008
tub-0.008
room-0.008
 port-0.007
 factory-0.007
Token
Token ID198
Feature activation+3.57e-03

Pos logit contributions
aid+0.043
 reins+0.033
 tighter+0.033
 brid+0.030
Sleep+0.029
Neg logit contributions
 port-0.052
 site-0.052
 factory-0.052
tub-0.051
 nation-0.050
Token
Token ID198
Feature activation+3.19e-03

Pos logit contributions
tub+0.006
room+0.006
 site+0.006
 port+0.006
 factory+0.006
Neg logit contributions
aid-0.007
 reins-0.006
 tighter-0.006
 brid-0.005
Sleep-0.005
Token and
Token ID290
Feature activation-2.00e-02

Pos logit contributions
tub+0.089
room+0.088
 site+0.087
 port+0.086
 factory+0.085
Neg logit contributions
aid-0.154
 reins-0.133
 tighter-0.127
 brid-0.125
Sleep-0.117
Token turned
Token ID2900
Feature activation+7.16e-03

Pos logit contributions
aid+0.040
 reins+0.035
 tighter+0.034
 brid+0.032
Sleep+0.030
Neg logit contributions
tub-0.031
room-0.031
 site-0.030
 port-0.030
 factory-0.030
Token off
Token ID572
Feature activation-6.31e-02

Pos logit contributions
tub+0.010
room+0.010
 site+0.010
 factory+0.010
 port+0.010
Neg logit contributions
aid-0.016
 reins-0.014
 tighter-0.013
 brid-0.013
Sleep-0.012
Token the
Token ID262
Feature activation-1.03e-02

Pos logit contributions
aid+0.120
 reins+0.105
 tighter+0.098
 brid+0.096
Sleep+0.088
Neg logit contributions
room-0.104
tub-0.104
 site-0.103
 factory-0.102
 port-0.101
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.022
 reins+0.019
 tighter+0.018
 brid+0.017
 advice+0.017
Neg logit contributions
room-0.014
 site-0.013
ide-0.013
ook-0.013
tub-0.013
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.111
 nation+0.107
 Fourth+0.099
 structure+0.098
 site+0.097
Neg logit contributions
aid-0.380
 tighter-0.288
ache-0.286
paste-0.281
 reins-0.280
Tokenet
Token ID316
Feature activation+5.85e-02

Pos logit contributions
 port+0.341
tub+0.328
 site+0.325
room+0.320
 factory+0.314
Neg logit contributions
aid-0.499
 tighter-0.417
 reins-0.409
 brid-0.379
 care-0.374
Token for
Token ID329
Feature activation+2.13e-02

Pos logit contributions
 site+0.106
 port+0.106
tub+0.105
 factory+0.103
 nation+0.103
Neg logit contributions
aid-0.097
 tighter-0.079
 reins-0.079
 brid-0.070
 scar-0.068
Token her
Token ID607
Feature activation-7.47e-02

Pos logit contributions
room+0.034
tub+0.034
 site+0.033
 port+0.033
 factory+0.033
Neg logit contributions
aid-0.042
 reins-0.037
 tighter-0.034
 brid-0.034
Sleep-0.030
Token.
Token ID13
Feature activation-3.17e-03

Pos logit contributions
aid+0.133
 reins+0.114
 tighter+0.108
 brid+0.104
Sleep+0.095
Neg logit contributions
tub-0.133
room-0.132
 site-0.129
 factory-0.129
 port-0.129
Token Lily
Token ID20037
Feature activation+2.74e-02

Pos logit contributions
aid+0.005
 tighter+0.004
 reins+0.004
 brid+0.003
Sleep+0.003
Neg logit contributions
 site-0.006
room-0.006
 port-0.006
tub-0.006
 nation-0.006
Token They
Token ID1119
Feature activation+2.75e-02

Pos logit contributions
aid+0.001
 tighter+0.001
 reins+0.001
 brid+0.001
Sleep+0.001
Neg logit contributions
 site-0.001
tub-0.001
room-0.001
iggle-0.001
aded-0.001
Token turned
Token ID2900
Feature activation+9.80e-03

Pos logit contributions
tub+0.049
 site+0.048
 factory+0.048
room+0.047
 port+0.047
Neg logit contributions
aid-0.050
 tighter-0.042
 reins-0.041
 brid-0.039
 scar-0.037
Token on
Token ID319
Feature activation+2.94e-02

Pos logit contributions
tub+0.016
room+0.016
 port+0.016
 site+0.016
 factory+0.016
Neg logit contributions
aid-0.019
 reins-0.016
 tighter-0.015
 brid-0.015
Sleep-0.014
Token the
Token ID262
Feature activation+1.95e-04

Pos logit contributions
tub+0.052
room+0.052
 site+0.051
 port+0.050
 factory+0.050
Neg logit contributions
aid-0.052
 reins-0.045
 tighter-0.043
 brid-0.041
Sleep-0.037
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
tub+0.000
 factory+0.000
 port+0.000
 site+0.000
room+0.000
Neg logit contributions
aid-0.000
 reins-0.000
 tighter-0.000
 brid-0.000
Sleep-0.000
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.106
 site+0.105
 factory+0.100
tub+0.099
room+0.096
Neg logit contributions
aid-0.381
 reins-0.329
 tighter-0.323
 brid-0.309
Sleep-0.297
Tokenet
Token ID316
Feature activation+5.93e-02

Pos logit contributions
 port+0.312
tub+0.312
 site+0.303
room+0.299
 factory+0.298
Neg logit contributions
aid-0.519
 reins-0.444
 tighter-0.439
 brid-0.416
 scar-0.392
Token and
Token ID290
Feature activation-1.65e-02

Pos logit contributions
tub+0.113
 port+0.112
 site+0.112
 factory+0.110
room+0.109
Neg logit contributions
aid-0.093
 reins-0.077
 tighter-0.076
 brid-0.069
 bud-0.063
Token ran
Token ID4966
Feature activation+2.23e-03

Pos logit contributions
aid+0.031
 tighter+0.026
 reins+0.025
 brid+0.024
 scar+0.023
Neg logit contributions
room-0.029
tub-0.028
 site-0.028
 factory-0.028
 port-0.027
Token some
Token ID617
Feature activation+1.77e-02

Pos logit contributions
tub+0.004
room+0.004
 port+0.004
 site+0.004
 factory+0.004
Neg logit contributions
aid-0.004
 reins-0.003
 brid-0.003
 tighter-0.003
Sleep-0.003
Token water
Token ID1660
Feature activation+3.54e-02

Pos logit contributions
tub+0.028
room+0.028
 site+0.027
 factory+0.027
 port+0.027
Neg logit contributions
aid-0.035
 reins-0.030
 tighter-0.029
 brid-0.028
 scar-0.026
Token.
Token ID13
Feature activation+8.92e-04

Pos logit contributions
tub+0.168
room+0.165
 site+0.164
 factory+0.162
 port+0.161
Neg logit contributions
aid-0.189
 reins-0.163
 tighter-0.154
 brid-0.150
Sleep-0.138
Token They
Token ID1119
Feature activation+2.81e-02

Pos logit contributions
aded+0.001
 site+0.001
iggle+0.001
ide+0.001
room+0.001
Neg logit contributions
aid-0.002
 reins-0.001
 tighter-0.001
Do-0.001
 brid-0.001
Token opened
Token ID4721
Feature activation-9.59e-03

Pos logit contributions
tub+0.050
 site+0.050
 factory+0.050
room+0.050
 port+0.049
Neg logit contributions
aid-0.051
 tighter-0.041
 reins-0.040
 brid-0.040
 scar-0.037
Token the
Token ID262
Feature activation-2.02e-03

Pos logit contributions
aid+0.016
 reins+0.014
 tighter+0.014
 brid+0.013
 scar+0.012
Neg logit contributions
tub-0.018
room-0.017
 site-0.017
 factory-0.017
 port-0.017
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.005
 reins+0.004
 tighter+0.004
 brid+0.004
Sleep+0.004
Neg logit contributions
 factory-0.002
tub-0.002
 port-0.002
 site-0.002
room-0.002
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.080
 site+0.075
 factory+0.072
tub+0.071
 nation+0.071
Neg logit contributions
aid-0.415
 reins-0.357
 tighter-0.348
 brid-0.335
ache-0.323
Tokenet
Token ID316
Feature activation+6.02e-02

Pos logit contributions
tub+0.297
room+0.291
 port+0.291
 site+0.289
 factory+0.283
Neg logit contributions
aid-0.533
 reins-0.465
 tighter-0.454
 brid-0.435
 scar-0.409
Token and
Token ID290
Feature activation-1.49e-02

Pos logit contributions
tub+0.115
 site+0.113
room+0.113
 port+0.113
 factory+0.112
Neg logit contributions
aid-0.097
 reins-0.082
 tighter-0.078
 brid-0.073
 scar-0.066
Token put
Token ID1234
Feature activation-3.80e-02

Pos logit contributions
aid+0.028
 tighter+0.024
 reins+0.023
 brid+0.022
 scar+0.021
Neg logit contributions
room-0.026
 site-0.025
tub-0.025
 factory-0.025
iggle-0.024
Token their
Token ID511
Feature activation+2.86e-03

Pos logit contributions
aid+0.070
 reins+0.059
 tighter+0.059
 brid+0.055
 scar+0.051
Neg logit contributions
tub-0.065
 site-0.065
room-0.064
 factory-0.063
 port-0.063
Token letters
Token ID7475
Feature activation-9.60e-02

Pos logit contributions
tub+0.005
room+0.005
 site+0.005
 factory+0.005
 port+0.005
Neg logit contributions
aid-0.005
 reins-0.005
 tighter-0.004
 brid-0.004
 scar-0.004
Token she
Token ID673
Feature activation-1.65e-02

Pos logit contributions
aid+0.119
 reins+0.094
 tighter+0.092
 brid+0.084
 scar+0.077
Neg logit contributions
tub-0.192
room-0.192
 site-0.191
 factory-0.186
 port-0.186
Token turned
Token ID2900
Feature activation+6.56e-03

Pos logit contributions
aid+0.025
 tighter+0.019
 care+0.018
 reins+0.017
Sleep+0.017
Neg logit contributions
 site-0.034
room-0.034
tub-0.033
 port-0.033
uders-0.033
Token on
Token ID319
Feature activation+2.48e-02

Pos logit contributions
tub+0.011
 port+0.011
room+0.010
 factory+0.010
 site+0.010
Neg logit contributions
aid-0.012
 reins-0.011
 tighter-0.010
 brid-0.010
Sleep-0.009
Token the
Token ID262
Feature activation-9.70e-03

Pos logit contributions
 site+0.039
 factory+0.039
tub+0.038
room+0.038
 port+0.038
Neg logit contributions
aid-0.050
 reins-0.043
 tighter-0.040
 brid-0.039
Dear-0.037
Token f
Token ID277
Feature activation+1.34e-01

Pos logit contributions
aid+0.021
 reins+0.018
 tighter+0.017
 brid+0.017
 scar+0.016
Neg logit contributions
room-0.014
 site-0.013
tub-0.013
 port-0.013
 factory-0.013
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.099
 nation+0.091
 site+0.089
 Fourth+0.085
 structure+0.075
Neg logit contributions
aid-0.406
 reins-0.311
 tighter-0.309
ache-0.308
Sleep-0.302
Tokenet
Token ID316
Feature activation+5.89e-02

Pos logit contributions
 port+0.321
tub+0.316
 site+0.312
room+0.306
 factory+0.301
Neg logit contributions
aid-0.515
 reins-0.436
 tighter-0.432
 brid-0.407
 scar-0.388
Token,
Token ID11
Feature activation+4.39e-02

Pos logit contributions
 site+0.099
agically+0.097
 port+0.097
 nation+0.096
undle+0.096
Neg logit contributions
aid-0.101
 reins-0.082
 tighter-0.081
 bud-0.077
 scar-0.074
Token no
Token ID645
Feature activation+5.50e-04

Pos logit contributions
tub+0.085
room+0.083
 port+0.083
 factory+0.082
 site+0.082
Neg logit contributions
aid-0.072
 reins-0.061
 tighter-0.056
 brid-0.054
Sleep-0.050
Token water
Token ID1660
Feature activation+3.32e-02

Pos logit contributions
tub+0.001
room+0.001
 site+0.001
 factory+0.001
 port+0.001
Neg logit contributions
aid-0.001
 reins-0.001
 tighter-0.001
 brid-0.001
 scar-0.001
Token came
Token ID1625
Feature activation+6.83e-02

Pos logit contributions
 site+0.053
room+0.052
 port+0.052
 factory+0.050
 nation+0.050
Neg logit contributions
aid-0.059
 reins-0.050
 tighter-0.049
 bud-0.046
 bleed-0.046
Token other
Token ID584
Feature activation+2.42e-02

Pos logit contributions
aid+0.018
 reins+0.015
 tighter+0.014
 brid+0.014
 bud+0.013
Neg logit contributions
room-0.015
 site-0.015
tub-0.014
apped-0.014
iggle-0.014
Token plants
Token ID6134
Feature activation+3.74e-02

Pos logit contributions
room+0.045
iggle+0.045
undle+0.044
tub+0.043
 site+0.043
Neg logit contributions
aid-0.034
 bud-0.028
 care-0.028
 reins-0.027
 advice-0.027
Token."
Token ID526
Feature activation-1.83e-02

Pos logit contributions
tub+0.065
room+0.064
 port+0.063
 site+0.063
 factory+0.063
Neg logit contributions
aid-0.068
 reins-0.058
 tighter-0.055
 brid-0.054
Sleep-0.048
Token The
Token ID383
Feature activation+7.25e-03

Pos logit contributions
aid+0.032
 reins+0.025
 tighter+0.025
 care+0.024
 advice+0.024
Neg logit contributions
tub-0.032
 port-0.031
auc-0.031
iced-0.030
 site-0.030
Token f
Token ID277
Feature activation+1.36e-01

Pos logit contributions
room+0.012
 site+0.011
tub+0.011
undle+0.011
iggle+0.011
Neg logit contributions
aid-0.014
 reins-0.011
 tighter-0.011
 bud-0.011
 advice-0.010
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.130
 Fourth+0.114
 site+0.104
 nation+0.094
 factory+0.091
Neg logit contributions
aid-0.394
ache-0.287
 bleed-0.287
 bud-0.283
Dear-0.280
Tokenet
Token ID316
Feature activation+5.99e-02

Pos logit contributions
 port+0.329
tub+0.320
 site+0.317
 factory+0.308
room+0.307
Neg logit contributions
aid-0.519
 reins-0.430
 tighter-0.428
 brid-0.402
 bleed-0.385
Token said
Token ID531
Feature activation+6.81e-02

Pos logit contributions
 port+0.101
tub+0.099
 site+0.099
room+0.098
 factory+0.097
Neg logit contributions
aid-0.112
 tighter-0.091
 reins-0.089
 brid-0.085
 scar-0.081
Token,
Token ID11
Feature activation+4.40e-02

Pos logit contributions
tub+0.086
room+0.086
 site+0.084
 factory+0.082
 port+0.082
Neg logit contributions
aid-0.156
 reins-0.140
 tighter-0.133
 brid-0.130
Sleep-0.122
Token "
Token ID366
Feature activation-1.09e-02

Pos logit contributions
tub+0.066
room+0.064
 site+0.064
 factory+0.063
 port+0.063
Neg logit contributions
aid-0.092
 reins-0.079
 tighter-0.076
 brid-0.073
Sleep-0.068
TokenYes
Token ID5297
Feature activation-2.07e-02

Pos logit contributions
aid+0.016
 reins+0.015
 tighter+0.013
 severe+0.013
 bleed+0.013
Neg logit contributions
room-0.021
tub-0.020
 site-0.019
 factory-0.019
 port-0.019
Token careful
Token ID8161
Feature activation-8.28e-02

Pos logit contributions
aid+0.209
 reins+0.209
 brid+0.179
 tighter+0.167
 bud+0.165
Neg logit contributions
room-0.219
tub-0.214
ap-0.214
aded-0.210
 site-0.205
Token with
Token ID351
Feature activation+1.34e-01

Pos logit contributions
aid+0.157
 reins+0.138
 brid+0.127
 tighter+0.126
 scar+0.116
Neg logit contributions
room-0.139
tub-0.138
 site-0.135
 factory-0.132
 port-0.130
Token spiders
Token ID26120
Feature activation+3.37e-02

Pos logit contributions
tub+0.236
room+0.232
 site+0.231
 port+0.228
 factory+0.227
Neg logit contributions
aid-0.241
 reins-0.206
 tighter-0.199
 brid-0.188
 scar-0.174
Token and
Token ID290
Feature activation-1.69e-02

Pos logit contributions
tub+0.056
room+0.055
 site+0.055
 factory+0.054
 port+0.054
Neg logit contributions
aid-0.064
 reins-0.055
 tighter-0.052
 brid-0.051
Sleep-0.046
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.029
 reins+0.026
 tighter+0.024
 brid+0.023
Sleep+0.021
Neg logit contributions
tub-0.029
 port-0.028
 factory-0.028
 site-0.028
room-0.028
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 site+0.167
 port+0.166
tub+0.164
 factory+0.163
room+0.158
Neg logit contributions
aid-0.328
 reins-0.280
 tighter-0.271
 brid-0.259
 bleed-0.247
Tokenets
Token ID1039
Feature activation+1.45e-02

Pos logit contributions
room+0.322
tub+0.316
 factory+0.302
 site+0.302
auc+0.296
Neg logit contributions
aid-0.486
 reins-0.450
 tighter-0.420
 brid-0.415
Sleep-0.386
Token.
Token ID13
Feature activation+1.76e-04

Pos logit contributions
room+0.023
tub+0.023
 site+0.023
 factory+0.022
 port+0.022
Neg logit contributions
aid-0.028
 reins-0.025
 tighter-0.023
 brid-0.023
 scar-0.021
Token
Token ID198
Feature activation+6.40e-03

Pos logit contributions
tub+0.000
room+0.000
 site+0.000
 factory+0.000
 port+0.000
Neg logit contributions
aid-0.000
 reins-0.000
 tighter-0.000
 brid-0.000
Sleep-0.000
Token
Token ID198
Feature activation+6.68e-03

Pos logit contributions
tub+0.011
room+0.011
 site+0.011
 port+0.011
 factory+0.011
Neg logit contributions
aid-0.012
 reins-0.010
 tighter-0.010
 brid-0.009
Sleep-0.008
TokenShe
Token ID3347
Feature activation-1.28e-01

Pos logit contributions
room+0.012
 site+0.012
 factory+0.012
tub+0.011
 port+0.011
Neg logit contributions
aid-0.011
 reins-0.010
 brid-0.009
 bleed-0.009
 tighter-0.009
Token him
Token ID683
Feature activation+5.53e-02

Pos logit contributions
aid+0.075
 reins+0.065
 tighter+0.063
 brid+0.059
 scar+0.054
Neg logit contributions
tub-0.071
room-0.069
 site-0.069
 factory-0.068
 port-0.068
Token,
Token ID11
Feature activation+4.23e-02

Pos logit contributions
tub+0.100
 site+0.099
room+0.099
 port+0.099
 factory+0.097
Neg logit contributions
aid-0.092
 reins-0.079
 tighter-0.078
 brid-0.072
 scar-0.067
Token with
Token ID351
Feature activation+1.29e-01

Pos logit contributions
tub+0.079
room+0.079
 site+0.077
 port+0.077
 factory+0.076
Neg logit contributions
aid-0.070
 reins-0.060
 tighter-0.058
 brid-0.055
 scar-0.050
Token many
Token ID867
Feature activation-3.48e-03

Pos logit contributions
tub+0.234
room+0.230
 site+0.228
 factory+0.221
 port+0.221
Neg logit contributions
aid-0.227
 reins-0.195
 tighter-0.187
 brid-0.178
 scar-0.165
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.006
 reins+0.006
 tighter+0.005
 brid+0.005
 scar+0.005
Neg logit contributions
room-0.006
tub-0.006
 site-0.006
 port-0.005
 factory-0.005
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 site+0.122
 port+0.118
 factory+0.114
 nation+0.109
room+0.107
Neg logit contributions
aid-0.372
 reins-0.315
 tighter-0.301
 brid-0.290
ache-0.286
Tokenets
Token ID1039
Feature activation+1.47e-02

Pos logit contributions
tub+0.313
 port+0.312
 site+0.311
room+0.303
 factory+0.300
Neg logit contributions
aid-0.520
 reins-0.447
 tighter-0.434
 brid-0.415
 scar-0.395
Token and
Token ID290
Feature activation-2.03e-02

Pos logit contributions
tub+0.026
room+0.026
 site+0.025
 port+0.025
 factory+0.025
Neg logit contributions
aid-0.025
 reins-0.021
 tighter-0.020
 brid-0.019
Sleep-0.018
Token a
Token ID257
Feature activation-4.11e-03

Pos logit contributions
aid+0.039
 reins+0.034
 tighter+0.033
 brid+0.031
 scar+0.029
Neg logit contributions
room-0.032
tub-0.032
 site-0.032
 port-0.031
 factory-0.031
Token big
Token ID1263
Feature activation+8.59e-02

Pos logit contributions
aid+0.009
 reins+0.008
 tighter+0.007
 brid+0.007
 scar+0.006
Neg logit contributions
tub-0.006
room-0.006
 site-0.006
 factory-0.006
 port-0.006
Token knob
Token ID36842
Feature activation-1.20e-02

Pos logit contributions
room+0.129
tub+0.129
 site+0.127
 port+0.123
 factory+0.123
Neg logit contributions
aid-0.173
 reins-0.152
 tighter-0.146
 brid-0.141
 scar-0.131
Token of
Token ID286
Feature activation+8.96e-02

Pos logit contributions
aid+0.023
 tighter+0.020
 reins+0.019
 brid+0.018
Sleep+0.017
Neg logit contributions
 site-0.021
 port-0.020
room-0.020
 factory-0.020
tub-0.020
Token water
Token ID1660
Feature activation+3.27e-02

Pos logit contributions
tub+0.149
room+0.145
 port+0.144
 site+0.144
 factory+0.144
Neg logit contributions
aid-0.169
 reins-0.147
 tighter-0.139
 brid-0.135
Sleep-0.122
Token from
Token ID422
Feature activation+4.55e-02

Pos logit contributions
 site+0.062
room+0.061
 port+0.060
 factory+0.060
tub+0.060
Neg logit contributions
aid-0.053
 tighter-0.044
 reins-0.044
 brid-0.040
 scar-0.037
Token the
Token ID262
Feature activation-1.19e-02

Pos logit contributions
tub+0.091
room+0.091
 site+0.090
 port+0.089
 factory+0.088
Neg logit contributions
aid-0.070
 reins-0.058
 tighter-0.056
 brid-0.052
 scar-0.047
Token f
Token ID277
Feature activation+1.34e-01

Pos logit contributions
aid+0.025
 reins+0.021
 tighter+0.021
 brid+0.020
Sleep+0.018
Neg logit contributions
tub-0.018
room-0.018
 site-0.017
 factory-0.017
 port-0.017
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.091
 site+0.087
 nation+0.079
 factory+0.078
room+0.074
Neg logit contributions
aid-0.406
 reins-0.341
 tighter-0.336
Sleep-0.320
ache-0.319
Tokenet
Token ID316
Feature activation+5.82e-02

Pos logit contributions
tub+0.302
 port+0.300
 site+0.299
room+0.297
 factory+0.289
Neg logit contributions
aid-0.527
 reins-0.456
 tighter-0.447
 brid-0.424
 scar-0.403
Token.
Token ID13
Feature activation-3.08e-03

Pos logit contributions
 site+0.105
 port+0.104
room+0.103
tub+0.102
 factory+0.102
Neg logit contributions
aid-0.099
 reins-0.083
 tighter-0.081
 brid-0.075
 scar-0.070
Token
Token ID198
Feature activation+4.73e-03

Pos logit contributions
aid+0.005
 reins+0.004
 tighter+0.004
 brid+0.004
Sleep+0.004
Neg logit contributions
 site-0.006
 port-0.006
tub-0.006
room-0.006
 factory-0.006
Token
Token ID198
Feature activation+4.74e-03

Pos logit contributions
tub+0.009
 factory+0.009
 port+0.009
 site+0.009
room+0.009
Neg logit contributions
aid-0.007
 reins-0.006
 tighter-0.006
 brid-0.005
Sleep-0.005
TokenWhen
Token ID2215
Feature activation-8.78e-02

Pos logit contributions
tub+0.010
room+0.010
 site+0.010
 port+0.009
 factory+0.009
Neg logit contributions
aid-0.007
 reins-0.006
 tighter-0.006
 brid-0.005
Sleep-0.005
Token the
Token ID262
Feature activation-3.48e-03

Pos logit contributions
aid+0.135
 reins+0.128
 brid+0.116
 tighter+0.109
Sleep+0.109
Neg logit contributions
room-0.081
 factory-0.079
tub-0.076
 port-0.076
 site-0.075
Token stove
Token ID27635
Feature activation+1.39e-01

Pos logit contributions
aid+0.009
 reins+0.008
 tighter+0.007
 brid+0.007
Sleep+0.007
Neg logit contributions
tub-0.004
 factory-0.004
 port-0.004
 site-0.004
room-0.004
Token and
Token ID290
Feature activation-1.68e-02

Pos logit contributions
tub+0.243
room+0.241
 site+0.239
 factory+0.237
 port+0.236
Neg logit contributions
aid-0.252
 reins-0.215
 tighter-0.203
 brid-0.197
Sleep-0.180
Token the
Token ID262
Feature activation-3.18e-03

Pos logit contributions
aid+0.031
 reins+0.027
 tighter+0.026
 brid+0.025
 scar+0.023
Neg logit contributions
tub-0.028
room-0.028
 site-0.028
 port-0.028
 factory-0.027
Token f
Token ID277
Feature activation+1.35e-01

Pos logit contributions
aid+0.007
 reins+0.007
 tighter+0.006
 brid+0.006
Sleep+0.006
Neg logit contributions
tub-0.004
 site-0.004
 factory-0.004
room-0.004
 port-0.004
Tokenauc
Token ID14272
Feature activation+2.32e-01

Pos logit contributions
 port+0.102
 nation+0.092
 structure+0.085
 site+0.085
 factory+0.082
Neg logit contributions
aid-0.411
ache-0.324
 reins-0.321
 bleed-0.320
 tighter-0.319
Tokenet
Token ID316
Feature activation+5.99e-02

Pos logit contributions
 port+0.318
tub+0.313
 site+0.308
room+0.303
 factory+0.301
Neg logit contributions
aid-0.519
 reins-0.439
 tighter-0.435
 brid-0.410
 bleed-0.393
Token.
Token ID13
Feature activation-1.56e-03

Pos logit contributions
 port+0.108
 site+0.108
tub+0.107
 factory+0.106
room+0.106
Neg logit contributions
aid-0.103
 reins-0.084
 tighter-0.083
 brid-0.076
 scar-0.071
Token She
Token ID1375
Feature activation-6.08e-02

Pos logit contributions
aid+0.003
 reins+0.002
 tighter+0.002
 brid+0.002
Sleep+0.002
Neg logit contributions
tub-0.003
room-0.003
 site-0.003
 factory-0.003
 port-0.003
Token picked
Token ID6497
Feature activation-5.45e-02

Pos logit contributions
aid+0.112
 tighter+0.091
 reins+0.091
 brid+0.086
 scar+0.081
Neg logit contributions
tub-0.109
room-0.108
 site-0.108
 port-0.107
 factory-0.106
Token up
Token ID510
Feature activation+1.48e-01

Pos logit contributions
aid+0.127
 tighter+0.112
 reins+0.110
 brid+0.102
 bleed+0.098
Neg logit contributions
 site-0.070
tub-0.068
 port-0.067
 factory-0.067
 nation-0.065
Token quickly
Token ID2952
Feature activation-9.62e-03

Pos logit contributions
tub+0.089
 port+0.087
room+0.087
 site+0.086
 factory+0.085
Neg logit contributions
aid-0.121
 reins-0.103
 tighter-0.103
 brid-0.097
 scar-0.091
Token grabbed
Token ID13176
Feature activation-1.79e-02

Pos logit contributions
aid+0.018
 reins+0.014
 tighter+0.014
 brid+0.013
 scar+0.012
Neg logit contributions
tub-0.017
room-0.017
 site-0.017
 port-0.017
 factory-0.017
Token a
Token ID257
Feature activation-2.05e-02

Pos logit contributions
aid+0.031
 reins+0.026
 tighter+0.025
 brid+0.024
 scar+0.022
Neg logit contributions
tub-0.033
room-0.033
 site-0.033
 factory-0.032
 port-0.032
Token band
Token ID4097
Feature activation-8.89e-02

Pos logit contributions
aid+0.040
 reins+0.035
 tighter+0.033
Sleep+0.032
 brid+0.032
Neg logit contributions
tub-0.031
 port-0.030
room-0.030
 factory-0.030
 site-0.029
Token-
Token ID12
Feature activation+1.39e-02

Pos logit contributions
aid+0.186
 reins+0.171
 tighter+0.162
 brid+0.155
Sleep+0.152
Neg logit contributions
room-0.126
tub-0.120
 site-0.118
 factory-0.116
 port-0.113
Tokenaid
Token ID1698
Feature activation-3.15e-01

Pos logit contributions
room+0.042
auc+0.040
ook+0.039
iced+0.039
apped+0.039
Neg logit contributions
 reins-0.004
aid-0.002
 brid-0.001
 scar-0.001
 tighter-0.001
Token and
Token ID290
Feature activation-3.38e-02

Pos logit contributions
aid+0.569
 reins+0.490
 tighter+0.454
 brid+0.444
Sleep+0.421
Neg logit contributions
tub-0.543
room-0.541
 site-0.531
 factory-0.524
 port-0.523
Token helped
Token ID4193
Feature activation-4.82e-02

Pos logit contributions
aid+0.064
 reins+0.054
 tighter+0.052
 brid+0.050
 scar+0.046
Neg logit contributions
tub-0.057
room-0.057
 site-0.056
 factory-0.055
 port-0.055
Token Tim
Token ID5045
Feature activation+1.35e-01

Pos logit contributions
aid+0.079
 tighter+0.064
 reins+0.064
 brid+0.058
 bleed+0.055
Neg logit contributions
tub-0.096
 site-0.093
 port-0.092
 factory-0.092
room-0.090
Tokenmy
Token ID1820
Feature activation-9.32e-02

Pos logit contributions
room+0.257
tub+0.247
 factory+0.239
iggle+0.236
iced+0.235
Neg logit contributions
aid-0.218
 reins-0.197
 brid-0.183
 tighter-0.170
Sleep-0.167
Token put
Token ID1234
Feature activation-5.66e-02

Pos logit contributions
aid+0.166
 reins+0.143
 tighter+0.135
 brid+0.130
Sleep+0.120
Neg logit contributions
tub-0.164
room-0.163
 site-0.161
 factory-0.159
 port-0.159
Token gave
Token ID2921
Feature activation-2.88e-03

Pos logit contributions
aid+0.064
 reins+0.056
 tighter+0.052
 brid+0.051
Sleep+0.046
Neg logit contributions
tub-0.063
room-0.061
 site-0.061
 factory-0.061
 port-0.060
Token Lily
Token ID20037
Feature activation+8.65e-03

Pos logit contributions
aid+0.005
 tighter+0.004
 reins+0.004
 brid+0.004
 care+0.003
Neg logit contributions
tub-0.005
 site-0.005
 port-0.005
room-0.005
 factory-0.005
Token a
Token ID257
Feature activation-2.58e-02

Pos logit contributions
tub+0.012
room+0.012
 port+0.011
 factory+0.011
 site+0.011
Neg logit contributions
aid-0.017
 reins-0.016
 brid-0.014
 bud-0.014
 tighter-0.014
Token band
Token ID4097
Feature activation-8.81e-02

Pos logit contributions
aid+0.042
 reins+0.037
 tighter+0.035
 brid+0.033
Sleep+0.032
Neg logit contributions
tub-0.046
 port-0.045
 factory-0.043
room-0.043
 site-0.041
Token-
Token ID12
Feature activation+1.18e-02

Pos logit contributions
 reins+0.144
aid+0.141
 tighter+0.141
 bud+0.128
 fiber+0.124
Neg logit contributions
room-0.146
tub-0.142
apped-0.135
ap-0.132
 nation-0.126
Tokenaid
Token ID1698
Feature activation-3.15e-01

Pos logit contributions
room+0.035
auc+0.034
apped+0.033
tub+0.032
aded+0.032
Neg logit contributions
 reins-0.003
 bud-0.002
 tighter-0.002
 brid-0.001
 scar-0.001
Token for
Token ID329
Feature activation+4.54e-03

Pos logit contributions
aid+0.603
 reins+0.568
 tighter+0.512
 brid+0.512
Are+0.504
Neg logit contributions
tub-0.464
room-0.450
apped-0.427
auc-0.420
 factory-0.408
Token her
Token ID607
Feature activation-9.62e-02

Pos logit contributions
room+0.007
tub+0.007
 site+0.007
 factory+0.007
 port+0.007
Neg logit contributions
aid-0.008
 reins-0.007
 tighter-0.007
 brid-0.007
Dear-0.006
Token knee
Token ID10329
Feature activation-8.69e-02

Pos logit contributions
aid+0.192
 reins+0.168
 tighter+0.161
 brid+0.155
Sleep+0.144
Neg logit contributions
tub-0.146
room-0.139
 factory-0.138
 port-0.136
 site-0.134
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
aid+0.182
 reins+0.170
 tighter+0.154
 brid+0.153
Sleep+0.143
Neg logit contributions
tub-0.123
room-0.116
 factory-0.109
 site-0.108
 port-0.104
Token She
Token ID1375
Feature activation-8.16e-02

Pos logit contributions
aid+0.027
 reins+0.023
 tighter+0.023
 brid+0.022
Sleep+0.021
Neg logit contributions
tub-0.018
room-0.018
 site-0.018
 port-0.018
 factory-0.018
Token doctor
Token ID6253
Feature activation-1.90e-02

Pos logit contributions
room+0.020
tub+0.020
 site+0.020
 port+0.020
 factory+0.020
Neg logit contributions
aid-0.025
 reins-0.022
 tighter-0.021
 brid-0.020
 scar-0.018
Token put
Token ID1234
Feature activation-4.47e-02

Pos logit contributions
aid+0.035
 reins+0.030
 tighter+0.029
 brid+0.028
 scar+0.026
Neg logit contributions
tub-0.032
room-0.031
 site-0.031
 port-0.031
 factory-0.030
Token a
Token ID257
Feature activation-1.40e-02

Pos logit contributions
aid+0.077
 reins+0.065
 tighter+0.063
 brid+0.059
 scar+0.054
Neg logit contributions
tub-0.083
 site-0.082
room-0.081
 port-0.081
 factory-0.080
Token band
Token ID4097
Feature activation-8.49e-02

Pos logit contributions
aid+0.025
 reins+0.022
 tighter+0.021
 brid+0.020
Sleep+0.019
Neg logit contributions
tub-0.024
room-0.023
 site-0.023
 port-0.023
 factory-0.023
Token-
Token ID12
Feature activation+1.72e-02

Pos logit contributions
aid+0.164
 reins+0.148
 tighter+0.142
 brid+0.134
Sleep+0.130
Neg logit contributions
tub-0.132
room-0.132
 site-0.124
 port-0.123
 factory-0.123
Tokenaid
Token ID1698
Feature activation-3.15e-01

Pos logit contributions
room+0.050
auc+0.050
aded+0.048
apped+0.047
tub+0.047
Neg logit contributions
 reins-0.004
aid-0.003
 brid-0.003
 bud-0.002
 tighter-0.001
Token on
Token ID319
Feature activation+8.12e-03

Pos logit contributions
aid+0.587
 reins+0.515
 tighter+0.477
 brid+0.467
Sleep+0.445
Neg logit contributions
tub-0.525
room-0.512
 site-0.496
 port-0.491
 factory-0.489
Token her
Token ID607
Feature activation-9.59e-02

Pos logit contributions
tub+0.015
 site+0.014
room+0.014
 port+0.014
 factory+0.014
Neg logit contributions
aid-0.014
 reins-0.012
 tighter-0.011
 brid-0.011
 scar-0.010
Token arm
Token ID3211
Feature activation-6.39e-02

Pos logit contributions
aid+0.181
 reins+0.153
 tighter+0.147
 brid+0.140
Sleep+0.133
Neg logit contributions
tub-0.160
room-0.157
 site-0.156
 port-0.154
 factory-0.154
Token.
Token ID13
Feature activation-8.98e-03

Pos logit contributions
aid+0.123
 reins+0.107
 tighter+0.102
 brid+0.098
Sleep+0.091
Neg logit contributions
tub-0.104
room-0.102
 site-0.101
 factory-0.099
 port-0.098
Token He
Token ID679
Feature activation-3.99e-02

Pos logit contributions
aid+0.016
 reins+0.014
 tighter+0.013
 brid+0.013
Sleep+0.012
Neg logit contributions
tub-0.016
room-0.015
 site-0.015
 port-0.015
 factory-0.015
Token He
Token ID679
Feature activation-3.11e-02

Pos logit contributions
 site+0.002
room+0.002
tub+0.002
 port+0.002
 factory+0.002
Neg logit contributions
aid-0.002
 reins-0.001
 tighter-0.001
 brid-0.001
Sleep-0.001
Token liked
Token ID8288
Feature activation+3.27e-03

Pos logit contributions
aid+0.054
 tighter+0.045
 reins+0.045
 brid+0.044
 scar+0.040
Neg logit contributions
room-0.057
tub-0.057
 site-0.056
 factory-0.055
 port-0.055
Token the
Token ID262
Feature activation-2.10e-02

Pos logit contributions
tub+0.006
room+0.006
 site+0.006
 factory+0.006
 port+0.006
Neg logit contributions
aid-0.006
 reins-0.005
 tighter-0.004
 brid-0.004
Sleep-0.004
Token band
Token ID4097
Feature activation-8.50e-02

Pos logit contributions
aid+0.041
 reins+0.035
 tighter+0.034
 brid+0.033
Sleep+0.030
Neg logit contributions
tub-0.034
room-0.033
 factory-0.033
 site-0.033
 port-0.033
Token-
Token ID12
Feature activation+1.53e-02

Pos logit contributions
aid+0.161
 reins+0.139
 tighter+0.133
 brid+0.128
Sleep+0.118
Neg logit contributions
tub-0.140
room-0.139
 site-0.138
 factory-0.136
 port-0.136
Tokenaid
Token ID1698
Feature activation-3.14e-01

Pos logit contributions
room+0.040
tub+0.038
auc+0.038
 site+0.038
 factory+0.037
Neg logit contributions
 reins-0.012
aid-0.011
 brid-0.009
 tighter-0.009
 scar-0.008
Token and
Token ID290
Feature activation-3.51e-02

Pos logit contributions
aid+0.577
 reins+0.498
 tighter+0.471
 brid+0.454
Sleep+0.419
Neg logit contributions
tub-0.536
room-0.531
 site-0.525
 factory-0.519
 port-0.518
Token the
Token ID262
Feature activation-2.34e-02

Pos logit contributions
aid+0.069
 reins+0.063
 tighter+0.058
 brid+0.055
Sleep+0.053
Neg logit contributions
tub-0.052
 factory-0.052
 port-0.052
 site-0.051
room-0.050
Token dinosaur
Token ID28257
Feature activation+5.53e-02

Pos logit contributions
aid+0.045
 reins+0.038
 tighter+0.037
 brid+0.035
Sleep+0.033
Neg logit contributions
 factory-0.038
tub-0.037
 port-0.037
 site-0.036
room-0.036
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
tub+0.091
room+0.091
 site+0.090
 port+0.089
 factory+0.088
Neg logit contributions
aid-0.105
 reins-0.089
 tighter-0.086
 brid-0.082
 scar-0.076
Token He
Token ID679
Feature activation-4.13e-02

Pos logit contributions
aid+0.023
 reins+0.020
 tighter+0.019
 brid+0.018
Sleep+0.017
Neg logit contributions
tub-0.020
room-0.020
 site-0.020
 port-0.020
 factory-0.020
Token bird
Token ID6512
Feature activation+6.80e-03

Pos logit contributions
 factory+0.001
tub+0.001
 port+0.001
 site+0.001
room+0.001
Neg logit contributions
aid-0.001
 reins-0.001
 tighter-0.001
 brid-0.001
Sleep-0.001
Token felt
Token ID2936
Feature activation-6.42e-02

Pos logit contributions
tub+0.010
room+0.010
 site+0.010
 factory+0.010
 port+0.010
Neg logit contributions
aid-0.014
 reins-0.012
 tighter-0.012
 brid-0.011
Sleep-0.011
Token the
Token ID262
Feature activation-2.33e-02

Pos logit contributions
aid+0.107
 reins+0.099
 tighter+0.087
 brid+0.086
 scar+0.079
Neg logit contributions
tub-0.115
 port-0.111
room-0.110
 site-0.108
 factory-0.108
Token band
Token ID4097
Feature activation-8.66e-02

Pos logit contributions
aid+0.043
 reins+0.036
 tighter+0.034
 brid+0.034
shadow+0.033
Neg logit contributions
 port-0.037
tub-0.037
 factory-0.036
 Fourth-0.035
room-0.035
Token-
Token ID12
Feature activation+1.48e-02

Pos logit contributions
aid+0.139
 reins+0.127
 tighter+0.116
 brid+0.110
 scar+0.106
Neg logit contributions
room-0.162
tub-0.162
 factory-0.150
 site-0.150
iced-0.149
Tokenaid
Token ID1698
Feature activation-3.14e-01

Pos logit contributions
room+0.042
iced+0.040
auc+0.040
apped+0.040
icker+0.039
Neg logit contributions
 reins-0.006
 brid-0.004
 scar-0.004
 bud-0.004
aid-0.003
Token was
Token ID373
Feature activation+9.00e-02

Pos logit contributions
aid+0.599
 reins+0.540
 brid+0.482
 tighter+0.480
Dear+0.461
Neg logit contributions
tub-0.499
room-0.491
 site-0.463
 port-0.458
 factory-0.457
Token sticky
Token ID23408
Feature activation-2.02e-02

Pos logit contributions
tub+0.144
 site+0.139
iggle+0.139
room+0.138
iced+0.137
Neg logit contributions
aid-0.162
 reins-0.150
 brid-0.130
 tighter-0.130
 scar-0.120
Token and
Token ID290
Feature activation-3.43e-02

Pos logit contributions
aid+0.040
 reins+0.036
 brid+0.033
 tighter+0.032
Dear+0.030
Neg logit contributions
tub-0.032
room-0.031
 site-0.030
 factory-0.030
 port-0.029
Token cool
Token ID3608
Feature activation+3.27e-02

Pos logit contributions
aid+0.064
 reins+0.060
 brid+0.051
 tighter+0.049
Dear+0.048
Neg logit contributions
tub-0.055
 site-0.051
 factory-0.051
 port-0.051
room-0.050
Token.
Token ID13
Feature activation-1.59e-02

Pos logit contributions
tub+0.048
room+0.047
 factory+0.045
 site+0.045
 port+0.044
Neg logit contributions
aid-0.069
 reins-0.061
 brid-0.056
 tighter-0.055
Dear-0.052
Token'll
Token ID1183
Feature activation-9.30e-02

Pos logit contributions
aid+0.004
 reins+0.004
 tighter+0.003
 brid+0.003
Sleep+0.003
Neg logit contributions
tub-0.005
room-0.005
 factory-0.005
 port-0.005
 site-0.005
Token put
Token ID1234
Feature activation-6.06e-02

Pos logit contributions
aid+0.152
 reins+0.129
 tighter+0.123
 brid+0.114
Sleep+0.106
Neg logit contributions
room-0.175
 port-0.173
 factory-0.173
 site-0.173
tub-0.173
Token a
Token ID257
Feature activation-2.51e-02

Pos logit contributions
aid+0.113
 reins+0.097
 tighter+0.093
 brid+0.089
Sleep+0.083
Neg logit contributions
tub-0.100
room-0.100
 site-0.099
 port-0.098
 factory-0.098
Token band
Token ID4097
Feature activation-8.83e-02

Pos logit contributions
aid+0.045
 reins+0.038
 tighter+0.037
 brid+0.035
Sleep+0.035
Neg logit contributions
tub-0.042
 port-0.042
 factory-0.042
 site-0.041
room-0.040
Token-
Token ID12
Feature activation+1.35e-02

Pos logit contributions
aid+0.159
 reins+0.146
 tighter+0.142
Sleep+0.131
 brid+0.130
Neg logit contributions
room-0.143
tub-0.140
 site-0.130
ap-0.129
 port-0.129
Tokenaid
Token ID1698
Feature activation-3.13e-01

Pos logit contributions
room+0.037
auc+0.036
aded+0.035
apped+0.034
ug+0.034
Neg logit contributions
 reins-0.005
 bud-0.004
 brid-0.003
 tighter-0.003
aid-0.003
Token on
Token ID319
Feature activation+8.67e-03

Pos logit contributions
aid+0.598
 reins+0.522
 tighter+0.487
 brid+0.479
Sleep+0.472
Neg logit contributions
tub-0.490
room-0.485
 port-0.459
 factory-0.452
 site-0.452
Token your
Token ID534
Feature activation-6.88e-02

Pos logit contributions
tub+0.015
 site+0.014
room+0.014
 factory+0.014
 port+0.014
Neg logit contributions
aid-0.016
 reins-0.014
 tighter-0.013
 brid-0.013
 scar-0.012
Token hand
Token ID1021
Feature activation-4.67e-02

Pos logit contributions
aid+0.135
 reins+0.111
 tighter+0.109
 brid+0.102
Sleep+0.102
Neg logit contributions
tub-0.109
room-0.107
 site-0.107
 port-0.106
 factory-0.105
Token and
Token ID290
Feature activation-3.11e-02

Pos logit contributions
aid+0.084
 reins+0.072
 tighter+0.068
 brid+0.066
Sleep+0.061
Neg logit contributions
tub-0.081
room-0.081
 site-0.079
 factory-0.078
 port-0.078
Token then
Token ID788
Feature activation-6.18e-02

Pos logit contributions
aid+0.051
 reins+0.043
 tighter+0.041
 brid+0.039
Sleep+0.036
Neg logit contributions
tub-0.057
room-0.057
 port-0.057
 site-0.056
 factory-0.056
Token gave
Token ID2921
Feature activation-1.71e-03

Pos logit contributions
aid+0.016
 tighter+0.013
 reins+0.012
 brid+0.012
 scar+0.011
Neg logit contributions
tub-0.015
room-0.014
 port-0.014
 site-0.014
 factory-0.014
Token Jack
Token ID3619
Feature activation+1.48e-01

Pos logit contributions
aid+0.004
 tighter+0.004
 care+0.003
 reins+0.003
 advice+0.003
Neg logit contributions
 site-0.002
tub-0.002
 factory-0.002
auc-0.002
uders-0.002
Token a
Token ID257
Feature activation-2.09e-02

Pos logit contributions
tub+0.236
room+0.232
 port+0.230
 site+0.227
 factory+0.225
Neg logit contributions
aid-0.280
 reins-0.241
 tighter-0.219
 brid-0.218
 bleed-0.208
Token band
Token ID4097
Feature activation-8.91e-02

Pos logit contributions
aid+0.039
 reins+0.034
 tighter+0.032
 brid+0.030
Sleep+0.030
Neg logit contributions
tub-0.033
 port-0.033
 factory-0.032
room-0.031
 site-0.031
Token-
Token ID12
Feature activation+1.40e-02

Pos logit contributions
aid+0.147
 reins+0.137
 tighter+0.132
 brid+0.119
 scar+0.119
Neg logit contributions
room-0.155
tub-0.152
 site-0.143
apped-0.142
 port-0.141
Tokenaid
Token ID1698
Feature activation-3.13e-01

Pos logit contributions
room+0.042
auc+0.040
apped+0.039
aded+0.039
tub+0.039
Neg logit contributions
 reins-0.003
 bud-0.002
 tighter-0.001
 scar-0.001
aid-0.001
Token for
Token ID329
Feature activation+8.52e-03

Pos logit contributions
aid+0.577
 reins+0.504
 tighter+0.464
 brid+0.457
Sleep+0.435
Neg logit contributions
tub-0.518
room-0.508
 site-0.489
 port-0.488
 factory-0.485
Token his
Token ID465
Feature activation-3.86e-02

Pos logit contributions
tub+0.013
room+0.013
 site+0.012
 factory+0.012
 port+0.012
Neg logit contributions
aid-0.018
 reins-0.015
 tighter-0.015
 brid-0.014
Sleep-0.013
Token knee
Token ID10329
Feature activation-8.54e-02

Pos logit contributions
aid+0.075
 reins+0.063
 tighter+0.061
 brid+0.058
Sleep+0.055
Neg logit contributions
tub-0.060
 factory-0.059
 port-0.059
room-0.059
 site-0.058
Token and
Token ID290
Feature activation-3.28e-02

Pos logit contributions
aid+0.167
 reins+0.149
 tighter+0.136
 brid+0.134
Sleep+0.126
Neg logit contributions
tub-0.135
room-0.131
 site-0.126
 factory-0.126
 port-0.123
Token a
Token ID257
Feature activation-1.88e-02

Pos logit contributions
aid+0.059
 reins+0.049
 tighter+0.049
 brid+0.046
 scar+0.043
Neg logit contributions
room-0.059
tub-0.058
 site-0.057
 factory-0.057
 port-0.056
Token inside
Token ID2641
Feature activation+9.17e-03

Pos logit contributions
aid+0.072
 tighter+0.062
 reins+0.062
 swollen+0.058
 fiber+0.058
Neg logit contributions
tub-0.055
 port-0.055
 factory-0.052
room-0.052
 site-0.050
Token and
Token ID290
Feature activation-3.56e-02

Pos logit contributions
tub+0.017
room+0.016
 site+0.016
 port+0.016
 factory+0.016
Neg logit contributions
aid-0.016
 reins-0.013
 tighter-0.013
 brid-0.012
Sleep-0.011
Token put
Token ID1234
Feature activation-5.95e-02

Pos logit contributions
aid+0.060
 reins+0.051
 tighter+0.048
 brid+0.046
Sleep+0.042
Neg logit contributions
tub-0.066
room-0.065
 port-0.065
 site-0.065
 factory-0.065
Token a
Token ID257
Feature activation-2.27e-02

Pos logit contributions
aid+0.108
 reins+0.092
 tighter+0.088
 brid+0.084
 scar+0.077
Neg logit contributions
tub-0.104
room-0.103
 site-0.102
 port-0.101
 factory-0.101
Token band
Token ID4097
Feature activation-8.68e-02

Pos logit contributions
aid+0.041
 reins+0.035
 tighter+0.034
Sleep+0.031
 brid+0.031
Neg logit contributions
tub-0.038
 port-0.038
 factory-0.037
room-0.036
 site-0.036
Tokenaid
Token ID1698
Feature activation-3.13e-01

Pos logit contributions
aid+0.152
 reins+0.139
 tighter+0.138
Sleep+0.124
 brid+0.123
Neg logit contributions
tub-0.145
room-0.144
 site-0.136
 port-0.133
 factory-0.133
Token on
Token ID319
Feature activation+9.07e-03

Pos logit contributions
aid+0.598
 reins+0.527
 tighter+0.491
Sleep+0.482
 brid+0.480
Neg logit contributions
tub-0.487
room-0.470
 site-0.450
 port-0.448
apped-0.439
Token it
Token ID340
Feature activation-1.15e-02

Pos logit contributions
tub+0.017
 site+0.017
 factory+0.017
room+0.017
 port+0.017
Neg logit contributions
aid-0.015
 reins-0.013
 tighter-0.012
 brid-0.012
 scar-0.010
Token,"
Token ID553
Feature activation-9.98e-02

Pos logit contributions
aid+0.019
 reins+0.016
 tighter+0.015
 brid+0.014
 scar+0.013
Neg logit contributions
tub-0.022
room-0.022
 site-0.021
 factory-0.021
 port-0.021
Token she
Token ID673
Feature activation-3.33e-02

Pos logit contributions
aid+0.172
 reins+0.142
 tighter+0.138
 brid+0.131
 scar+0.119
Neg logit contributions
tub-0.186
room-0.185
 site-0.183
 port-0.181
 factory-0.180
Token said
Token ID531
Feature activation+5.56e-02

Pos logit contributions
aid+0.059
 tighter+0.049
 reins+0.047
 brid+0.046
 scar+0.043
Neg logit contributions
room-0.063
 factory-0.062
 site-0.062
tub-0.062
 port-0.062
Token gave
Token ID2921
Feature activation-1.42e-03

Pos logit contributions
aid+0.196
 tighter+0.165
 brid+0.154
 reins+0.150
 scar+0.142
Neg logit contributions
tub-0.225
room-0.224
 port-0.220
 factory-0.220
 site-0.219
Token them
Token ID606
Feature activation-3.67e-03

Pos logit contributions
aid+0.002
 tighter+0.002
 reins+0.002
 brid+0.002
 scar+0.002
Neg logit contributions
tub-0.003
 site-0.003
room-0.003
 factory-0.003
 port-0.003
Token a
Token ID257
Feature activation-2.04e-02

Pos logit contributions
aid+0.007
 reins+0.006
 tighter+0.006
 brid+0.005
Sleep+0.005
Neg logit contributions
tub-0.006
room-0.006
 port-0.006
 site-0.006
 factory-0.006
Token band
Token ID4097
Feature activation-8.83e-02

Pos logit contributions
aid+0.034
 reins+0.029
 tighter+0.028
Sleep+0.026
 brid+0.026
Neg logit contributions
tub-0.037
 port-0.036
 factory-0.035
room-0.034
 site-0.033
Token-
Token ID12
Feature activation+1.41e-02

Pos logit contributions
aid+0.168
 reins+0.166
 tighter+0.159
Sleep+0.145
 brid+0.145
Neg logit contributions
room-0.128
tub-0.123
apped-0.117
ap-0.113
auc-0.111
Tokenaid
Token ID1698
Feature activation-3.12e-01

Pos logit contributions
room+0.043
auc+0.042
apped+0.040
tub+0.040
aded+0.039
Neg logit contributions
 reins-0.003
 bud-0.001
 tighter-0.001
aid-0.001
 brid-0.000
Token and
Token ID290
Feature activation-3.37e-02

Pos logit contributions
aid+0.584
 reins+0.532
 tighter+0.481
 brid+0.481
Sleep+0.464
Neg logit contributions
tub-0.495
room-0.484
auc-0.456
apped-0.456
 port-0.450
Token moved
Token ID3888
Feature activation+1.52e-02

Pos logit contributions
aid+0.062
 reins+0.054
 tighter+0.050
 brid+0.048
Sleep+0.045
Neg logit contributions
tub-0.057
room-0.056
 site-0.056
 port-0.055
 factory-0.055
Token a
Token ID257
Feature activation-2.10e-02

Pos logit contributions
room+0.023
tub+0.023
 port+0.023
 site+0.023
 factory+0.022
Neg logit contributions
aid-0.030
 reins-0.026
 tighter-0.024
 brid-0.024
Sleep-0.023
Token little
Token ID1310
Feature activation+7.01e-02

Pos logit contributions
aid+0.039
 reins+0.032
 tighter+0.030
Sleep+0.030
Dear+0.029
Neg logit contributions
tub-0.036
 port-0.035
 factory-0.034
 site-0.034
room-0.033
Token to
Token ID284
Feature activation-5.39e-02

Pos logit contributions
tub+0.120
 factory+0.119
 port+0.118
 site+0.116
room+0.114
Neg logit contributions
aid-0.128
 reins-0.106
Sleep-0.097
 brid-0.096
Dear-0.093
Token and
Token ID290
Feature activation-2.04e-02

Pos logit contributions
aid+0.145
 reins+0.127
 tighter+0.115
 brid+0.114
Sleep+0.105
Neg logit contributions
tub-0.136
room-0.134
 site-0.130
 factory-0.129
 port-0.127
Token put
Token ID1234
Feature activation-5.13e-02

Pos logit contributions
aid+0.037
 reins+0.032
 tighter+0.030
 brid+0.029
 scar+0.027
Neg logit contributions
tub-0.035
room-0.035
 site-0.035
 factory-0.034
 port-0.034
Token a
Token ID257
Feature activation-1.92e-02

Pos logit contributions
aid+0.097
 reins+0.086
 tighter+0.080
 brid+0.079
Sleep+0.074
Neg logit contributions
room-0.081
tub-0.081
 site-0.078
 port-0.078
 factory-0.078
Token band
Token ID4097
Feature activation-8.28e-02

Pos logit contributions
aid+0.027
 reins+0.024
 tighter+0.021
Sleep+0.021
 brid+0.021
Neg logit contributions
tub-0.037
 port-0.036
room-0.035
 factory-0.035
 site-0.034
Token-
Token ID12
Feature activation+1.62e-02

Pos logit contributions
 reins+0.156
aid+0.153
 tighter+0.146
 fiber+0.142
 bud+0.139
Neg logit contributions
room-0.120
tub-0.116
apped-0.107
ap-0.104
auc-0.103
Tokenaid
Token ID1698
Feature activation-3.12e-01

Pos logit contributions
room+0.045
auc+0.045
apped+0.042
aded+0.042
iced+0.041
Neg logit contributions
 reins-0.005
 bud-0.005
 hesitation-0.004
 brid-0.003
 scar-0.002
Token on
Token ID319
Feature activation+7.85e-03

Pos logit contributions
aid+0.593
 reins+0.538
 brid+0.489
 tighter+0.479
Sleep+0.473
Neg logit contributions
tub-0.482
room-0.466
apped-0.437
auc-0.434
 site-0.431
Token it
Token ID340
Feature activation-1.10e-02

Pos logit contributions
tub+0.015
room+0.014
 site+0.014
 factory+0.014
 port+0.014
Neg logit contributions
aid-0.013
 reins-0.011
 tighter-0.011
 brid-0.010
Sleep-0.009
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
aid+0.020
 reins+0.017
 tighter+0.016
 brid+0.015
 scar+0.014
Neg logit contributions
tub-0.019
room-0.019
 site-0.019
 port-0.019
 factory-0.019
Token They
Token ID1119
Feature activation+1.64e-02

Pos logit contributions
aid+0.020
 reins+0.017
 tighter+0.016
 brid+0.016
Sleep+0.015
Neg logit contributions
room-0.017
 site-0.017
tub-0.016
 factory-0.016
 port-0.016
Token kissed
Token ID27946
Feature activation-1.13e-01

Pos logit contributions
tub+0.025
room+0.025
 port+0.025
 factory+0.024
 site+0.024
Neg logit contributions
aid-0.031
 reins-0.029
 tighter-0.026
 brid-0.025
Sleep-0.024
Token can
Token ID460
Feature activation-8.91e-02

Pos logit contributions
tub+0.128
room+0.127
 port+0.125
 factory+0.125
 site+0.125
Neg logit contributions
aid-0.108
 reins-0.091
 tighter-0.086
 brid-0.083
Sleep-0.075
Token put
Token ID1234
Feature activation-6.07e-02

Pos logit contributions
aid+0.146
 reins+0.121
 tighter+0.115
 brid+0.110
 scar+0.099
Neg logit contributions
tub-0.171
 site-0.168
room-0.168
 port-0.165
 factory-0.165
Token a
Token ID257
Feature activation-2.38e-02

Pos logit contributions
aid+0.111
 reins+0.095
 tighter+0.091
 brid+0.087
 scar+0.080
Neg logit contributions
tub-0.105
room-0.104
 site-0.103
 port-0.102
 factory-0.102
Token band
Token ID4097
Feature activation-8.64e-02

Pos logit contributions
aid+0.044
 reins+0.038
 tighter+0.037
 brid+0.035
Sleep+0.034
Neg logit contributions
tub-0.039
 port-0.039
 factory-0.038
room-0.038
 site-0.038
Token-
Token ID12
Feature activation+1.50e-02

Pos logit contributions
aid+0.166
 reins+0.155
 tighter+0.153
Sleep+0.140
 brid+0.140
Neg logit contributions
room-0.130
tub-0.130
 port-0.117
 site-0.117
 factory-0.117
Tokenaid
Token ID1698
Feature activation-3.12e-01

Pos logit contributions
room+0.042
auc+0.041
aded+0.039
tub+0.039
apped+0.039
Neg logit contributions
 reins-0.006
 bud-0.005
 tighter-0.004
 brid-0.004
aid-0.004
Token on
Token ID319
Feature activation+9.24e-03

Pos logit contributions
aid+0.596
 reins+0.526
 tighter+0.494
 brid+0.486
Sleep+0.473
Neg logit contributions
tub-0.499
room-0.486
 port-0.461
 factory-0.453
 site-0.450
Token it
Token ID340
Feature activation-1.26e-02

Pos logit contributions
tub+0.018
 site+0.018
 factory+0.017
 port+0.017
room+0.017
Neg logit contributions
aid-0.014
 reins-0.012
 tighter-0.012
 brid-0.011
 scar-0.010
Token."
Token ID526
Feature activation-2.83e-02

Pos logit contributions
aid+0.020
 reins+0.017
 tighter+0.017
 brid+0.016
 scar+0.014
Neg logit contributions
 site-0.024
tub-0.023
room-0.023
 factory-0.023
 port-0.023
Token Lily
Token ID20037
Feature activation+1.48e-02

Pos logit contributions
aid+0.052
 reins+0.042
 tighter+0.042
 brid+0.039
Sleep+0.037
Neg logit contributions
 site-0.049
 port-0.049
tub-0.049
 factory-0.048
room-0.048
Token felt
Token ID2936
Feature activation-6.24e-02

Pos logit contributions
tub+0.027
 site+0.027
room+0.027
 port+0.027
 factory+0.027
Neg logit contributions
aid-0.025
 reins-0.021
 tighter-0.021
 brid-0.019
 scar-0.018
Token to
Token ID284
Feature activation-5.35e-02

Pos logit contributions
room+0.028
tub+0.028
 site+0.028
 port+0.027
 factory+0.027
Neg logit contributions
aid-0.020
 tighter-0.017
 reins-0.017
 brid-0.015
Sleep-0.014
Token get
Token ID651
Feature activation-7.83e-02

Pos logit contributions
aid+0.087
 reins+0.072
 tighter+0.070
 brid+0.066
 bleed+0.060
Neg logit contributions
tub-0.102
room-0.101
 site-0.100
 factory-0.098
 port-0.098
Token a
Token ID257
Feature activation-2.29e-02

Pos logit contributions
aid+0.145
 reins+0.122
 tighter+0.119
 brid+0.112
Sleep+0.103
Neg logit contributions
tub-0.135
room-0.135
 site-0.134
 port-0.131
 factory-0.131
Token band
Token ID4097
Feature activation-8.53e-02

Pos logit contributions
aid+0.042
 reins+0.036
 tighter+0.034
 brid+0.033
Sleep+0.031
Neg logit contributions
tub-0.039
 port-0.038
 site-0.038
 factory-0.038
room-0.038
Token-
Token ID12
Feature activation+1.46e-02

Pos logit contributions
aid+0.147
 reins+0.135
 tighter+0.128
 brid+0.121
Sleep+0.112
Neg logit contributions
room-0.150
tub-0.150
 factory-0.144
 site-0.143
 port-0.141
Tokenaid
Token ID1698
Feature activation-3.11e-01

Pos logit contributions
room+0.042
auc+0.042
aded+0.039
apped+0.039
tub+0.039
Neg logit contributions
 reins-0.005
 bud-0.003
 brid-0.003
 tighter-0.002
 hesitation-0.001
Token and
Token ID290
Feature activation-3.52e-02

Pos logit contributions
aid+0.593
 reins+0.528
 tighter+0.486
 brid+0.481
Sleep+0.452
Neg logit contributions
tub-0.504
room-0.497
 site-0.477
 factory-0.475
 port-0.469
Token a
Token ID257
Feature activation-2.40e-02

Pos logit contributions
aid+0.064
 reins+0.059
 tighter+0.053
 brid+0.052
Sleep+0.049
Neg logit contributions
tub-0.056
 port-0.056
 factory-0.055
 site-0.054
room-0.054
Token cookie
Token ID19751
Feature activation-8.79e-02

Pos logit contributions
aid+0.038
 reins+0.034
 tighter+0.031
Sleep+0.029
 brid+0.029
Neg logit contributions
tub-0.044
 factory-0.043
 port-0.043
 site-0.041
room-0.040
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
aid+0.170
 reins+0.152
 tighter+0.142
 brid+0.138
Sleep+0.130
Neg logit contributions
tub-0.141
room-0.138
 site-0.134
 factory-0.134
 port-0.133
Token They
Token ID1119
Feature activation+1.39e-02

Pos logit contributions
aid+0.022
 reins+0.019
 tighter+0.019
Sleep+0.018
 brid+0.018
Neg logit contributions
 site-0.020
room-0.020
aded-0.019
 factory-0.019
 port-0.019
Token gave
Token ID2921
Feature activation+8.59e-05

Pos logit contributions
aid+0.035
 reins+0.030
 tighter+0.029
 brid+0.028
 scar+0.026
Neg logit contributions
tub-0.028
room-0.027
 site-0.027
 port-0.027
 factory-0.027
Token Lily
Token ID20037
Feature activation+1.20e-02

Pos logit contributions
tub+0.000
 site+0.000
room+0.000
 factory+0.000
 port+0.000
Neg logit contributions
aid-0.000
 reins-0.000
 tighter-0.000
 brid-0.000
 scar-0.000
Token a
Token ID257
Feature activation-2.29e-02

Pos logit contributions
tub+0.019
room+0.018
 port+0.018
 factory+0.017
 site+0.017
Neg logit contributions
aid-0.023
 reins-0.020
 tighter-0.019
 brid-0.018
 bleed-0.018
Token band
Token ID4097
Feature activation-8.68e-02

Pos logit contributions
aid+0.037
 reins+0.032
 tighter+0.031
 brid+0.028
Sleep+0.028
Neg logit contributions
tub-0.042
 port-0.040
room-0.039
 factory-0.039
 structure-0.037
Token-
Token ID12
Feature activation+1.47e-02

Pos logit contributions
aid+0.156
 reins+0.149
 tighter+0.149
 fiber+0.131
 bud+0.131
Neg logit contributions
room-0.136
tub-0.132
apped-0.126
ap-0.121
iggle-0.117
Tokenaid
Token ID1698
Feature activation-3.11e-01

Pos logit contributions
room+0.045
auc+0.043
apped+0.042
tub+0.041
aded+0.041
Neg logit contributions
 reins-0.003
 tighter-0.002
 bud-0.001
aid-0.001
 brid-0.000
Token for
Token ID329
Feature activation+6.56e-03

Pos logit contributions
aid+0.606
 reins+0.543
 tighter+0.504
 brid+0.494
Sleep+0.475
Neg logit contributions
tub-0.474
room-0.466
apped-0.435
 site-0.428
auc-0.427
Token her
Token ID607
Feature activation-9.26e-02

Pos logit contributions
room+0.011
 site+0.011
tub+0.010
 port+0.010
 factory+0.010
Neg logit contributions
aid-0.012
 reins-0.011
 tighter-0.010
 brid-0.010
Sleep-0.009
Token knee
Token ID10329
Feature activation-8.25e-02

Pos logit contributions
aid+0.186
 reins+0.162
 tighter+0.156
 brid+0.149
Sleep+0.139
Neg logit contributions
tub-0.142
room-0.136
 factory-0.135
 port-0.135
 site-0.132
Token.
Token ID13
Feature activation-7.52e-03

Pos logit contributions
aid+0.173
 reins+0.157
 tighter+0.144
 brid+0.142
Sleep+0.134
Neg logit contributions
tub-0.118
room-0.114
 site-0.106
 factory-0.106
 port-0.102
Token They
Token ID1119
Feature activation+1.79e-02

Pos logit contributions
aid+0.012
 reins+0.011
 tighter+0.010
Sleep+0.010
 brid+0.010
Neg logit contributions
 site-0.014
room-0.013
 port-0.013
tub-0.013
auc-0.013
TokenBen
Token ID11696
Feature activation-5.66e-03

Pos logit contributions
aid+0.006
 reins+0.005
 tighter+0.005
 brid+0.004
 scar+0.004
Neg logit contributions
room-0.007
tub-0.007
 site-0.007
 port-0.007
 factory-0.007
Token put
Token ID1234
Feature activation-5.55e-02

Pos logit contributions
aid+0.009
 reins+0.007
 tighter+0.007
 brid+0.007
 scar+0.006
Neg logit contributions
tub-0.011
room-0.011
 site-0.011
 port-0.011
 factory-0.011
Token the
Token ID262
Feature activation-1.96e-02

Pos logit contributions
aid+0.099
 reins+0.084
 tighter+0.080
 brid+0.076
 scar+0.069
Neg logit contributions
tub-0.099
room-0.098
 site-0.098
 port-0.097
 factory-0.097
Token band
Token ID4097
Feature activation-8.38e-02

Pos logit contributions
aid+0.038
shadow+0.032
 tighter+0.032
Sleep+0.031
 reins+0.031
Neg logit contributions
tub-0.029
 factory-0.028
 port-0.027
 structure-0.027
 elevator-0.026
Token-
Token ID12
Feature activation+1.56e-02

Pos logit contributions
aid+0.150
 reins+0.144
 tighter+0.132
 brid+0.129
Sleep+0.126
Neg logit contributions
room-0.134
tub-0.132
apped-0.122
ap-0.122
 site-0.120
Tokenaid
Token ID1698
Feature activation-3.11e-01

Pos logit contributions
room+0.045
auc+0.045
apped+0.042
icker+0.042
iced+0.042
Neg logit contributions
 reins-0.005
 hesitation-0.003
 bud-0.003
 brid-0.003
 scar-0.002
Token on
Token ID319
Feature activation+1.08e-02

Pos logit contributions
aid+0.566
 reins+0.507
 brid+0.462
 tighter+0.450
Sleep+0.441
Neg logit contributions
tub-0.511
room-0.506
 site-0.483
 port-0.482
 factory-0.478
Token Lily
Token ID20037
Feature activation+1.68e-02

Pos logit contributions
tub+0.022
 factory+0.021
 site+0.021
 port+0.021
auc+0.020
Neg logit contributions
aid-0.016
 tighter-0.014
 reins-0.013
 brid-0.013
 scar-0.011
Token's
Token ID338
Feature activation+1.07e-01

Pos logit contributions
tub+0.016
room+0.016
 site+0.016
 port+0.015
 factory+0.015
Neg logit contributions
aid-0.043
 reins-0.039
 tighter-0.038
 brid-0.037
Sleep-0.035
Token knee
Token ID10329
Feature activation-8.36e-02

Pos logit contributions
tub+0.144
room+0.143
 site+0.134
 port+0.134
 factory+0.132
Neg logit contributions
aid-0.236
 reins-0.201
 tighter-0.195
Sleep-0.190
Dear-0.190
Token.
Token ID13
Feature activation-1.36e-02

Pos logit contributions
aid+0.156
 reins+0.139
 tighter+0.126
 brid+0.124
Sleep+0.116
Neg logit contributions
tub-0.140
room-0.138
 site-0.134
 factory-0.133
 port-0.130
Token back
Token ID736
Feature activation-8.34e-02

Pos logit contributions
tub+0.122
room+0.121
 port+0.120
 site+0.119
 factory+0.118
Neg logit contributions
aid-0.086
 reins-0.069
 tighter-0.065
 brid-0.062
Sleep-0.056
Token with
Token ID351
Feature activation+1.16e-01

Pos logit contributions
aid+0.155
 reins+0.135
 tighter+0.132
 brid+0.126
 bud+0.116
Neg logit contributions
tub-0.135
 site-0.133
room-0.132
 factory-0.128
 port-0.128
Token the
Token ID262
Feature activation-2.04e-02

Pos logit contributions
tub+0.210
room+0.208
 site+0.207
 factory+0.204
 port+0.201
Neg logit contributions
aid-0.205
 reins-0.174
 tighter-0.168
 brid-0.160
 scar-0.146
Token band
Token ID4097
Feature activation-8.20e-02

Pos logit contributions
aid+0.037
 reins+0.031
 tighter+0.030
 brid+0.029
Sleep+0.026
Neg logit contributions
tub-0.036
room-0.036
 site-0.035
 port-0.035
 factory-0.035
Token-
Token ID12
Feature activation+1.83e-02

Pos logit contributions
aid+0.167
 reins+0.144
 tighter+0.138
 brid+0.133
 scar+0.123
Neg logit contributions
tub-0.125
room-0.124
 site-0.123
 port-0.122
 factory-0.121
Tokenaid
Token ID1698
Feature activation-3.11e-01

Pos logit contributions
room+0.038
tub+0.037
 site+0.037
 factory+0.036
auc+0.036
Neg logit contributions
aid-0.025
 reins-0.022
 tighter-0.020
 brid-0.020
 scar-0.018
Token,
Token ID11
Feature activation+2.63e-02

Pos logit contributions
aid+0.635
 reins+0.546
 tighter+0.538
 brid+0.509
 scar+0.474
Neg logit contributions
tub-0.467
room-0.467
 site-0.463
 port-0.458
 factory-0.455
Token Lily
Token ID20037
Feature activation+1.36e-02

Pos logit contributions
room+0.053
 site+0.052
tub+0.052
 factory+0.051
auc+0.050
Neg logit contributions
aid-0.039
 tighter-0.033
 reins-0.032
 brid-0.030
 scar-0.027
Token was
Token ID373
Feature activation+9.01e-02

Pos logit contributions
room+0.022
tub+0.022
 site+0.022
 port+0.022
 factory+0.022
Neg logit contributions
aid-0.026
 reins-0.022
 tighter-0.022
 brid-0.021
 scar-0.019
Token smiling
Token ID16755
Feature activation-4.16e-02

Pos logit contributions
tub+0.162
room+0.160
 site+0.159
 factory+0.158
 port+0.158
Neg logit contributions
aid-0.159
 reins-0.134
 tighter-0.130
 brid-0.123
Sleep-0.112
Token and
Token ID290
Feature activation-3.35e-02

Pos logit contributions
aid+0.084
 reins+0.073
 tighter+0.068
 brid+0.066
Sleep+0.062
Neg logit contributions
tub-0.066
room-0.064
 port-0.063
 site-0.062
 factory-0.061
Token She
Token ID1375
Feature activation-7.45e-02

Pos logit contributions
aid+0.017
 reins+0.014
 tighter+0.014
 brid+0.013
Sleep+0.012
Neg logit contributions
 site-0.016
tub-0.016
room-0.016
 factory-0.016
 port-0.016
Token put
Token ID1234
Feature activation-5.59e-02

Pos logit contributions
aid+0.125
 tighter+0.096
 brid+0.091
 scar+0.088
 reins+0.082
Neg logit contributions
 site-0.151
room-0.150
 factory-0.150
 port-0.148
tub-0.145
Token a
Token ID257
Feature activation-1.92e-02

Pos logit contributions
aid+0.105
 reins+0.091
 tighter+0.086
 brid+0.083
Sleep+0.078
Neg logit contributions
tub-0.092
room-0.092
 site-0.089
 port-0.089
 factory-0.089
Token band
Token ID4097
Feature activation-8.34e-02

Pos logit contributions
aid+0.033
 reins+0.028
 tighter+0.027
 brid+0.025
Sleep+0.024
Neg logit contributions
tub-0.035
 port-0.034
room-0.034
 site-0.034
 factory-0.033
Token-
Token ID12
Feature activation+1.75e-02

Pos logit contributions
aid+0.171
 reins+0.164
 tighter+0.158
 brid+0.148
Sleep+0.146
Neg logit contributions
room-0.115
tub-0.111
apped-0.100
 site-0.100
auc-0.099
Tokenaid
Token ID1698
Feature activation-3.09e-01

Pos logit contributions
room+0.053
auc+0.052
tub+0.050
aded+0.050
apped+0.050
Neg logit contributions
 reins-0.004
 brid-0.001
 bud-0.001
aid-0.001
 tighter-0.001
Token on
Token ID319
Feature activation+1.26e-02

Pos logit contributions
aid+0.579
 reins+0.509
 brid+0.465
 tighter+0.464
Sleep+0.454
Neg logit contributions
tub-0.498
room-0.492
 port-0.467
 site-0.466
 factory-0.459
Token it
Token ID340
Feature activation-8.59e-03

Pos logit contributions
tub+0.023
 site+0.022
room+0.022
 factory+0.022
 port+0.022
Neg logit contributions
aid-0.022
 reins-0.019
 tighter-0.018
 brid-0.017
 scar-0.016
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
aid+0.014
 reins+0.012
 tighter+0.012
 brid+0.011
 scar+0.010
Neg logit contributions
tub-0.016
room-0.016
 site-0.016
 port-0.016
 factory-0.016
Token She
Token ID1375
Feature activation-7.42e-02

Pos logit contributions
aid+0.019
 reins+0.016
 tighter+0.015
 brid+0.015
Sleep+0.013
Neg logit contributions
tub-0.017
room-0.017
 site-0.017
 factory-0.016
 port-0.016
Token hugged
Token ID41130
Feature activation-8.58e-02

Pos logit contributions
aid+0.124
 tighter+0.096
 brid+0.093
 scar+0.089
 reins+0.088
Neg logit contributions
room-0.148
 site-0.148
 factory-0.146
 port-0.146
tub-0.145
Token asked
Token ID1965
Feature activation+1.77e-03

Pos logit contributions
aid+0.055
 reins+0.046
 tighter+0.046
 brid+0.044
 scar+0.040
Neg logit contributions
tub-0.053
room-0.053
 site-0.051
 port-0.051
 factory-0.051
Token for
Token ID329
Feature activation+8.26e-03

Pos logit contributions
tub+0.003
room+0.003
 site+0.003
 port+0.003
 factory+0.003
Neg logit contributions
aid-0.003
 reins-0.003
 tighter-0.003
 brid-0.002
 scar-0.002
Token a
Token ID257
Feature activation-2.10e-02

Pos logit contributions
 site+0.016
 port+0.016
room+0.016
 factory+0.016
tub+0.016
Neg logit contributions
aid-0.013
 reins-0.011
 tighter-0.010
 brid-0.010
 bleed-0.009
Token band
Token ID4097
Feature activation-8.47e-02

Pos logit contributions
aid+0.037
 reins+0.030
 tighter+0.030
 brid+0.028
Sleep+0.026
Neg logit contributions
tub-0.037
 port-0.037
 factory-0.037
 site-0.036
room-0.036
Token-
Token ID12
Feature activation+1.68e-02

Pos logit contributions
aid+0.157
 reins+0.141
 tighter+0.136
 brid+0.128
Sleep+0.120
Neg logit contributions
room-0.139
tub-0.138
 site-0.133
 factory-0.133
 port-0.131
Tokenaid
Token ID1698
Feature activation-3.09e-01

Pos logit contributions
room+0.042
auc+0.041
 site+0.040
 factory+0.039
ook+0.039
Neg logit contributions
 reins-0.012
aid-0.011
 tighter-0.010
 bleed-0.010
 brid-0.010
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
aid+0.593
 reins+0.517
 tighter+0.485
 brid+0.475
Sleep+0.443
Neg logit contributions
tub-0.504
room-0.496
 site-0.483
 factory-0.480
 port-0.474
Token Miss
Token ID4544
Feature activation+3.07e-02

Pos logit contributions
aid+0.022
 reins+0.018
 tighter+0.018
 brid+0.017
Dear+0.016
Neg logit contributions
tub-0.018
room-0.017
 site-0.017
 port-0.017
 factory-0.017
Token Lee
Token ID5741
Feature activation-6.32e-02

Pos logit contributions
 site+0.046
tub+0.046
 port+0.046
room+0.044
 factory+0.044
Neg logit contributions
aid-0.062
 reins-0.053
 tighter-0.052
 brid-0.050
Sleep-0.046
Token gave
Token ID2921
Feature activation-1.44e-04

Pos logit contributions
aid+0.098
 tighter+0.080
 brid+0.076
 reins+0.072
 scar+0.070
Neg logit contributions
tub-0.132
room-0.127
 port-0.126
 site-0.122
 Fourth-0.122
Token them
Token ID606
Feature activation-3.36e-03

Pos logit contributions
aid+0.000
 reins+0.000
 tighter+0.000
 brid+0.000
 scar+0.000
Neg logit contributions
tub-0.000
 site-0.000
 port-0.000
room-0.000
 factory-0.000
Token quickly
Token ID2952
Feature activation-6.67e-03

Pos logit contributions
aid+0.183
 reins+0.156
 tighter+0.152
 brid+0.145
 scar+0.134
Neg logit contributions
tub-0.150
 site-0.148
room-0.147
 port-0.146
 factory-0.144
Token got
Token ID1392
Feature activation-1.57e-02

Pos logit contributions
aid+0.012
 reins+0.011
 tighter+0.010
 brid+0.010
Sleep+0.009
Neg logit contributions
tub-0.011
room-0.011
 site-0.011
 port-0.011
 factory-0.011
Token a
Token ID257
Feature activation-2.44e-02

Pos logit contributions
aid+0.029
 reins+0.026
 brid+0.024
 tighter+0.023
Sleep+0.022
Neg logit contributions
 factory-0.025
tub-0.025
 port-0.025
room-0.025
 site-0.025
Token band
Token ID4097
Feature activation-8.48e-02

Pos logit contributions
aid+0.047
 reins+0.041
 tighter+0.038
 brid+0.037
Sleep+0.035
Neg logit contributions
tub-0.039
 factory-0.039
 port-0.038
 site-0.038
room-0.038
Token-
Token ID12
Feature activation+1.72e-02

Pos logit contributions
aid+0.172
 reins+0.160
 tighter+0.150
 brid+0.145
 scar+0.138
Neg logit contributions
room-0.124
tub-0.121
 site-0.117
 factory-0.116
 port-0.112
Tokenaid
Token ID1698
Feature activation-3.09e-01

Pos logit contributions
room+0.053
auc+0.052
iced+0.050
 site+0.050
ook+0.049
Neg logit contributions
 reins-0.004
aid-0.002
 brid-0.001
 scar-0.000
 bud+0.000
Token to
Token ID284
Feature activation-5.32e-02

Pos logit contributions
aid+0.616
 reins+0.550
 brid+0.501
 tighter+0.491
Sleep+0.479
Neg logit contributions
tub-0.465
room-0.463
 factory-0.436
 site-0.436
 port-0.426
Token make
Token ID787
Feature activation-7.70e-02

Pos logit contributions
 reins+0.094
aid+0.085
 tighter+0.080
 brid+0.080
Sleep+0.075
Neg logit contributions
room-0.089
iggle-0.081
 factory-0.080
 site-0.080
iced-0.075
Token it
Token ID340
Feature activation-1.00e-02

Pos logit contributions
aid+0.120
 reins+0.098
 tighter+0.094
 brid+0.088
Sleep+0.079
Neg logit contributions
tub-0.155
 site-0.153
room-0.153
 port-0.151
 factory-0.151
Token better
Token ID1365
Feature activation-1.31e-01

Pos logit contributions
aid+0.016
 reins+0.014
 brid+0.012
 tighter+0.012
Sleep+0.012
Neg logit contributions
tub-0.019
room-0.019
iced-0.018
 port-0.018
iggle-0.018
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
aid+0.319
 reins+0.312
 brid+0.276
Sleep+0.260
 scar+0.259
Neg logit contributions
room-0.148
tub-0.142
 site-0.137
 factory-0.127
ap-0.124
Token They
Token ID1119
Feature activation+2.34e-02

Pos logit contributions
tub+0.004
room+0.004
 site+0.004
 factory+0.004
 port+0.004
Neg logit contributions
aid-0.007
 reins-0.006
 tighter-0.006
 brid-0.006
Sleep-0.005
Token put
Token ID1234
Feature activation-5.10e-02

Pos logit contributions
 port+0.039
 nation+0.037
 factory+0.037
room+0.036
tub+0.036
Neg logit contributions
aid-0.041
 reins-0.037
shadow-0.034
 tighter-0.034
Sweet-0.031
Token a
Token ID257
Feature activation-1.43e-02

Pos logit contributions
aid+0.103
 reins+0.089
 tighter+0.086
 brid+0.083
Sleep+0.076
Neg logit contributions
tub-0.079
room-0.078
 site-0.077
 port-0.076
 factory-0.076
Token band
Token ID4097
Feature activation-8.15e-02

Pos logit contributions
aid+0.024
 reins+0.021
 tighter+0.020
 brid+0.019
Sleep+0.018
Neg logit contributions
tub-0.026
 port-0.025
 factory-0.025
room-0.025
 site-0.024
Token-
Token ID12
Feature activation+2.07e-02

Pos logit contributions
aid+0.156
 reins+0.156
 tighter+0.150
 fiber+0.144
 bud+0.138
Neg logit contributions
room-0.115
tub-0.108
apped-0.107
ap-0.102
auc-0.095
Tokenaid
Token ID1698
Feature activation-3.09e-01

Pos logit contributions
room+0.059
auc+0.059
apped+0.056
tub+0.055
aded+0.055
Neg logit contributions
 reins-0.006
 bud-0.005
 hesitation-0.003
 brid-0.002
 tighter-0.001
Token on
Token ID319
Feature activation+1.43e-02

Pos logit contributions
aid+0.592
 reins+0.539
 brid+0.491
Sleep+0.488
 fiber+0.486
Neg logit contributions
tub-0.460
room-0.446
apped-0.433
auc-0.412
 site-0.408
Token Anna
Token ID11735
Feature activation-1.32e-02

Pos logit contributions
tub+0.025
 factory+0.023
 site+0.023
 port+0.023
auc+0.023
Neg logit contributions
aid-0.026
 reins-0.023
 tighter-0.023
 brid-0.021
 scar-0.020
Token's
Token ID338
Feature activation+1.07e-01

Pos logit contributions
aid+0.035
 reins+0.031
 tighter+0.029
 brid+0.029
Sleep+0.028
Neg logit contributions
room-0.012
tub-0.011
ap-0.011
 factory-0.010
 port-0.010
Token finger
Token ID7660
Feature activation-1.80e-02

Pos logit contributions
tub+0.153
room+0.147
 port+0.142
ap+0.140
 site+0.138
Neg logit contributions
aid-0.221
 reins-0.185
 tighter-0.181
Sleep-0.174
Dear-0.171
Token.
Token ID13
Feature activation-8.03e-03

Pos logit contributions
aid+0.035
 reins+0.031
 tighter+0.029
 brid+0.029
Sleep+0.027
Neg logit contributions
tub-0.028
room-0.027
 site-0.026
 port-0.025
 factory-0.025
Token and
Token ID290
Feature activation-3.42e-02

Pos logit contributions
aid+0.348
 reins+0.299
 tighter+0.279
 brid+0.275
 scar+0.255
Neg logit contributions
room-0.274
tub-0.273
 site-0.266
 factory-0.261
 port-0.261
Token put
Token ID1234
Feature activation-5.93e-02

Pos logit contributions
aid+0.058
 reins+0.052
 tighter+0.046
Sleep+0.044
 brid+0.044
Neg logit contributions
 port-0.057
 factory-0.057
tub-0.056
 site-0.055
 structure-0.054
Token some
Token ID617
Feature activation+3.70e-03

Pos logit contributions
aid+0.113
 reins+0.098
 tighter+0.093
 brid+0.090
Sleep+0.082
Neg logit contributions
tub-0.098
room-0.096
 site-0.096
 port-0.094
 factory-0.094
Token band
Token ID4097
Feature activation-8.35e-02

Pos logit contributions
tub+0.006
room+0.006
 port+0.006
 factory+0.006
 site+0.006
Neg logit contributions
aid-0.006
 reins-0.006
 tighter-0.005
 brid-0.005
Sleep-0.005
Token-
Token ID12
Feature activation+1.59e-02

Pos logit contributions
 reins+0.154
aid+0.153
 tighter+0.149
 brid+0.138
 bud+0.136
Neg logit contributions
room-0.123
tub-0.122
apped-0.111
ap-0.110
auc-0.108
Tokenaid
Token ID1698
Feature activation-3.09e-01

Pos logit contributions
room+0.044
auc+0.044
aded+0.042
 site+0.041
tub+0.041
Neg logit contributions
 reins-0.006
 bud-0.004
 brid-0.004
 tighter-0.003
aid-0.003
Tokens
Token ID82
Feature activation+6.50e-02

Pos logit contributions
aid+0.671
 reins+0.622
 brid+0.580
 tighter+0.579
Are+0.556
Neg logit contributions
tub-0.389
room-0.376
auc-0.346
 site-0.342
apped-0.338
Token on
Token ID319
Feature activation+1.01e-02

Pos logit contributions
tub+0.101
room+0.097
 site+0.094
 port+0.093
 factory+0.093
Neg logit contributions
aid-0.124
 reins-0.109
 tighter-0.102
 brid-0.102
Sleep-0.093
Token them
Token ID606
Feature activation-1.31e-03

Pos logit contributions
tub+0.018
 site+0.018
room+0.018
 factory+0.018
 port+0.018
Neg logit contributions
aid-0.018
 reins-0.015
 tighter-0.015
 brid-0.014
 scar-0.013
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
aid+0.002
 reins+0.002
 tighter+0.002
 brid+0.002
Sleep+0.002
Neg logit contributions
tub-0.002
room-0.002
 site-0.002
 port-0.002
 factory-0.002
Token Then
Token ID3244
Feature activation-2.05e-02

Pos logit contributions
aid+0.028
 reins+0.025
 tighter+0.024
 brid+0.023
 scar+0.022
Neg logit contributions
room-0.017
tub-0.017
 factory-0.016
 port-0.016
 site-0.016
TokenSo
Token ID2396
Feature activation-6.44e-03

Pos logit contributions
 site+0.010
room+0.010
 port+0.010
tub+0.010
 factory+0.010
Neg logit contributions
aid-0.008
 reins-0.006
 tighter-0.006
 brid-0.006
 bleed-0.005
Token Murray
Token ID12164
Feature activation+3.38e-02

Pos logit contributions
aid+0.013
 reins+0.012
 tighter+0.011
 brid+0.011
 scar+0.010
Neg logit contributions
tub-0.009
room-0.009
 site-0.009
 factory-0.009
 port-0.009
Token turned
Token ID2900
Feature activation+6.26e-03

Pos logit contributions
tub+0.062
 site+0.062
room+0.061
 factory+0.060
 port+0.060
Neg logit contributions
aid-0.058
 tighter-0.048
 reins-0.047
 brid-0.045
 scar-0.041
Token the
Token ID262
Feature activation-1.26e-02

Pos logit contributions
tub+0.009
 port+0.009
 site+0.009
room+0.009
 factory+0.009
Neg logit contributions
aid-0.013
 reins-0.011
 tighter-0.010
 brid-0.010
Sleep-0.010
Token dish
Token ID9433
Feature activation+7.42e-02

Pos logit contributions
aid+0.028
 reins+0.025
 tighter+0.024
 brid+0.023
 advice+0.022
Neg logit contributions
room-0.016
tub-0.015
 site-0.015
iggle-0.015
 port-0.015
Tokenwasher
Token ID45146
Feature activation+1.55e-01

Pos logit contributions
room+0.068
 site+0.068
tub+0.066
 port+0.066
 factory+0.063
Neg logit contributions
aid-0.190
 tighter-0.170
 reins-0.167
 brid-0.157
 scar-0.150
Token on
Token ID319
Feature activation+2.32e-02

Pos logit contributions
tub+0.296
room+0.292
 site+0.289
 port+0.287
 factory+0.283
Neg logit contributions
aid-0.248
 tighter-0.212
 reins-0.209
 brid-0.188
 scar-0.173
Token and
Token ID290
Feature activation-2.12e-02

Pos logit contributions
tub+0.043
room+0.042
 site+0.042
 port+0.041
 factory+0.041
Neg logit contributions
aid-0.039
 reins-0.033
 tighter-0.032
 brid-0.030
 scar-0.027
Token started
Token ID2067
Feature activation+1.56e-02

Pos logit contributions
aid+0.036
 tighter+0.031
 reins+0.029
 brid+0.028
 scar+0.026
Neg logit contributions
room-0.039
tub-0.039
 site-0.038
 factory-0.038
 port-0.038
Token enjoying
Token ID13226
Feature activation+1.12e-02

Pos logit contributions
tub+0.030
 site+0.029
room+0.029
 factory+0.029
 port+0.029
Neg logit contributions
aid-0.026
 reins-0.022
 tighter-0.021
 brid-0.020
Sleep-0.018
Token it
Token ID340
Feature activation+3.69e-03

Pos logit contributions
tub+0.019
 site+0.019
room+0.018
 port+0.018
 factory+0.018
Neg logit contributions
aid-0.021
 reins-0.018
 tighter-0.017
 brid-0.017
Sleep-0.015
Token were
Token ID547
Feature activation+6.76e-02

Pos logit contributions
tub+0.036
 site+0.036
room+0.036
 port+0.035
 factory+0.035
Neg logit contributions
aid-0.053
 reins-0.045
 tighter-0.044
 brid-0.043
 scar-0.040
Token watching
Token ID4964
Feature activation+4.10e-02

Pos logit contributions
room+0.127
 site+0.122
tub+0.120
 factory+0.117
 port+0.116
Neg logit contributions
aid-0.110
 reins-0.095
 tighter-0.095
 scar-0.090
 brid-0.090
Token a
Token ID257
Feature activation-2.49e-03

Pos logit contributions
tub+0.071
 site+0.070
aded+0.068
undle+0.067
 port+0.067
Neg logit contributions
aid-0.066
 tighter-0.060
 reins-0.058
 scar-0.055
 brid-0.052
Token big
Token ID1263
Feature activation+8.68e-02

Pos logit contributions
aid+0.005
 reins+0.005
 tighter+0.004
 brid+0.004
Sleep+0.004
Neg logit contributions
tub-0.004
room-0.004
 site-0.004
 port-0.003
 factory-0.003
Token box
Token ID3091
Feature activation+1.03e-01

Pos logit contributions
tub+0.125
room+0.123
 site+0.121
 port+0.119
 factory+0.118
Neg logit contributions
aid-0.181
 reins-0.159
 tighter-0.154
 brid-0.149
 scar-0.140
Token with
Token ID351
Feature activation+1.33e-01

Pos logit contributions
tub+0.183
room+0.179
 site+0.178
 factory+0.176
 port+0.175
Neg logit contributions
aid-0.174
 reins-0.147
 tighter-0.146
 brid-0.135
 bud-0.127
Token a
Token ID257
Feature activation-2.22e-03

Pos logit contributions
tub+0.247
 site+0.245
room+0.242
iggle+0.240
 factory+0.238
Neg logit contributions
aid-0.217
 reins-0.185
 tighter-0.177
 brid-0.170
 scar-0.168
Token lot
Token ID1256
Feature activation-7.72e-02

Pos logit contributions
aid+0.005
 reins+0.004
 tighter+0.004
Sleep+0.004
 brid+0.004
Neg logit contributions
 factory-0.003
 port-0.003
tub-0.003
 site-0.003
room-0.003
Token of
Token ID286
Feature activation+9.12e-02

Pos logit contributions
aid+0.175
 reins+0.153
 tighter+0.149
 brid+0.143
Sleep+0.134
Neg logit contributions
tub-0.100
room-0.098
 site-0.097
 port-0.096
 factory-0.095
Token lights
Token ID7588
Feature activation-1.62e-02

Pos logit contributions
tub+0.144
room+0.142
 site+0.141
 port+0.139
 factory+0.139
Neg logit contributions
aid-0.180
 reins-0.156
 tighter-0.150
 brid-0.144
Sleep-0.133
Token and
Token ID290
Feature activation-1.90e-02

Pos logit contributions
aid+0.028
 reins+0.024
 tighter+0.023
 brid+0.022
 scar+0.020
Neg logit contributions
tub-0.028
room-0.028
 site-0.028
 factory-0.027
 port-0.027
Token suggested
Token ID5220
Feature activation+3.77e-02

Pos logit contributions
aid+0.057
 tighter+0.049
 reins+0.046
 brid+0.045
 scar+0.042
Neg logit contributions
tub-0.065
room-0.064
 port-0.064
 factory-0.064
 site-0.063
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
tub+0.071
 port+0.069
room+0.069
 site+0.069
 factory+0.069
Neg logit contributions
aid-0.063
 tighter-0.052
 reins-0.052
 brid-0.047
 advice-0.043
Token
Token ID198
Feature activation-5.59e-03

Pos logit contributions
aid+0.019
 reins+0.017
 tighter+0.015
 brid+0.014
She+0.014
Neg logit contributions
tub-0.025
 port-0.025
 site-0.025
 factory-0.025
room-0.025
Token
Token ID198
Feature activation-5.63e-03

Pos logit contributions
aid+0.010
 reins+0.008
 tighter+0.008
 brid+0.007
Sleep+0.007
Neg logit contributions
tub-0.010
 port-0.010
 factory-0.010
 site-0.010
room-0.010
TokenSo
Token ID2396
Feature activation-2.00e-02

Pos logit contributions
aid+0.009
 reins+0.007
 tighter+0.007
 brid+0.006
Sleep+0.006
Neg logit contributions
tub-0.012
room-0.011
 site-0.011
 port-0.011
 factory-0.011
Token Jack
Token ID3619
Feature activation+1.51e-01

Pos logit contributions
aid+0.037
 tighter+0.034
 reins+0.032
 care+0.031
 listen+0.030
Neg logit contributions
tub-0.033
room-0.031
 site-0.031
auc-0.031
 factory-0.030
Token and
Token ID290
Feature activation-3.36e-02

Pos logit contributions
tub+0.258
room+0.255
 site+0.253
 port+0.250
 factory+0.250
Neg logit contributions
aid-0.278
 reins-0.238
 tighter-0.228
 brid-0.218
 scar-0.199
Token Jane
Token ID12091
Feature activation+5.27e-02

Pos logit contributions
aid+0.084
 reins+0.074
 tighter+0.074
 brid+0.070
 scar+0.066
Neg logit contributions
tub-0.035
room-0.034
 site-0.034
 port-0.033
 factory-0.032
Token parted
Token ID37813
Feature activation-2.93e-02

Pos logit contributions
tub+0.084
room+0.083
 site+0.082
 factory+0.081
 port+0.081
Neg logit contributions
aid-0.104
 reins-0.089
 tighter-0.086
 brid-0.083
 scar-0.076
Token the
Token ID262
Feature activation-2.21e-02

Pos logit contributions
aid+0.051
 reins+0.044
 tighter+0.043
 brid+0.040
 scar+0.037
Neg logit contributions
tub-0.053
room-0.052
 site-0.051
 factory-0.051
 port-0.050
Token branches
Token ID13737
Feature activation-9.27e-02

Pos logit contributions
aid+0.048
Sleep+0.038
 reins+0.038
Dear+0.037
 brid+0.036
Neg logit contributions
 structure-0.034
 factory-0.032
 site-0.031
 nation-0.030
 volcano-0.029
Token and
Token ID290
Feature activation-2.36e-02

Pos logit contributions
tub+0.067
room+0.067
 site+0.066
 port+0.066
 factory+0.065
Neg logit contributions
aid-0.067
 reins-0.057
 tighter-0.054
 brid-0.052
 scar-0.047
Token Papa
Token ID42328
Feature activation+1.94e-02

Pos logit contributions
aid+0.055
 reins+0.048
 tighter+0.047
 brid+0.045
Sleep+0.043
Neg logit contributions
tub-0.028
 port-0.028
 factory-0.028
room-0.028
 site-0.027
Token looked
Token ID3114
Feature activation+6.83e-02

Pos logit contributions
tub+0.032
 site+0.031
room+0.031
 factory+0.030
 port+0.030
Neg logit contributions
aid-0.037
 reins-0.032
 tighter-0.031
 brid-0.030
 scar-0.028
Token at
Token ID379
Feature activation+1.44e-01

Pos logit contributions
room+0.094
tub+0.088
 site+0.088
 port+0.081
uders+0.080
Neg logit contributions
aid-0.154
 tighter-0.142
 reins-0.140
 brid-0.131
 scar-0.128
Token them
Token ID606
Feature activation+4.85e-03

Pos logit contributions
tub+0.201
room+0.201
 site+0.199
 port+0.197
 factory+0.196
Neg logit contributions
aid-0.310
 reins-0.272
 tighter-0.259
 brid-0.252
Sleep-0.233
Token with
Token ID351
Feature activation+1.27e-01

Pos logit contributions
tub+0.009
room+0.008
 site+0.008
 port+0.008
 factory+0.008
Neg logit contributions
aid-0.009
 reins-0.007
 tighter-0.007
 brid-0.007
 scar-0.006
Token love
Token ID1842
Feature activation-1.63e-01

Pos logit contributions
 port+0.204
room+0.204
tub+0.201
 factory+0.200
 site+0.198
Neg logit contributions
aid-0.240
 reins-0.208
 tighter-0.198
 brid-0.188
Sleep-0.182
Token.
Token ID13
Feature activation-4.87e-03

Pos logit contributions
aid+0.332
 reins+0.294
 tighter+0.274
 brid+0.271
Sleep+0.247
Neg logit contributions
room-0.250
tub-0.250
 site-0.244
 factory-0.244
 port-0.238
Token They
Token ID1119
Feature activation+2.16e-02

Pos logit contributions
aid+0.009
 reins+0.008
 tighter+0.007
 brid+0.007
Sleep+0.007
Neg logit contributions
room-0.008
 site-0.008
tub-0.008
iggle-0.007
 factory-0.007
Token said
Token ID531
Feature activation+6.44e-02

Pos logit contributions
tub+0.033
room+0.032
 site+0.032
 port+0.032
 factory+0.032
Neg logit contributions
aid-0.044
 reins-0.039
 tighter-0.037
 brid-0.036
Sleep-0.033
Token,
Token ID11
Feature activation+4.32e-02

Pos logit contributions
tub+0.098
room+0.097
 site+0.096
 port+0.094
 factory+0.094
Neg logit contributions
aid-0.132
 reins-0.114
 tighter-0.110
 brid-0.106
Sleep-0.099
Token.
Token ID13
Feature activation-3.21e-03

Pos logit contributions
aid+0.054
 reins+0.047
 tighter+0.044
 brid+0.043
Sleep+0.040
Neg logit contributions
tub-0.044
room-0.044
 site-0.043
 factory-0.043
 port-0.043
Token The
Token ID383
Feature activation+7.03e-03

Pos logit contributions
aid+0.006
 reins+0.005
 tighter+0.005
 brid+0.005
Sleep+0.005
Neg logit contributions
tub-0.005
room-0.005
 site-0.005
 port-0.005
iggle-0.005
Token old
Token ID1468
Feature activation+2.62e-02

Pos logit contributions
tub+0.012
room+0.012
 site+0.012
 port+0.012
iggle+0.011
Neg logit contributions
aid-0.013
 reins-0.011
 tighter-0.011
 brid-0.010
 scar-0.009
Token man
Token ID582
Feature activation+6.46e-03

Pos logit contributions
tub+0.053
room+0.053
 site+0.052
 factory+0.052
 port+0.052
Neg logit contributions
aid-0.040
 reins-0.033
 tighter-0.031
 brid-0.030
Sleep-0.027
Token looked
Token ID3114
Feature activation+7.09e-02

Pos logit contributions
tub+0.013
room+0.013
 port+0.013
 site+0.012
 factory+0.012
Neg logit contributions
aid-0.011
 tighter-0.009
 reins-0.008
 brid-0.008
 scar-0.008
Token at
Token ID379
Feature activation+1.44e-01

Pos logit contributions
room+0.121
tub+0.119
 site+0.118
 port+0.112
 factory+0.112
Neg logit contributions
aid-0.135
 tighter-0.118
 reins-0.117
 brid-0.109
 scar-0.103
Token her
Token ID607
Feature activation-7.62e-02

Pos logit contributions
tub+0.262
room+0.256
 site+0.255
 port+0.252
 factory+0.250
Neg logit contributions
aid-0.252
 reins-0.214
 tighter-0.206
 brid-0.196
 scar-0.180
Token and
Token ID290
Feature activation-2.02e-02

Pos logit contributions
aid+0.148
 reins+0.125
 tighter+0.119
 brid+0.114
Sleep+0.108
Neg logit contributions
tub-0.125
room-0.124
 site-0.123
 factory-0.122
 port-0.122
Token smiled
Token ID13541
Feature activation-6.21e-02

Pos logit contributions
aid+0.035
 tighter+0.030
 reins+0.029
 brid+0.028
 scar+0.026
Neg logit contributions
room-0.038
tub-0.038
 port-0.036
 site-0.036
 factory-0.035
Token.
Token ID13
Feature activation-2.55e-03

Pos logit contributions
aid+0.150
 reins+0.133
 brid+0.119
 tighter+0.115
 fiber+0.113
Neg logit contributions
tub-0.079
 port-0.072
room-0.072
apped-0.071
ap-0.069
Token He
Token ID679
Feature activation-3.34e-02

Pos logit contributions
aid+0.005
 reins+0.004
 tighter+0.004
 brid+0.004
Sleep+0.003
Neg logit contributions
tub-0.004
room-0.004
 site-0.004
 port-0.004
 factory-0.004
Token,
Token ID11
Feature activation+4.91e-02

Pos logit contributions
tub+0.006
 site+0.006
 port+0.006
room+0.006
 factory+0.006
Neg logit contributions
aid-0.007
 reins-0.006
 tighter-0.006
 brid-0.005
 scar-0.005
Token no
Token ID645
Feature activation-2.71e-03

Pos logit contributions
 factory+0.080
room+0.080
tub+0.080
 port+0.079
 site+0.079
Neg logit contributions
aid-0.093
 reins-0.081
 tighter-0.077
 brid-0.075
Sleep-0.068
Token!"
Token ID2474
Feature activation-2.08e-02

Pos logit contributions
aid+0.006
 reins+0.005
 tighter+0.005
 brid+0.004
 scar+0.004
Neg logit contributions
tub-0.004
room-0.004
 site-0.004
 port-0.004
 factory-0.004
Token Mom
Token ID11254
Feature activation+5.57e-02

Pos logit contributions
aid+0.037
 reins+0.030
 tighter+0.030
 brid+0.028
 scar+0.026
Neg logit contributions
tub-0.038
room-0.037
 site-0.037
 port-0.036
 factory-0.036
Token says
Token ID1139
Feature activation+5.50e-02

Pos logit contributions
tub+0.082
room+0.080
 site+0.080
 port+0.079
 factory+0.078
Neg logit contributions
aid-0.117
 reins-0.102
 tighter-0.098
 brid-0.094
 scar-0.088
Token.
Token ID13
Feature activation-1.99e-03

Pos logit contributions
tub+0.086
room+0.085
 site+0.084
 factory+0.083
 port+0.082
Neg logit contributions
aid-0.109
 reins-0.096
 tighter-0.090
 brid-0.089
Sleep-0.082
Token "
Token ID366
Feature activation-9.70e-03

Pos logit contributions
aid+0.005
 reins+0.004
 tighter+0.004
 brid+0.004
 scar+0.004
Neg logit contributions
tub-0.002
 factory-0.002
room-0.002
 site-0.002
 port-0.002
TokenWhat
Token ID2061
Feature activation-1.30e-01

Pos logit contributions
aid+0.014
 reins+0.013
 tighter+0.012
 brid+0.012
 scar+0.012
Neg logit contributions
room-0.020
tub-0.019
 site-0.018
 factory-0.018
auc-0.017
Token happened
Token ID3022
Feature activation+4.28e-02

Pos logit contributions
aid+0.242
 tighter+0.189
 listen+0.186
 reins+0.182
Sleep+0.179
Neg logit contributions
 site-0.226
tub-0.218
 port-0.214
 factory-0.208
aded-0.201
Token here
Token ID994
Feature activation+2.53e-02

Pos logit contributions
tub+0.059
room+0.058
 factory+0.058
 site+0.057
 port+0.057
Neg logit contributions
aid-0.097
 reins-0.086
 tighter-0.082
 brid-0.079
Sleep-0.073
Token?"
Token ID1701
Feature activation-2.00e-02

Pos logit contributions
tub+0.044
 site+0.043
room+0.042
apped+0.042
 port+0.042
Neg logit contributions
aid-0.042
 tighter-0.034
 reins-0.033
 brid-0.032
 listen-0.032
Token."
Token ID526
Feature activation-1.99e-02

Pos logit contributions
aid+0.095
 reins+0.083
 tighter+0.079
 brid+0.076
Sleep+0.070
Neg logit contributions
tub-0.078
room-0.077
 site-0.076
 port-0.075
 factory-0.075
Token
Token ID220
Feature activation-2.60e-02

Pos logit contributions
aid+0.040
 tighter+0.033
 reins+0.032
 brid+0.030
Sleep+0.030
Neg logit contributions
 site-0.032
 port-0.031
room-0.031
 factory-0.030
tub-0.030
Token
Token ID198
Feature activation+4.77e-03

Pos logit contributions
aid+0.031
She+0.021
He+0.020
 tighter+0.018
 reins+0.017
Neg logit contributions
 factory-0.063
 port-0.062
 nation-0.062
 site-0.062
 structure-0.060
Token
Token ID198
Feature activation+4.74e-03

Pos logit contributions
tub+0.008
room+0.008
 site+0.008
 port+0.008
 factory+0.008
Neg logit contributions
aid-0.009
 reins-0.008
 tighter-0.008
 brid-0.007
Sleep-0.007
TokenL
Token ID43
Feature activation+3.43e-02

Pos logit contributions
room+0.009
tub+0.009
 site+0.009
 factory+0.009
 port+0.009
Neg logit contributions
aid-0.008
 reins-0.007
 tighter-0.006
 brid-0.006
 scar-0.006
Tokenily
Token ID813
Feature activation+5.59e-03

Pos logit contributions
 site+0.055
 port+0.054
tub+0.053
 factory+0.053
room+0.050
Neg logit contributions
aid-0.070
 tighter-0.056
 reins-0.055
Sleep-0.051
 brid-0.050
Token felt
Token ID2936
Feature activation-5.26e-02

Pos logit contributions
tub+0.009
room+0.009
 site+0.008
 factory+0.008
 port+0.008
Neg logit contributions
aid-0.011
 reins-0.010
 tighter-0.009
 brid-0.009
Sleep-0.008
Token happy
Token ID3772
Feature activation-4.79e-02

Pos logit contributions
 reins+0.102
aid+0.098
 brid+0.086
 tighter+0.083
 scar+0.080
Neg logit contributions
 port-0.076
tub-0.075
iggle-0.072
 factory-0.072
room-0.071
Token that
Token ID326
Feature activation+6.39e-02

Pos logit contributions
aid+0.108
 reins+0.107
 brid+0.092
 tighter+0.088
 fiber+0.085
Neg logit contributions
tub-0.062
iggle-0.058
apped-0.057
 factory-0.056
 port-0.056
Token she
Token ID673
Feature activation-1.67e-02

Pos logit contributions
tub+0.136
room+0.135
 site+0.135
 port+0.131
 factory+0.131
Neg logit contributions
aid-0.091
 reins-0.073
 tighter-0.071
 brid-0.065
Sleep-0.059
Token helped
Token ID4193
Feature activation-3.49e-02

Pos logit contributions
aid+0.036
 reins+0.033
 tighter+0.031
 brid+0.030
 scar+0.028
Neg logit contributions
tub-0.023
room-0.023
 factory-0.022
 port-0.021
 site-0.021
Token and
Token ID290
Feature activation-2.84e-02

Pos logit contributions
aid+0.131
 reins+0.111
 tighter+0.105
 brid+0.101
Sleep+0.093
Neg logit contributions
tub-0.125
room-0.125
 site-0.124
 port-0.122
 factory-0.122
Token everyone
Token ID2506
Feature activation+8.59e-03

Pos logit contributions
aid+0.046
 tighter+0.039
 reins+0.037
 brid+0.036
 scar+0.034
Neg logit contributions
room-0.054
tub-0.054
 site-0.053
auc-0.052
 factory-0.052
Token had
Token ID550
Feature activation-3.92e-02

Pos logit contributions
 site+0.015
room+0.015
 port+0.015
 factory+0.015
tub+0.015
Neg logit contributions
aid-0.016
 tighter-0.012
 reins-0.012
 brid-0.012
 care-0.011
Token fun
Token ID1257
Feature activation-2.09e-02

Pos logit contributions
aid+0.073
 reins+0.062
 tighter+0.059
 brid+0.057
Sleep+0.052
Neg logit contributions
tub-0.067
room-0.066
 site-0.066
 port-0.065
 factory-0.065
Token dancing
Token ID15360
Feature activation+2.26e-02

Pos logit contributions
aid+0.045
 reins+0.040
 tighter+0.038
 brid+0.037
Sleep+0.034
Neg logit contributions
tub-0.029
room-0.029
 site-0.028
 port-0.028
 factory-0.028
Token.
Token ID13
Feature activation-9.79e-03

Pos logit contributions
tub+0.036
room+0.036
 site+0.035
 factory+0.035
 port+0.035
Neg logit contributions
aid-0.044
 reins-0.038
 tighter-0.037
 brid-0.035
Sleep-0.032
Token The
Token ID383
Feature activation-3.53e-03

Pos logit contributions
aid+0.012
Sleep+0.010
Don+0.010
Do+0.010
 reins+0.009
Neg logit contributions
auc-0.020
 site-0.020
room-0.020
tub-0.020
iggle-0.019
Token end
Token ID886
Feature activation-1.14e-01

Pos logit contributions
aid+0.007
 reins+0.006
 tighter+0.006
 brid+0.006
 bleed+0.005
Neg logit contributions
 factory-0.005
 port-0.005
tub-0.005
 nation-0.005
 site-0.005
Token.
Token ID13
Feature activation-9.01e-03

Pos logit contributions
aid+0.234
 reins+0.211
 tighter+0.194
 brid+0.191
 scar+0.173
Neg logit contributions
tub-0.175
 site-0.173
room-0.173
 factory-0.171
 port-0.166
Token<|endoftext|>
Token ID50256
Feature activation-9.12e-02

Pos logit contributions
aid+0.015
 reins+0.012
 tighter+0.012
 brid+0.011
Sleep+0.011
Neg logit contributions
 site-0.017
tub-0.017
room-0.017
 port-0.017
 factory-0.017
TokenOnce
Token ID7454
Feature activation-5.13e-03

Pos logit contributions
aid+0.136
 reins+0.109
 tighter+0.102
Sleep+0.100
 brid+0.100
Neg logit contributions
 site-0.175
 port-0.174
 factory-0.173
tub-0.173
auc-0.169
Token had
Token ID550
Feature activation-4.83e-02

Pos logit contributions
aid+0.110
 tighter+0.094
 reins+0.093
 brid+0.089
 scar+0.083
Neg logit contributions
room-0.079
 site-0.077
tub-0.077
 port-0.076
 factory-0.075
Token to
Token ID284
Feature activation-5.32e-02

Pos logit contributions
aid+0.091
 reins+0.079
 tighter+0.075
 brid+0.072
Sleep+0.066
Neg logit contributions
tub-0.080
room-0.079
 site-0.078
 port-0.078
 factory-0.077
Token be
Token ID307
Feature activation-1.48e-01

Pos logit contributions
aid+0.086
 reins+0.075
 tighter+0.070
 brid+0.065
 scar+0.060
Neg logit contributions
room-0.102
 port-0.101
 site-0.099
tub-0.099
 factory-0.097
Token very
Token ID845
Feature activation+6.50e-03

Pos logit contributions
aid+0.279
 reins+0.246
 tighter+0.229
 brid+0.223
Sleep+0.206
Neg logit contributions
tub-0.245
 site-0.240
room-0.240
 port-0.238
 factory-0.236
Token special
Token ID2041
Feature activation+5.06e-02

Pos logit contributions
tub+0.011
 site+0.011
room+0.011
 port+0.011
 factory+0.011
Neg logit contributions
aid-0.012
 reins-0.010
 tighter-0.010
 brid-0.009
Sleep-0.009
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
tub+0.081
room+0.079
 site+0.079
 factory+0.078
 port+0.078
Neg logit contributions
aid-0.101
 reins-0.087
 tighter-0.082
 brid-0.080
Sleep-0.074
Token She
Token ID1375
Feature activation-7.74e-02

Pos logit contributions
aid+0.028
 reins+0.024
 tighter+0.023
 brid+0.022
Sleep+0.020
Neg logit contributions
tub-0.025
room-0.025
 site-0.025
 port-0.024
 factory-0.024
Token thanked
Token ID26280
Feature activation-6.75e-02

Pos logit contributions
aid+0.135
 reins+0.113
 tighter+0.111
 brid+0.107
 scar+0.098
Neg logit contributions
tub-0.141
room-0.141
 site-0.138
 factory-0.136
 port-0.136
Token Sam
Token ID3409
Feature activation+4.46e-02

Pos logit contributions
aid+0.143
 reins+0.122
 tighter+0.118
 brid+0.113
Sleep+0.108
Neg logit contributions
room-0.099
 site-0.095
 port-0.095
 factory-0.094
tub-0.094
Token again
Token ID757
Feature activation-7.63e-02

Pos logit contributions
tub+0.069
room+0.068
 port+0.067
 factory+0.067
 site+0.066
Neg logit contributions
aid-0.089
 reins-0.075
 brid-0.069
 tighter-0.067
 bleed-0.067
Token and
Token ID290
Feature activation-3.10e-02

Pos logit contributions
aid+0.165
 reins+0.140
 bleed+0.128
 brid+0.127
 tighter+0.127
Neg logit contributions
 site-0.113
room-0.109
 port-0.109
 factory-0.109
tub-0.108
Token her
Token ID607
Feature activation-7.60e-02

Pos logit contributions
aid+0.106
 reins+0.100
 tighter+0.090
 brid+0.090
Sleep+0.084
Neg logit contributions
tub-0.072
 port-0.069
 factory-0.069
room-0.068
 site-0.066
Token dress
Token ID6576
Feature activation-1.76e-02

Pos logit contributions
aid+0.141
 reins+0.122
 tighter+0.116
 brid+0.111
 scar+0.102
Neg logit contributions
tub-0.130
room-0.129
 site-0.129
 factory-0.126
 port-0.125
Token.
Token ID13
Feature activation-2.97e-03

Pos logit contributions
aid+0.033
 reins+0.029
 tighter+0.026
 brid+0.026
Sleep+0.025
Neg logit contributions
room-0.030
tub-0.029
 site-0.028
 factory-0.028
 port-0.028
Token She
Token ID1375
Feature activation-6.72e-02

Pos logit contributions
aid+0.005
 reins+0.004
 tighter+0.004
 brid+0.004
Sleep+0.004
Neg logit contributions
tub-0.005
room-0.005
 site-0.005
 factory-0.005
 port-0.005
Token saw
Token ID2497
Feature activation+7.77e-02

Pos logit contributions
aid+0.126
 reins+0.108
 tighter+0.103
 brid+0.099
Sleep+0.091
Neg logit contributions
tub-0.114
room-0.112
 site-0.112
 port-0.110
 factory-0.110
Token the
Token ID262
Feature activation-1.02e-02

Pos logit contributions
tub+0.151
room+0.149
 site+0.149
 port+0.147
 factory+0.147
Neg logit contributions
aid-0.127
 reins-0.105
 tighter-0.100
 brid-0.095
 scar-0.086
Token hole
Token ID7604
Feature activation+7.55e-02

Pos logit contributions
aid+0.022
 reins+0.020
 tighter+0.019
 brid+0.018
Sleep+0.017
Neg logit contributions
tub-0.015
 factory-0.015
 port-0.014
 site-0.014
room-0.014
Token.
Token ID13
Feature activation-2.73e-03

Pos logit contributions
 port+0.135
tub+0.134
 site+0.134
 factory+0.133
room+0.132
Neg logit contributions
aid-0.129
 tighter-0.110
 reins-0.106
 brid-0.096
 bleed-0.091
Token She
Token ID1375
Feature activation-6.67e-02

Pos logit contributions
aid+0.005
 reins+0.004
 tighter+0.004
 brid+0.004
Sleep+0.003
Neg logit contributions
tub-0.005
room-0.005
 site-0.005
 factory-0.005
 port-0.005
Token was
Token ID373
Feature activation+9.90e-02

Pos logit contributions
aid+0.135
 reins+0.120
 tighter+0.112
 brid+0.109
Sleep+0.103
Neg logit contributions
tub-0.099
room-0.099
 site-0.098
 factory-0.096
 port-0.095
Token sad
Token ID6507
Feature activation+1.30e-02

Pos logit contributions
room+0.179
tub+0.178
 site+0.176
 port+0.174
 factory+0.174
Neg logit contributions
aid-0.177
 reins-0.146
 tighter-0.144
 brid-0.135
 bleed-0.127
Token eager
Token ID11069
Feature activation+5.75e-02

Pos logit contributions
aid+0.058
 reins+0.050
 tighter+0.048
 brid+0.046
Sleep+0.042
Neg logit contributions
tub-0.055
room-0.055
 site-0.054
 port-0.053
 factory-0.053
Token to
Token ID284
Feature activation-4.56e-02

Pos logit contributions
room+0.125
tub+0.125
 site+0.124
 port+0.122
 factory+0.122
Neg logit contributions
aid-0.076
 reins-0.063
 tighter-0.060
 brid-0.055
 scar-0.050
Token play
Token ID711
Feature activation-3.91e-02

Pos logit contributions
aid+0.063
 reins+0.052
 tighter+0.047
 brid+0.046
 listen+0.042
Neg logit contributions
tub-0.098
room-0.095
 site-0.095
 factory-0.094
auc-0.093
Token with
Token ID351
Feature activation+1.26e-01

Pos logit contributions
aid+0.081
 reins+0.070
 tighter+0.068
 brid+0.067
 scar+0.062
Neg logit contributions
tub-0.055
 site-0.053
room-0.053
 factory-0.053
 port-0.052
Token her
Token ID607
Feature activation-8.09e-02

Pos logit contributions
tub+0.320
 site+0.307
 port+0.303
room+0.301
auc+0.299
Neg logit contributions
aid-0.143
 reins-0.101
 tighter-0.093
 brid-0.089
 scar-0.085
Token friends
Token ID2460
Feature activation-2.52e-02

Pos logit contributions
aid+0.133
 reins+0.121
 brid+0.111
 tighter+0.107
 scar+0.105
Neg logit contributions
room-0.145
auc-0.145
 site-0.142
tub-0.140
aded-0.140
Token.
Token ID13
Feature activation-8.08e-03

Pos logit contributions
aid+0.042
 reins+0.037
 tighter+0.036
 brid+0.034
 scar+0.031
Neg logit contributions
 site-0.045
tub-0.045
room-0.044
 port-0.043
auc-0.042
Token One
Token ID1881
Feature activation-3.34e-02

Pos logit contributions
aid+0.012
 reins+0.010
 tighter+0.010
She+0.010
Sleep+0.009
Neg logit contributions
 site-0.015
aded-0.015
tub-0.015
auc-0.014
uders-0.014
Token day
Token ID1110
Feature activation+2.07e-02

Pos logit contributions
aid+0.052
 tighter+0.044
 listen+0.044
Sleep+0.042
 reins+0.042
Neg logit contributions
 site-0.064
uders-0.062
room-0.062
tub-0.060
auc-0.060
Token,
Token ID11
Feature activation+3.90e-02

Pos logit contributions
 site+0.040
tub+0.039
 port+0.038
auc+0.037
room+0.037
Neg logit contributions
aid-0.034
 tighter-0.026
 reins-0.026
 care-0.026
 listen-0.025
Token Lily
Token ID20037
Feature activation+2.29e-02

Pos logit contributions
 site+0.068
tub+0.067
room+0.067
 factory+0.065
 port+0.065
Neg logit contributions
aid-0.071
 reins-0.059
 tighter-0.059
 brid-0.055
 scar-0.052
Token at
Token ID379
Feature activation+1.43e-01

Pos logit contributions
aid+0.090
 reins+0.077
 tighter+0.076
 brid+0.072
Sleep+0.066
Neg logit contributions
tub-0.083
room-0.083
 site-0.081
 factory-0.081
 port-0.081
Token night
Token ID1755
Feature activation-2.00e-02

Pos logit contributions
tub+0.264
room+0.260
auc+0.256
 site+0.254
iced+0.250
Neg logit contributions
aid-0.232
 reins-0.199
 tighter-0.199
 brid-0.180
 care-0.169
Token.
Token ID13
Feature activation-2.28e-03

Pos logit contributions
aid+0.022
 tighter+0.019
 reins+0.018
ache+0.017
 brid+0.017
Neg logit contributions
aded-0.042
auc-0.041
unky-0.041
room-0.041
agically-0.041
Token The
Token ID383
Feature activation+6.13e-03

Pos logit contributions
aid+0.003
 tighter+0.003
He+0.002
Sleep+0.002
Don+0.002
Neg logit contributions
 port-0.005
room-0.004
 nation-0.004
 site-0.004
tub-0.004
Token monster
Token ID9234
Feature activation+6.93e-02

Pos logit contributions
tub+0.009
room+0.009
 site+0.009
 factory+0.008
 port+0.008
Neg logit contributions
aid-0.013
 reins-0.011
 tighter-0.011
 brid-0.011
Sleep-0.010
Token stayed
Token ID9658
Feature activation-5.67e-02

Pos logit contributions
room+0.127
tub+0.126
 port+0.123
 site+0.121
 factory+0.120
Neg logit contributions
aid-0.121
 tighter-0.103
 reins-0.099
 brid-0.096
 scar-0.091
Token under
Token ID739
Feature activation+1.44e-01

Pos logit contributions
aid+0.106
 reins+0.091
 tighter+0.090
 brid+0.085
 scar+0.078
Neg logit contributions
tub-0.095
room-0.095
 site-0.093
 factory-0.092
 port-0.092
Token his
Token ID465
Feature activation-2.87e-02

Pos logit contributions
auc+0.327
tub+0.327
iced+0.324
ook+0.313
aded+0.312
Neg logit contributions
aid-0.160
 tighter-0.129
 care-0.128
 reins-0.127
 advice-0.111
Token bed
Token ID3996
Feature activation-4.18e-02

Pos logit contributions
aid+0.053
 reins+0.047
 tighter+0.045
 brid+0.043
 scar+0.040
Neg logit contributions
room-0.048
tub-0.048
 site-0.047
 factory-0.047
 port-0.046
Token,
Token ID11
Feature activation+4.50e-02

Pos logit contributions
aid+0.066
 tighter+0.056
 reins+0.054
 brid+0.053
 scar+0.048
Neg logit contributions
 port-0.075
auc-0.075
 factory-0.074
room-0.074
tub-0.073
Token and
Token ID290
Feature activation-1.93e-02

Pos logit contributions
tub+0.082
room+0.081
 site+0.081
 port+0.080
 factory+0.080
Neg logit contributions
aid-0.078
 reins-0.066
 tighter-0.063
 brid-0.060
Sleep-0.055
Token much
Token ID881
Feature activation-4.29e-02

Pos logit contributions
 site+0.082
room+0.082
tub+0.081
 factory+0.079
 port+0.079
Neg logit contributions
aid-0.071
 reins-0.054
 tighter-0.054
 brid-0.050
Sleep-0.049
Token fun
Token ID1257
Feature activation-1.85e-02

Pos logit contributions
aid+0.079
 reins+0.068
 tighter+0.065
 brid+0.062
Sleep+0.057
Neg logit contributions
tub-0.073
room-0.072
 site-0.072
 port-0.071
 factory-0.071
Token at
Token ID379
Feature activation+1.37e-01

Pos logit contributions
aid+0.038
 reins+0.033
 tighter+0.032
 brid+0.030
Sleep+0.028
Neg logit contributions
tub-0.028
room-0.028
 site-0.028
 factory-0.027
 port-0.027
Token the
Token ID262
Feature activation-1.65e-02

Pos logit contributions
tub+0.233
room+0.230
 site+0.229
 port+0.227
 factory+0.227
Neg logit contributions
aid-0.256
 reins-0.219
 tighter-0.209
 brid-0.200
Sleep-0.183
Token park
Token ID3952
Feature activation+5.40e-02

Pos logit contributions
aid+0.032
 reins+0.030
 tighter+0.029
 brid+0.029
Dear+0.027
Neg logit contributions
tub-0.023
room-0.023
apped-0.022
auc-0.022
aded-0.021
Token."
Token ID526
Feature activation-2.53e-02

Pos logit contributions
tub+0.106
 port+0.106
 site+0.105
room+0.105
 factory+0.104
Neg logit contributions
aid-0.077
 reins-0.065
 tighter-0.063
 brid-0.059
Sleep-0.054
Token Her
Token ID2332
Feature activation-6.41e-02

Pos logit contributions
aid+0.042
 tighter+0.033
 reins+0.033
Sleep+0.031
 brid+0.030
Neg logit contributions
 site-0.049
 port-0.047
 factory-0.046
room-0.046
tub-0.046
Token mom
Token ID1995
Feature activation-5.41e-03

Pos logit contributions
aid+0.144
 reins+0.127
 tighter+0.121
 brid+0.118
Sleep+0.111
Neg logit contributions
tub-0.086
room-0.083
 port-0.083
 factory-0.083
 site-0.082
Token smiled
Token ID13541
Feature activation-6.91e-02

Pos logit contributions
aid+0.009
 reins+0.007
 tighter+0.007
 brid+0.007
 scar+0.006
Neg logit contributions
tub-0.010
room-0.010
 site-0.010
 port-0.010
 factory-0.010
Token and
Token ID290
Feature activation-2.93e-02

Pos logit contributions
aid+0.158
 reins+0.139
 fiber+0.124
 bleed+0.123
 brid+0.122
Neg logit contributions
tub-0.091
apped-0.091
 port-0.086
room-0.085
ap-0.085
Token said
Token ID531
Feature activation+6.03e-02

Pos logit contributions
aid+0.057
 reins+0.049
 tighter+0.047
 brid+0.045
Sleep+0.042
Neg logit contributions
tub-0.048
room-0.047
 site-0.047
 port-0.046
 factory-0.046
Token win
Token ID1592
Feature activation-6.28e-02

Pos logit contributions
aid+0.189
 reins+0.164
 tighter+0.157
 brid+0.150
 scar+0.139
Neg logit contributions
tub-0.164
room-0.163
 site-0.161
 port-0.158
 factory-0.157
Token that
Token ID326
Feature activation+4.26e-02

Pos logit contributions
aid+0.106
 reins+0.088
 tighter+0.087
 brid+0.080
 bud+0.073
Neg logit contributions
tub-0.112
 port-0.111
 site-0.110
 factory-0.109
room-0.108
Token she
Token ID673
Feature activation-3.99e-02

Pos logit contributions
tub+0.072
room+0.072
 site+0.071
 port+0.069
 factory+0.068
Neg logit contributions
aid-0.077
 reins-0.066
 tighter-0.065
 brid-0.061
 scar-0.057
Token kept
Token ID4030
Feature activation-4.47e-02

Pos logit contributions
aid+0.070
 reins+0.058
 tighter+0.056
 brid+0.054
 scar+0.049
Neg logit contributions
tub-0.072
room-0.072
 site-0.072
 port-0.070
 factory-0.070
Token the
Token ID262
Feature activation-2.89e-02

Pos logit contributions
aid+0.089
 reins+0.076
 tighter+0.073
 brid+0.070
Sleep+0.067
Neg logit contributions
room-0.070
 site-0.069
tub-0.069
 factory-0.069
 port-0.068
Token trophy
Token ID16383
Feature activation-5.10e-02

Pos logit contributions
aid+0.057
 reins+0.049
 tighter+0.047
 brid+0.045
Sleep+0.042
Neg logit contributions
tub-0.046
room-0.045
 site-0.045
 port-0.045
 factory-0.045
Token in
Token ID287
Feature activation+8.23e-02

Pos logit contributions
aid+0.100
 reins+0.086
 tighter+0.081
 brid+0.079
Sleep+0.074
Neg logit contributions
tub-0.081
room-0.080
 site-0.079
 port-0.079
 factory-0.078
Token her
Token ID607
Feature activation-9.71e-02

Pos logit contributions
room+0.152
tub+0.148
 site+0.148
 port+0.148
 factory+0.146
Neg logit contributions
aid-0.145
 reins-0.121
 tighter-0.112
 brid-0.110
Sleep-0.100
Token room
Token ID2119
Feature activation+5.00e-02

Pos logit contributions
aid+0.158
 reins+0.140
 tighter+0.137
 brid+0.131
 scar+0.120
Neg logit contributions
room-0.178
tub-0.175
auc-0.174
 site-0.171
ide-0.169
Token.
Token ID13
Feature activation-1.89e-02

Pos logit contributions
tub+0.089
room+0.088
 site+0.088
 port+0.087
 factory+0.087
Neg logit contributions
aid-0.085
 reins-0.072
 tighter-0.071
 brid-0.066
 scar-0.060
Token Every
Token ID3887
Feature activation-2.22e-02

Pos logit contributions
aid+0.033
 reins+0.028
 tighter+0.026
 brid+0.025
Sleep+0.024
Neg logit contributions
tub-0.034
 site-0.034
room-0.033
 port-0.033
 factory-0.033
Token to
Token ID284
Feature activation-4.02e-02

Pos logit contributions
aid+0.235
 reins+0.197
 brid+0.182
 tighter+0.182
 bleed+0.169
Neg logit contributions
 port-0.234
 site-0.231
 factory-0.231
tub-0.229
room-0.221
Token pay
Token ID1414
Feature activation-5.59e-02

Pos logit contributions
aid+0.071
 reins+0.060
 tighter+0.056
 brid+0.054
Sleep+0.050
Neg logit contributions
room-0.072
 port-0.072
 site-0.071
 factory-0.070
ap-0.069
Token for
Token ID329
Feature activation+2.24e-02

Pos logit contributions
aid+0.098
 reins+0.084
 tighter+0.079
 brid+0.076
Sleep+0.070
Neg logit contributions
tub-0.100
room-0.099
 site-0.099
 port-0.097
 factory-0.097
Token food
Token ID2057
Feature activation-3.05e-02

Pos logit contributions
 site+0.035
 port+0.034
 factory+0.034
room+0.033
tub+0.033
Neg logit contributions
aid-0.045
 reins-0.038
 tighter-0.037
 brid-0.035
Sleep-0.033
Token,
Token ID11
Feature activation+4.96e-02

Pos logit contributions
aid+0.054
 reins+0.046
 tighter+0.044
 brid+0.042
Sleep+0.038
Neg logit contributions
tub-0.054
room-0.053
 site-0.053
 port-0.052
 factory-0.052
Token clothes
Token ID8242
Feature activation-3.34e-02

Pos logit contributions
tub+0.086
room+0.085
 site+0.085
 port+0.084
 factory+0.084
Neg logit contributions
aid-0.090
 reins-0.077
 tighter-0.073
 brid-0.070
Sleep-0.064
Token,
Token ID11
Feature activation+4.96e-02

Pos logit contributions
aid+0.069
 reins+0.061
 tighter+0.058
 brid+0.056
Sleep+0.052
Neg logit contributions
tub-0.050
room-0.049
 site-0.048
 factory-0.048
 port-0.048
Token rent
Token ID5602
Feature activation-1.16e-01

Pos logit contributions
tub+0.078
 port+0.077
room+0.077
 site+0.077
 factory+0.076
Neg logit contributions
aid-0.095
 reins-0.082
 tighter-0.078
 brid-0.075
Dear-0.070
Token and
Token ID290
Feature activation-1.71e-02

Pos logit contributions
aid+0.220
 reins+0.190
 tighter+0.181
 brid+0.174
Sleep+0.160
Neg logit contributions
tub-0.191
room-0.189
 site-0.187
 port-0.185
 factory-0.185
Token other
Token ID584
Feature activation+2.72e-02

Pos logit contributions
aid+0.030
 reins+0.026
 tighter+0.025
 brid+0.024
Dear+0.021
Neg logit contributions
 port-0.029
 factory-0.029
 site-0.028
tub-0.028
 nation-0.027
Token things
Token ID1243
Feature activation-8.64e-02

Pos logit contributions
tub+0.042
 port+0.042
 site+0.042
 factory+0.042
room+0.041
Neg logit contributions
aid-0.054
 reins-0.046
 tighter-0.044
 brid-0.042
Sleep-0.039
Token loved
Token ID6151
Feature activation+2.52e-03

Pos logit contributions
aid+0.145
 tighter+0.122
 reins+0.117
 brid+0.115
 scar+0.109
Neg logit contributions
room-0.146
tub-0.145
 site-0.144
 port-0.142
 factory-0.141
Token it
Token ID340
Feature activation-1.50e-02

Pos logit contributions
tub+0.004
room+0.004
 site+0.004
 factory+0.004
 port+0.004
Neg logit contributions
aid-0.005
 reins-0.004
 tighter-0.004
 brid-0.004
Sleep-0.003
Token!
Token ID0
Feature activation+3.25e-02

Pos logit contributions
aid+0.027
 reins+0.023
 tighter+0.023
 brid+0.022
Sleep+0.020
Neg logit contributions
tub-0.025
 site-0.025
room-0.025
 port-0.025
 factory-0.025
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
tub+0.054
 site+0.053
room+0.053
 port+0.052
 factory+0.052
Neg logit contributions
aid-0.062
 reins-0.053
 tighter-0.051
 brid-0.049
Sleep-0.045
Token
Token ID198
Feature activation-9.88e-03

Pos logit contributions
aid+0.018
 reins+0.015
 tighter+0.015
 brid+0.014
Sleep+0.013
Neg logit contributions
tub-0.018
room-0.018
 site-0.018
 port-0.018
 factory-0.018
Token"
Token ID1
Feature activation-1.78e-01

Pos logit contributions
aid+0.014
 reins+0.012
 tighter+0.011
 brid+0.010
 bleed+0.009
Neg logit contributions
room-0.021
tub-0.021
 site-0.021
 factory-0.021
 port-0.021
TokenCan
Token ID6090
Feature activation-1.14e-01

Pos logit contributions
aid+0.268
 reins+0.242
 tighter+0.222
 brid+0.212
 bleed+0.211
Neg logit contributions
room-0.364
tub-0.336
 Fourth-0.328
 factory-0.325
 site-0.322
Token I
Token ID314
Feature activation-6.04e-03

Pos logit contributions
aid+0.227
 reins+0.200
 tighter+0.189
 brid+0.183
 scar+0.168
Neg logit contributions
tub-0.176
room-0.176
 factory-0.173
 site-0.173
 port-0.171
Token have
Token ID423
Feature activation-1.53e-01

Pos logit contributions
aid+0.010
 reins+0.009
 tighter+0.008
 brid+0.008
Sleep+0.007
Neg logit contributions
room-0.012
tub-0.012
 port-0.011
 factory-0.011
 site-0.011
Token my
Token ID616
Feature activation-5.61e-02

Pos logit contributions
aid+0.292
 reins+0.256
 tighter+0.243
 brid+0.234
Sleep+0.214
Neg logit contributions
tub-0.243
room-0.242
 site-0.242
 port-0.242
 factory-0.240
Token own
Token ID898
Feature activation+1.20e-02

Pos logit contributions
aid+0.114
 reins+0.102
 tighter+0.097
 brid+0.093
 scar+0.093
Neg logit contributions
room-0.082
 site-0.081
tub-0.079
 port-0.075
 factory-0.074
Token!"
Token ID2474
Feature activation-2.69e-02

Pos logit contributions
aid+0.023
 reins+0.020
 tighter+0.018
 brid+0.018
Sleep+0.017
Neg logit contributions
room-0.021
tub-0.020
 site-0.020
 port-0.020
 factory-0.020
Token Lily
Token ID20037
Feature activation+1.69e-02

Pos logit contributions
aid+0.053
 tighter+0.043
 reins+0.043
 brid+0.040
 scar+0.037
Neg logit contributions
 port-0.045
 site-0.045
tub-0.044
 factory-0.044
room-0.044
Token said
Token ID531
Feature activation+5.73e-02

Pos logit contributions
tub+0.029
 site+0.029
 port+0.029
room+0.028
 factory+0.028
Neg logit contributions
aid-0.032
 tighter-0.026
 reins-0.026
 brid-0.025
 scar-0.023
Token with
Token ID351
Feature activation+1.21e-01

Pos logit contributions
tub+0.098
 site+0.096
room+0.096
 port+0.095
 factory+0.095
Neg logit contributions
aid-0.107
 reins-0.091
 tighter-0.088
 brid-0.083
Sleep-0.076
Token a
Token ID257
Feature activation-1.75e-02

Pos logit contributions
room+0.169
 port+0.169
 factory+0.155
 structure+0.151
 Jack+0.151
Neg logit contributions
aid-0.252
 reins-0.229
shadow-0.208
 tighter-0.204
 brid-0.203
Token smile
Token ID8212
Feature activation-1.88e-01

Pos logit contributions
aid+0.030
 reins+0.025
 tighter+0.023
Sleep+0.023
 brid+0.021
Neg logit contributions
tub-0.032
 port-0.032
room-0.031
 factory-0.031
 structure-0.030
Token.
Token ID13
Feature activation-8.09e-03

Pos logit contributions
aid+0.445
 reins+0.413
 brid+0.386
 tighter+0.374
Sleep+0.370
Neg logit contributions
room-0.223
tub-0.210
apped-0.208
 factory-0.197
ap-0.193
Token
Token ID198
Feature activation-3.70e-03

Pos logit contributions
aid+0.015
 reins+0.012
 tighter+0.012
 brid+0.011
She+0.011
Neg logit contributions
 site-0.014
 port-0.014
 factory-0.013
 nation-0.013
tub-0.013
Token
Token ID198
Feature activation-4.04e-03

Pos logit contributions
aid+0.006
 reins+0.004
 tighter+0.004
 brid+0.004
Sleep+0.004
Neg logit contributions
 port-0.007
tub-0.007
 factory-0.007
 site-0.007
 nation-0.007
TokenThey
Token ID2990
Feature activation-5.75e-02

Pos logit contributions
aid+0.006
 reins+0.005
 tighter+0.004
 brid+0.004
Sleep+0.004
Neg logit contributions
tub-0.009
 site-0.009
 port-0.008
 factory-0.008
room-0.008
Token carefully
Token ID7773
Feature activation-2.42e-02

Pos logit contributions
aid+0.105
 tighter+0.089
 reins+0.087
 brid+0.082
 scar+0.078
Neg logit contributions
tub-0.104
 site-0.103
 factory-0.100
room-0.098
auc-0.097
Token put
Token ID1234
Feature activation-5.66e-02

Pos logit contributions
 site+0.027
tub+0.027
room+0.026
 factory+0.026
 port+0.025
Neg logit contributions
aid-0.027
 reins-0.022
 tighter-0.022
 brid-0.021
 scar-0.020
Token on
Token ID319
Feature activation+1.23e-02

Pos logit contributions
aid+0.098
 reins+0.083
 tighter+0.080
 brid+0.076
 scar+0.070
Neg logit contributions
tub-0.105
 site-0.103
room-0.103
 factory-0.101
 port-0.100
Token their
Token ID511
Feature activation-1.19e-02

Pos logit contributions
tub+0.020
 site+0.019
room+0.019
 factory+0.018
auc+0.018
Neg logit contributions
aid-0.024
 reins-0.021
 tighter-0.021
 brid-0.020
 scar-0.020
Token hats
Token ID23910
Feature activation-7.18e-02

Pos logit contributions
aid+0.022
 reins+0.020
 tighter+0.019
 brid+0.018
 scar+0.017
Neg logit contributions
room-0.020
tub-0.020
 site-0.019
 factory-0.019
 port-0.018
Token and
Token ID290
Feature activation-3.03e-02

Pos logit contributions
aid+0.090
 reins+0.075
 tighter+0.073
 brid+0.068
 scar+0.060
Neg logit contributions
 site-0.159
 factory-0.155
aded-0.154
tub-0.154
room-0.152
Token scar
Token ID10153
Feature activation-2.16e-01

Pos logit contributions
aid+0.057
 reins+0.048
 tighter+0.046
 brid+0.044
Sleep+0.042
Neg logit contributions
tub-0.050
room-0.050
 port-0.050
 site-0.049
 factory-0.049
Tokenves
Token ID1158
Feature activation+1.50e-02

Pos logit contributions
aid+0.557
 reins+0.499
 tighter+0.484
 brid+0.471
Sleep+0.445
Neg logit contributions
tub-0.210
room-0.207
 site-0.204
 factory-0.200
 port-0.200
Token and
Token ID290
Feature activation-2.99e-02

Pos logit contributions
tub+0.028
room+0.028
 site+0.027
 factory+0.027
 port+0.027
Neg logit contributions
aid-0.025
 reins-0.021
 tighter-0.020
 brid-0.019
 scar-0.017
Token got
Token ID1392
Feature activation-1.29e-02

Pos logit contributions
aid+0.056
 reins+0.049
 tighter+0.046
 brid+0.044
Sleep+0.042
Neg logit contributions
tub-0.049
room-0.049
 port-0.048
 site-0.048
 factory-0.048
Token their
Token ID511
Feature activation-9.42e-03

Pos logit contributions
aid+0.024
 reins+0.021
 tighter+0.020
 brid+0.019
Sleep+0.018
Neg logit contributions
tub-0.022
room-0.021
 site-0.021
 port-0.021
 factory-0.021
Token pots
Token ID32195
Feature activation+9.09e-02

Pos logit contributions
aid+0.018
 reins+0.016
 tighter+0.015
 brid+0.015
 scar+0.014
Neg logit contributions
room-0.015
tub-0.015
 site-0.015
 factory-0.014
 port-0.014
Token:
Token ID25
Feature activation+1.11e-03

Pos logit contributions
tub+0.082
room+0.081
 site+0.080
 port+0.079
 factory+0.079
Neg logit contributions
aid-0.128
 reins-0.112
 tighter-0.108
 brid-0.104
Sleep-0.098
Token You
Token ID921
Feature activation+6.29e-02

Pos logit contributions
 factory+0.002
room+0.002
 port+0.002
tub+0.002
 site+0.002
Neg logit contributions
aid-0.002
 reins-0.002
 brid-0.002
 tighter-0.002
 scar-0.002
Token should
Token ID815
Feature activation-7.35e-02

Pos logit contributions
 port+0.112
room+0.112
tub+0.112
 factory+0.111
 site+0.109
Neg logit contributions
aid-0.110
 reins-0.097
 tighter-0.092
 brid-0.087
Sleep-0.078
Token share
Token ID2648
Feature activation-1.63e-01

Pos logit contributions
aid+0.132
 reins+0.120
 tighter+0.111
 brid+0.106
 scar+0.098
Neg logit contributions
room-0.127
 port-0.126
 factory-0.126
ap-0.126
 nation-0.124
Token and
Token ID290
Feature activation-2.20e-02

Pos logit contributions
aid+0.304
 reins+0.262
 tighter+0.249
 brid+0.240
Sleep+0.220
Neg logit contributions
tub-0.274
room-0.272
 site-0.270
 port-0.267
 factory-0.266
Token respect
Token ID2461
Feature activation-2.00e-01

Pos logit contributions
aid+0.035
 reins+0.033
 brid+0.028
 tighter+0.027
ache+0.025
Neg logit contributions
 site-0.040
 nation-0.040
room-0.040
 factory-0.040
 port-0.040
Token others
Token ID1854
Feature activation-3.60e-02

Pos logit contributions
aid+0.374
 reins+0.320
 tighter+0.314
 brid+0.290
Sleep+0.273
Neg logit contributions
tub-0.338
 site-0.327
room-0.326
 port-0.322
 factory-0.319
Token who
Token ID508
Feature activation+5.98e-02

Pos logit contributions
aid+0.072
 reins+0.063
 tighter+0.059
 brid+0.058
 scar+0.054
Neg logit contributions
tub-0.055
room-0.055
 site-0.054
 factory-0.054
 port-0.053
Token need
Token ID761
Feature activation-6.59e-02

Pos logit contributions
tub+0.119
room+0.118
 site+0.117
 port+0.114
 factory+0.114
Neg logit contributions
aid-0.094
 reins-0.076
 tighter-0.073
 brid-0.068
Sleep-0.063
Token help
Token ID1037
Feature activation-9.64e-02

Pos logit contributions
aid+0.109
 reins+0.093
 tighter+0.087
 brid+0.084
 scar+0.076
Neg logit contributions
tub-0.123
room-0.122
 site-0.122
 port-0.121
 factory-0.120
Token.
Token ID13
Feature activation-5.64e-03

Pos logit contributions
aid+0.170
 tighter+0.143
 reins+0.143
 brid+0.128
 care+0.126
Neg logit contributions
tub-0.173
 site-0.169
room-0.165
 port-0.165
 factory-0.165
Token can
Token ID460
Feature activation-8.45e-02

Pos logit contributions
tub+0.005
room+0.005
 site+0.005
 factory+0.005
 port+0.005
Neg logit contributions
aid-0.004
 reins-0.003
 tighter-0.003
 brid-0.003
Sleep-0.002
Token help
Token ID1037
Feature activation-1.02e-01

Pos logit contributions
aid+0.131
 reins+0.107
 tighter+0.101
 brid+0.096
Sleep+0.086
Neg logit contributions
tub-0.171
 site-0.168
room-0.168
 factory-0.166
 port-0.166
Token you
Token ID345
Feature activation+7.30e-02

Pos logit contributions
aid+0.188
 reins+0.161
 tighter+0.155
 brid+0.147
Sleep+0.135
Neg logit contributions
tub-0.178
room-0.174
 site-0.173
 port-0.172
 factory-0.171
Token.
Token ID13
Feature activation-6.42e-03

Pos logit contributions
room+0.123
tub+0.123
 port+0.121
 site+0.120
 factory+0.119
Neg logit contributions
aid-0.138
 reins-0.120
 tighter-0.111
 brid-0.109
Sleep-0.101
Token I
Token ID314
Feature activation+3.88e-03

Pos logit contributions
aid+0.013
 reins+0.011
 tighter+0.011
 brid+0.010
Sleep+0.010
Neg logit contributions
tub-0.010
 site-0.010
room-0.010
 port-0.010
 factory-0.010
Token know
Token ID760
Feature activation-1.85e-01

Pos logit contributions
tub+0.008
room+0.008
 factory+0.008
 port+0.008
 site+0.008
Neg logit contributions
aid-0.006
 reins-0.005
 tighter-0.005
 brid-0.004
Sleep-0.004
Token how
Token ID703
Feature activation-1.23e-01

Pos logit contributions
aid+0.322
 reins+0.273
 tighter+0.262
 brid+0.248
Sleep+0.228
Neg logit contributions
tub-0.337
room-0.331
 site-0.329
 port-0.325
 factory-0.324
Token to
Token ID284
Feature activation-4.54e-02

Pos logit contributions
aid+0.217
 reins+0.190
 tighter+0.177
 brid+0.177
 scar+0.160
Neg logit contributions
tub-0.214
 factory-0.212
 port-0.212
 site-0.210
room-0.207
Token repair
Token ID9185
Feature activation-1.49e-02

Pos logit contributions
aid+0.078
 reins+0.070
 tighter+0.065
 brid+0.061
Sleep+0.058
Neg logit contributions
room-0.083
 port-0.080
 factory-0.080
 site-0.079
tub-0.079
Token cars
Token ID5006
Feature activation+3.63e-02

Pos logit contributions
aid+0.027
 reins+0.023
 tighter+0.022
 brid+0.021
 scar+0.019
Neg logit contributions
tub-0.027
room-0.026
 site-0.026
 port-0.026
 factory-0.026
Token,"
Token ID553
Feature activation-9.04e-02

Pos logit contributions
room+0.056
tub+0.055
 site+0.054
 factory+0.054
 port+0.053
Neg logit contributions
aid-0.073
 reins-0.066
 brid-0.060
 tighter-0.060
Sleep-0.057