TOP ACTIVATIONS
MAX = 4.221

holes in American politics ' MORE as a 68 - year
ice . V ox can beat Flip S id
than 10 years in prison MORE and tick ed through her
holes in American politics ' MORE completed a swing through North
t weet / <|endoftext|> Story highlights Secretary of Defense Chuck Hag
vote accordingly . <|endoftext|> Story highlights Police chief vows wanted suspect
holes in American politics ' MORE , told 77 WA BC
great mechanical stress ( bending open and slamming shut
forehead a butt - cr ack with an ax : a
this . This [ ep id emic ] is happening .
candidate . N ancy Pelosi In October
ernel ) L ines 20 and 21 loads our
How a pro pos that this famous and very
necessary skills to analyze and synthes ize information and to generate
than 10 years in prison MORE and Hillary Clinton Hillary Diane
during this time period but rather " on the other side
Silver Bullet but rather a combination of D DoS
approach to designing X e od r ifter was a case
T ear V oid Ray J KS
s Cody Wester lund (@ C ody W ester lund

MIN ACTIVATIONS
MIN = -4.261

411 horsepower and 4 34 lb .- ft . of torque
all minions . IGN : Sure . Before we
Al ignment ] :: Center break } Left { $ s
- im perial ist sc ound rel Vac lav Ha vel
: 50 pur ak ushi wrote : Happy it
this article . NOTE : Also , it should
[ 10 : 47 ] <@ t ay l ort ot
MI 24 . 99 kg / m ² ), overweight
amazing I 've been ch omp ing at the bit for
. I had the 10 " 150 watt J BL before
this thing . IGN : The armour option
ieving Hollywood agent and anthrop omorphic cat Princess Carolyn . She
that is , for Michael Ign at ie ff . At
m ew 2 king > OM FG <|endoftext|> By Andrew Benson
oring fans wanting his aut ograph , and so he drinks
a massive audience -- and whichever prevailed would be required to
in January , three weeks ahead of its normal security updates
within 2 weeks . This sub sounds amazing . It really
s presidency , whichever comes first . Po etic
the question ? IGN : Just about the key

INTERVAL 2.101 - 4.221
CONTAINS 0.222%

November 2016 , featured the rather violent mating fights of snow
survey 2 , 600 years Age of the world
nearly 50 products over the past few years , from massive
> or < Tab >) { vi : | vim :
approach to designing X e od r ifter was a case

INTERVAL -0.020 - 2.101
CONTAINS 51.157%

the one that I find the most annoying / dist ract
platform ing that under line the original game . Much of
z has denied he coerced La Feb re into filing the
s a moving target because it keeps changing .
Drive In . Call 440 - 327 - 9

INTERVAL -2.140 - -0.020
CONTAINS 48.428%

in support for Snap . Meanwhile Flat pak has not enjoyed
stats , including last week against San Diego when he scored
T unes feed ) If you have a moment
exponentially , with implications for our common security .
. On 28 April , European Court of Human Rights demanded

INTERVAL -4.261 - -2.140
CONTAINS 0.192%

How in the hell could a man enjoy being
07 : 44 Se eker wrote : Cl arity
you re not just waiting for a surprise
[ 10 : 47 ] < abal icious s > lol
the trial . As you may recall , on Monday it
Tokenholes
Token ID28439
Feature activation-2.31e-01

Pos logit contributions
abase+0.136
rador+0.101
 MB+0.099
 CAD+0.091
ielding+0.089
Neg logit contributions
 moons-0.187
 horm-0.182
 nerv-0.177
 mosqu-0.172
 behavi-0.169
Token in
Token ID287
Feature activation-1.51e-01

Pos logit contributions
 moons+0.175
 horm+0.168
 nerv+0.163
 mosqu+0.156
 behavi+0.153
Neg logit contributions
abase-0.206
rador-0.165
 MB-0.162
 CAD-0.153
ielding-0.151
Token American
Token ID1605
Feature activation+1.65e-01

Pos logit contributions
 moons+0.110
 horm+0.106
 nerv+0.102
 mosqu+0.097
 behavi+0.096
Neg logit contributions
abase-0.140
rador-0.112
 MB-0.109
 CAD-0.104
ielding-0.104
Token politics
Token ID4819
Feature activation+3.93e-01

Pos logit contributions
abase+0.171
 MB+0.141
rador+0.141
 CAD+0.133
ielding+0.133
Neg logit contributions
 moons-0.099
 horm-0.098
 nerv-0.091
 mosqu-0.090
 behavi-0.087
Token'
Token ID6
Feature activation-7.21e-01

Pos logit contributions
abase+0.346
rador+0.275
 MB+0.272
 CAD+0.256
ielding+0.253
Neg logit contributions
 moons-0.301
 horm-0.292
 nerv-0.281
 mosqu-0.272
 behavi-0.266
Token MORE
Token ID12011
Feature activation+4.22e+00

Pos logit contributions
 moons+0.627
 horm+0.608
 nerv+0.594
 mosqu+0.565
 seiz+0.552
Neg logit contributions
abase-0.568
rador-0.438
 MB-0.403
xes-0.376
 CAD-0.375
Token as
Token ID355
Feature activation+6.84e-01

Pos logit contributions
abase+3.877
 MB+3.215
rador+3.145
 CAD+3.004
ielding+2.992
Neg logit contributions
 moons-2.873
 horm-2.873
 mosqu-2.670
 nerv-2.657
 behavi-2.584
Token a
Token ID257
Feature activation+1.15e+00

Pos logit contributions
abase+0.629
rador+0.506
 MB+0.504
 CAD+0.474
ielding+0.470
Neg logit contributions
 moons-0.493
 horm-0.479
 nerv-0.459
 mosqu-0.447
 behavi-0.434
Token 68
Token ID8257
Feature activation+6.02e-01

Pos logit contributions
abase+1.117
rador+0.911
 MB+0.911
 CAD+0.861
ielding+0.851
Neg logit contributions
 moons-0.768
 horm-0.747
 nerv-0.711
 mosqu-0.696
 behavi-0.676
Token-
Token ID12
Feature activation+4.68e-01

Pos logit contributions
abase+0.457
rador+0.349
 MB+0.345
 CAD+0.319
ielding+0.316
Neg logit contributions
 moons-0.533
 horm-0.519
 nerv-0.502
 mosqu-0.489
 behavi-0.478
Tokenyear
Token ID1941
Feature activation-5.35e-02

Pos logit contributions
abase+0.378
rador+0.294
 MB+0.291
 CAD+0.271
ielding+0.268
Neg logit contributions
 moons-0.391
 horm-0.381
 nerv-0.368
 mosqu-0.359
 behavi-0.351
Tokenice
Token ID501
Feature activation-1.85e-01

Pos logit contributions
 moons+0.790
 horm+0.783
 mosqu+0.752
 nerv+0.748
 behavi+0.729
Neg logit contributions
abase-0.604
 MB-0.456
rador-0.451
ielding-0.413
 CAD-0.410
Token.
Token ID13
Feature activation+2.05e-01

Pos logit contributions
 moons+0.125
 horm+0.120
 nerv+0.115
 mosqu+0.111
 behavi+0.108
Neg logit contributions
abase-0.180
rador-0.147
 MB-0.146
 CAD-0.138
ielding-0.136
Token
Token ID198
Feature activation-3.36e-01

Pos logit contributions
abase+0.184
rador+0.147
 MB+0.146
 CAD+0.137
ielding+0.135
Neg logit contributions
 moons-0.154
 horm-0.149
 nerv-0.143
 mosqu-0.139
 behavi-0.135
Token
Token ID198
Feature activation-3.41e-01

Pos logit contributions
 moons+0.251
 horm+0.242
 nerv+0.234
 mosqu+0.224
 behavi+0.219
Neg logit contributions
abase-0.303
rador-0.242
 MB-0.239
 CAD-0.225
ielding-0.223
TokenV
Token ID53
Feature activation+1.11e-01

Pos logit contributions
 moons+0.252
 horm+0.243
 nerv+0.234
 mosqu+0.225
 behavi+0.219
Neg logit contributions
abase-0.308
rador-0.248
 MB-0.244
 CAD-0.230
ielding-0.228
Tokenox
Token ID1140
Feature activation+4.10e+00

Pos logit contributions
abase+0.095
rador+0.075
 MB+0.074
 CAD+0.070
ielding+0.069
Neg logit contributions
 moons-0.088
 horm-0.085
 nerv-0.082
 mosqu-0.080
 behavi-0.078
Token can
Token ID460
Feature activation+2.37e-01

Pos logit contributions
abase+3.728
 MB+2.986
rador+2.974
 CAD+2.798
ielding+2.752
Neg logit contributions
 moons-2.960
 horm-2.922
 nerv-2.752
 mosqu-2.719
 behavi-2.657
Token beat
Token ID4405
Feature activation+8.53e-01

Pos logit contributions
abase+0.223
rador+0.181
 MB+0.179
 CAD+0.169
ielding+0.167
Neg logit contributions
 moons-0.167
 horm-0.162
 nerv-0.155
 mosqu-0.150
 behavi-0.146
Token Flip
Token ID29583
Feature activation-6.95e-01

Pos logit contributions
abase+0.780
rador+0.625
 MB+0.624
 CAD+0.587
ielding+0.579
Neg logit contributions
 moons-0.621
 horm-0.603
 nerv-0.578
 mosqu-0.561
 behavi-0.547
TokenS
Token ID50
Feature activation-4.72e-01

Pos logit contributions
 moons+0.526
 horm+0.504
 nerv+0.491
 mosqu+0.469
 behavi+0.457
Neg logit contributions
abase-0.620
rador-0.496
 MB-0.485
ielding-0.456
 CAD-0.455
Tokenid
Token ID312
Feature activation+2.43e+00

Pos logit contributions
 moons+0.416
 horm+0.397
 nerv+0.390
 mosqu+0.371
 behavi+0.364
Neg logit contributions
abase-0.357
rador-0.277
 MB-0.271
 CAD-0.251
ielding-0.249
Token than
Token ID621
Feature activation-4.47e-01

Pos logit contributions
 moons+1.859
 horm+1.778
 nerv+1.738
 mosqu+1.669
 behavi+1.642
Neg logit contributions
abase-1.789
rador-1.375
 MB-1.321
 CAD-1.241
ielding-1.236
Token 10
Token ID838
Feature activation-9.26e-01

Pos logit contributions
 moons+0.363
 horm+0.353
 nerv+0.342
 mosqu+0.332
 behavi+0.324
Neg logit contributions
abase-0.370
rador-0.291
 MB-0.290
 CAD-0.270
ielding-0.267
Token years
Token ID812
Feature activation-7.60e-01

Pos logit contributions
 moons+0.758
 horm+0.718
 nerv+0.700
 mosqu+0.672
 behavi+0.662
Neg logit contributions
abase-0.793
rador-0.637
 MB-0.563
 CAD-0.553
ielding-0.538
Token in
Token ID287
Feature activation-4.42e-01

Pos logit contributions
 moons+0.533
 horm+0.516
 nerv+0.495
 mosqu+0.479
 behavi+0.464
Neg logit contributions
abase-0.716
rador-0.580
 MB-0.577
 CAD-0.543
ielding-0.538
Token prison
Token ID3770
Feature activation+6.35e-01

Pos logit contributions
 moons+0.354
 horm+0.349
 nerv+0.335
 mosqu+0.325
 behavi+0.318
Neg logit contributions
abase-0.368
 MB-0.297
rador-0.292
 CAD-0.270
ielding-0.264
Token MORE
Token ID12011
Feature activation+3.88e+00

Pos logit contributions
abase+0.533
 MB+0.422
rador+0.418
 CAD+0.392
ielding+0.387
Neg logit contributions
 moons-0.506
 horm-0.494
 nerv-0.474
 mosqu-0.465
 behavi-0.455
Token and
Token ID290
Feature activation+4.63e-01

Pos logit contributions
abase+3.483
 MB+2.909
rador+2.841
ielding+2.704
 CAD+2.687
Neg logit contributions
 horm-2.695
 moons-2.668
 mosqu-2.516
 nerv-2.497
 behavi-2.438
Token tick
Token ID4378
Feature activation+1.86e+00

Pos logit contributions
abase+0.436
rador+0.353
 MB+0.352
 CAD+0.331
ielding+0.329
Neg logit contributions
 moons-0.323
 horm-0.314
 nerv-0.300
 mosqu-0.291
 behavi-0.284
Tokened
Token ID276
Feature activation-9.98e-02

Pos logit contributions
abase+1.130
rador+0.800
 MB+0.793
 CAD+0.709
ielding+0.699
Neg logit contributions
 moons-1.917
 horm-1.876
 nerv-1.826
 mosqu-1.788
 behavi-1.753
Token through
Token ID832
Feature activation+6.87e-01

Pos logit contributions
 moons+0.059
 horm+0.056
 nerv+0.054
 mosqu+0.051
 behavi+0.049
Neg logit contributions
abase-0.106
rador-0.088
 MB-0.087
 CAD-0.083
ielding-0.082
Token her
Token ID607
Feature activation+1.16e-01

Pos logit contributions
abase+0.623
rador+0.501
 MB+0.501
 CAD+0.469
ielding+0.465
Neg logit contributions
 moons-0.501
 horm-0.487
 nerv-0.467
 mosqu-0.456
 behavi-0.444
Tokenholes
Token ID28439
Feature activation-2.73e-01

Pos logit contributions
abase+0.119
rador+0.088
 MB+0.086
 CAD+0.079
ielding+0.078
Neg logit contributions
 moons-0.169
 horm-0.164
 nerv-0.160
 mosqu-0.156
 behavi-0.153
Token in
Token ID287
Feature activation-1.45e-01

Pos logit contributions
 moons+0.208
 horm+0.201
 nerv+0.194
 mosqu+0.187
 behavi+0.182
Neg logit contributions
abase-0.241
rador-0.192
 MB-0.190
 CAD-0.178
ielding-0.177
Token American
Token ID1605
Feature activation+6.76e-01

Pos logit contributions
 moons+0.106
 horm+0.102
 nerv+0.099
 mosqu+0.094
 behavi+0.093
Neg logit contributions
abase-0.134
rador-0.107
 MB-0.104
 CAD-0.099
ielding-0.099
Token politics
Token ID4819
Feature activation+4.18e-01

Pos logit contributions
abase+0.705
 MB+0.584
rador+0.582
 CAD+0.550
ielding+0.547
Neg logit contributions
 moons-0.399
 horm-0.394
 nerv-0.367
 mosqu-0.364
 behavi-0.349
Token'
Token ID6
Feature activation-5.88e-01

Pos logit contributions
abase+0.368
rador+0.293
 MB+0.290
 CAD+0.272
ielding+0.269
Neg logit contributions
 moons-0.320
 horm-0.310
 nerv-0.299
 mosqu-0.289
 behavi-0.282
Token MORE
Token ID12011
Feature activation+3.87e+00

Pos logit contributions
 moons+0.514
 horm+0.499
 nerv+0.486
 mosqu+0.464
 seiz+0.452
Neg logit contributions
abase-0.462
rador-0.354
 MB-0.324
xes-0.304
 CAD-0.303
Token completed
Token ID5668
Feature activation+2.52e-01

Pos logit contributions
abase+3.383
 MB+2.749
rador+2.673
 CAD+2.533
ielding+2.503
Neg logit contributions
 moons-2.842
 horm-2.830
 mosqu-2.689
 nerv-2.655
 behavi-2.617
Token a
Token ID257
Feature activation+1.12e+00

Pos logit contributions
abase+0.228
rador+0.183
 MB+0.181
 CAD+0.170
ielding+0.169
Neg logit contributions
 moons-0.187
 horm-0.181
 nerv-0.174
 mosqu-0.168
 behavi-0.164
Token swing
Token ID9628
Feature activation+8.31e-01

Pos logit contributions
abase+1.034
rador+0.835
 MB+0.833
 CAD+0.784
ielding+0.773
Neg logit contributions
 moons-0.792
 horm-0.772
 nerv-0.736
 mosqu-0.720
 behavi-0.699
Token through
Token ID832
Feature activation+4.96e-01

Pos logit contributions
abase+0.781
rador+0.631
 MB+0.626
 CAD+0.590
ielding+0.585
Neg logit contributions
 moons-0.587
 horm-0.567
 nerv-0.544
 mosqu-0.526
 behavi-0.511
Token North
Token ID2258
Feature activation+1.45e+00

Pos logit contributions
abase+0.451
rador+0.362
 MB+0.359
 CAD+0.338
ielding+0.335
Neg logit contributions
 moons-0.364
 horm-0.352
 nerv-0.339
 mosqu-0.328
 behavi-0.319
Tokent
Token ID83
Feature activation-2.12e-01

Pos logit contributions
abase+0.032
rador+0.025
 MB+0.025
 CAD+0.023
ielding+0.023
Neg logit contributions
 moons-0.029
 horm-0.028
 nerv-0.027
 mosqu-0.026
 behavi-0.026
Tokenweet
Token ID7277
Feature activation+9.03e-01

Pos logit contributions
 moons+0.163
 horm+0.158
 nerv+0.152
 mosqu+0.148
 behavi+0.144
Neg logit contributions
abase-0.186
rador-0.148
 MB-0.146
 CAD-0.137
ielding-0.136
Token/
Token ID14
Feature activation-9.23e-01

Pos logit contributions
abase+0.716
rador+0.554
 MB+0.548
 CAD+0.509
ielding+0.504
Neg logit contributions
 moons-0.769
 horm-0.748
 nerv-0.724
 mosqu-0.703
 behavi-0.687
Token<|endoftext|>
Token ID50256
Feature activation-1.98e-01

Pos logit contributions
 moons+0.664
 horm+0.641
 nerv+0.618
 mosqu+0.596
 behavi+0.581
Neg logit contributions
abase-0.853
rador-0.686
 MB-0.678
 CAD-0.639
ielding-0.634
TokenStory
Token ID11605
Feature activation+4.11e-01

Pos logit contributions
 moons+0.147
 horm+0.142
 nerv+0.137
 mosqu+0.132
 behavi+0.128
Neg logit contributions
abase-0.178
rador-0.142
 MB-0.141
 CAD-0.132
ielding-0.131
Token highlights
Token ID11330
Feature activation+3.80e+00

Pos logit contributions
abase+0.380
rador+0.306
 MB+0.302
 CAD+0.285
ielding+0.283
Neg logit contributions
 moons-0.297
 horm-0.287
 nerv-0.276
 mosqu-0.266
 behavi-0.259
Token Secretary
Token ID4986
Feature activation+9.31e-02

Pos logit contributions
abase+3.264
 MB+2.678
rador+2.584
 CAD+2.491
ielding+2.404
Neg logit contributions
 moons-2.891
 horm-2.840
 nerv-2.708
 mosqu-2.697
 behavi-2.640
Token of
Token ID286
Feature activation+2.97e-01

Pos logit contributions
abase+0.081
rador+0.065
 MB+0.064
 CAD+0.060
ielding+0.059
Neg logit contributions
 moons-0.072
 horm-0.070
 nerv-0.067
 mosqu-0.065
 behavi-0.063
Token Defense
Token ID5947
Feature activation-2.48e-02

Pos logit contributions
abase+0.282
rador+0.229
 MB+0.227
 CAD+0.214
ielding+0.212
Neg logit contributions
 moons-0.206
 horm-0.199
 nerv-0.191
 mosqu-0.184
 behavi-0.179
Token Chuck
Token ID14663
Feature activation+4.84e-02

Pos logit contributions
 moons+0.021
 horm+0.021
 nerv+0.020
 mosqu+0.020
 behavi+0.019
Neg logit contributions
abase-0.019
 MB-0.015
rador-0.015
 CAD-0.014
ielding-0.014
Token Hag
Token ID21375
Feature activation+1.45e-01

Pos logit contributions
abase+0.027
 MB+0.018
rador+0.018
 CAD+0.016
ielding+0.016
Neg logit contributions
 moons-0.053
 horm-0.052
 nerv-0.050
 mosqu-0.050
 behavi-0.049
Token vote
Token ID3015
Feature activation+5.80e-01

Pos logit contributions
 moons+0.172
 horm+0.166
 nerv+0.159
 mosqu+0.155
 behavi+0.150
Neg logit contributions
abase-0.251
rador-0.205
 MB-0.205
 CAD-0.194
ielding-0.191
Token accordingly
Token ID16062
Feature activation+1.66e-01

Pos logit contributions
abase+0.515
 MB+0.410
rador+0.410
 CAD+0.384
ielding+0.379
Neg logit contributions
 moons-0.438
 horm-0.425
 nerv-0.409
 mosqu-0.398
 behavi-0.387
Token.
Token ID13
Feature activation+3.38e-02

Pos logit contributions
abase+0.163
 MB+0.133
rador+0.132
 CAD+0.125
ielding+0.124
Neg logit contributions
 moons-0.111
 horm-0.107
 nerv-0.102
 mosqu-0.100
 behavi-0.096
Token<|endoftext|>
Token ID50256
Feature activation-1.79e-01

Pos logit contributions
abase+0.031
rador+0.025
 MB+0.025
 CAD+0.024
ielding+0.023
Neg logit contributions
 moons-0.024
 horm-0.024
 nerv-0.023
 mosqu-0.022
 behavi-0.021
TokenStory
Token ID11605
Feature activation+5.23e-01

Pos logit contributions
 moons+0.133
 horm+0.129
 nerv+0.124
 mosqu+0.119
 behavi+0.116
Neg logit contributions
abase-0.161
rador-0.129
 MB-0.128
 CAD-0.120
ielding-0.119
Token highlights
Token ID11330
Feature activation+3.73e+00

Pos logit contributions
abase+0.482
rador+0.388
 MB+0.383
 CAD+0.361
ielding+0.358
Neg logit contributions
 moons-0.379
 horm-0.366
 nerv-0.352
 mosqu-0.340
 behavi-0.331
Token Police
Token ID4287
Feature activation+3.46e-01

Pos logit contributions
abase+3.207
 MB+2.626
rador+2.541
 CAD+2.445
ielding+2.360
Neg logit contributions
 moons-2.843
 horm-2.792
 nerv-2.664
 mosqu-2.651
 behavi-2.594
Token chief
Token ID4039
Feature activation-5.72e-01

Pos logit contributions
abase+0.319
rador+0.257
 MB+0.256
 CAD+0.241
ielding+0.239
Neg logit contributions
 moons-0.248
 horm-0.241
 nerv-0.231
 mosqu-0.224
 behavi-0.218
Token vows
Token ID36605
Feature activation-1.49e+00

Pos logit contributions
 moons+0.367
 horm+0.353
 nerv+0.338
 mosqu+0.324
 behavi+0.314
Neg logit contributions
abase-0.575
rador-0.472
 MB-0.467
 CAD-0.443
ielding-0.440
Token wanted
Token ID2227
Feature activation+3.80e-01

Pos logit contributions
 moons+1.049
 horm+0.999
 nerv+0.964
 mosqu+0.922
 behavi+0.897
Neg logit contributions
abase-1.416
rador-1.154
 MB-1.120
ielding-1.065
 CAD-1.060
Token suspect
Token ID4099
Feature activation+8.30e-02

Pos logit contributions
abase+0.344
rador+0.276
 MB+0.274
 CAD+0.258
ielding+0.255
Neg logit contributions
 moons-0.280
 horm-0.272
 nerv-0.261
 mosqu-0.254
 behavi-0.246
Tokenholes
Token ID28439
Feature activation-2.92e-01

Pos logit contributions
abase+0.067
rador+0.050
 MB+0.049
 CAD+0.045
ielding+0.044
Neg logit contributions
 moons-0.092
 horm-0.090
 nerv-0.087
 mosqu-0.085
 behavi-0.083
Token in
Token ID287
Feature activation-2.05e-01

Pos logit contributions
 moons+0.221
 horm+0.213
 nerv+0.206
 mosqu+0.198
 behavi+0.193
Neg logit contributions
abase-0.260
rador-0.208
 MB-0.205
 CAD-0.193
ielding-0.191
Token American
Token ID1605
Feature activation+4.19e-01

Pos logit contributions
 moons+0.151
 horm+0.145
 nerv+0.140
 mosqu+0.134
 behavi+0.131
Neg logit contributions
abase-0.189
rador-0.151
 MB-0.147
 CAD-0.140
ielding-0.140
Token politics
Token ID4819
Feature activation+3.77e-01

Pos logit contributions
abase+0.427
 MB+0.352
rador+0.351
 CAD+0.331
ielding+0.329
Neg logit contributions
 moons-0.257
 horm-0.255
 nerv-0.237
 mosqu-0.236
 behavi-0.227
Token'
Token ID6
Feature activation-6.89e-01

Pos logit contributions
abase+0.333
rador+0.265
 MB+0.262
 CAD+0.246
ielding+0.244
Neg logit contributions
 moons-0.287
 horm-0.278
 nerv-0.268
 mosqu-0.259
 behavi-0.252
Token MORE
Token ID12011
Feature activation+3.68e+00

Pos logit contributions
 moons+0.590
 horm+0.575
 nerv+0.560
 mosqu+0.529
 seiz+0.518
Neg logit contributions
abase-0.555
rador-0.429
 MB-0.390
xes-0.369
 CAD-0.363
Token,
Token ID11
Feature activation+4.90e-01

Pos logit contributions
abase+3.085
 MB+2.498
rador+2.471
 CAD+2.307
ielding+2.287
Neg logit contributions
 moons-2.819
 horm-2.807
 nerv-2.666
 mosqu-2.623
 behavi-2.556
Token told
Token ID1297
Feature activation+9.44e-01

Pos logit contributions
abase+0.445
 MB+0.357
rador+0.356
 CAD+0.334
ielding+0.331
Neg logit contributions
 moons-0.357
 horm-0.349
 nerv-0.333
 mosqu-0.325
 behavi-0.316
Token 77
Token ID8541
Feature activation-9.95e-02

Pos logit contributions
abase+0.818
 MB+0.650
rador+0.649
 CAD+0.606
ielding+0.600
Neg logit contributions
 moons-0.730
 horm-0.711
 nerv-0.684
 mosqu-0.664
 behavi-0.651
TokenWA
Token ID15543
Feature activation+6.63e-01

Pos logit contributions
 moons+0.076
 horm+0.073
 nerv+0.071
 mosqu+0.068
 behavi+0.067
Neg logit contributions
abase-0.088
rador-0.070
 MB-0.069
 CAD-0.065
ielding-0.065
TokenBC
Token ID2749
Feature activation+6.92e-01

Pos logit contributions
abase+0.595
rador+0.477
 MB+0.476
 CAD+0.446
ielding+0.441
Neg logit contributions
 moons-0.494
 horm-0.481
 nerv-0.462
 mosqu-0.446
 behavi-0.437
Token great
Token ID1049
Feature activation-5.32e-01

Pos logit contributions
abase+0.155
rador+0.123
 MB+0.122
 CAD+0.115
ielding+0.114
Neg logit contributions
 moons-0.134
 horm-0.130
 nerv-0.125
 mosqu-0.122
 behavi-0.119
Token mechanical
Token ID12370
Feature activation+1.47e-03

Pos logit contributions
 moons+0.393
 horm+0.379
 nerv+0.366
 mosqu+0.350
 behavi+0.343
Neg logit contributions
abase-0.486
rador-0.390
 MB-0.383
 CAD-0.360
ielding-0.359
Token stress
Token ID5503
Feature activation+8.63e-01

Pos logit contributions
abase+0.001
rador+0.001
 MB+0.001
 CAD+0.001
ielding+0.001
Neg logit contributions
 moons-0.001
 horm-0.001
 nerv-0.001
 mosqu-0.001
 behavi-0.001
Token (
Token ID357
Feature activation-4.57e-01

Pos logit contributions
abase+0.821
rador+0.669
 MB+0.668
 CAD+0.631
ielding+0.625
Neg logit contributions
 moons-0.590
 horm-0.571
 nerv-0.545
 mosqu-0.535
 behavi-0.516
Tokenbending
Token ID49667
Feature activation-6.65e-01

Pos logit contributions
 moons+0.357
 horm+0.346
 nerv+0.333
 mosqu+0.323
 behavi+0.315
Neg logit contributions
abase-0.394
rador-0.312
 MB-0.309
 CAD-0.289
ielding-0.287
Token open
Token ID1280
Feature activation+3.56e+00

Pos logit contributions
 moons+0.495
 horm+0.477
 nerv+0.462
 mosqu+0.441
 behavi+0.430
Neg logit contributions
abase-0.601
rador-0.482
 MB-0.475
 CAD-0.446
ielding-0.444
Token and
Token ID290
Feature activation+1.86e-01

Pos logit contributions
abase+3.084
 MB+2.459
rador+2.453
 CAD+2.307
ielding+2.261
Neg logit contributions
 moons-2.697
 horm-2.641
 nerv-2.515
 mosqu-2.474
 behavi-2.422
Token slamming
Token ID39603
Feature activation-2.14e-01

Pos logit contributions
abase+0.167
rador+0.134
 MB+0.132
 CAD+0.124
ielding+0.123
Neg logit contributions
 moons-0.139
 horm-0.135
 nerv-0.130
 mosqu-0.125
 behavi-0.122
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
 moons+0.156
 horm+0.150
 nerv+0.145
 mosqu+0.139
 behavi+0.135
Neg logit contributions
abase-0.196
rador-0.158
 MB-0.156
 CAD-0.146
ielding-0.146
Token
Token ID198
Feature activation+3.22e-01

Pos logit contributions
abase+0.136
rador+0.109
 MB+0.107
 CAD+0.101
ielding+0.101
Neg logit contributions
 moons-0.109
 horm-0.105
 nerv-0.101
 mosqu-0.095
 behavi-0.093
Tokenshut
Token ID49625
Feature activation+6.50e-01

Pos logit contributions
abase+0.278
rador+0.220
 MB+0.219
 CAD+0.204
ielding+0.203
Neg logit contributions
 moons-0.251
 horm-0.243
 nerv-0.234
 mosqu-0.225
 behavi-0.219
Token forehead
Token ID22645
Feature activation-3.61e-01

Pos logit contributions
abase+0.227
rador+0.183
 MB+0.181
 CAD+0.171
ielding+0.169
Neg logit contributions
 moons-0.174
 horm-0.168
 nerv-0.161
 mosqu-0.156
 behavi-0.152
Token a
Token ID257
Feature activation+9.41e-01

Pos logit contributions
 moons+0.271
 horm+0.263
 nerv+0.253
 mosqu+0.245
 behavi+0.239
Neg logit contributions
abase-0.323
rador-0.258
 MB-0.256
 CAD-0.240
ielding-0.238
Token butt
Token ID8530
Feature activation-7.99e-01

Pos logit contributions
abase+0.887
rador+0.719
 MB+0.717
 CAD+0.676
ielding+0.665
Neg logit contributions
 moons-0.654
 horm-0.635
 nerv-0.607
 mosqu-0.593
 behavi-0.576
Token-
Token ID12
Feature activation-1.42e-01

Pos logit contributions
 moons+0.550
 horm+0.533
 nerv+0.509
 mosqu+0.495
 behavi+0.481
Neg logit contributions
abase-0.765
rador-0.621
 MB-0.616
 CAD-0.581
ielding-0.575
Tokencr
Token ID6098
Feature activation+1.49e+00

Pos logit contributions
 moons+0.108
 horm+0.105
 nerv+0.101
 mosqu+0.098
 behavi+0.096
Neg logit contributions
abase-0.125
rador-0.100
 MB-0.099
 CAD-0.093
ielding-0.092
Tokenack
Token ID441
Feature activation+3.53e+00

Pos logit contributions
abase+1.012
rador+0.744
 MB+0.734
 CAD+0.669
ielding+0.662
Neg logit contributions
 moons-1.438
 horm-1.405
 nerv-1.364
 mosqu-1.332
 behavi-1.308
Token with
Token ID351
Feature activation+5.48e-01

Pos logit contributions
abase+3.282
 MB+2.693
rador+2.667
 CAD+2.505
ielding+2.444
Neg logit contributions
 moons-2.430
 horm-2.420
 mosqu-2.266
 nerv-2.248
 behavi-2.160
Token an
Token ID281
Feature activation+1.13e+00

Pos logit contributions
abase+0.491
rador+0.393
 MB+0.390
 CAD+0.366
ielding+0.362
Neg logit contributions
 moons-0.410
 horm-0.397
 nerv-0.382
 mosqu-0.370
 behavi-0.361
Token ax
Token ID7877
Feature activation+3.13e-01

Pos logit contributions
abase+1.016
 MB+0.812
rador+0.809
 CAD+0.758
ielding+0.749
Neg logit contributions
 moons-0.845
 horm-0.820
 nerv-0.786
 mosqu-0.765
 behavi-0.745
Token:
Token ID25
Feature activation-5.12e-01

Pos logit contributions
abase+0.298
rador+0.242
 MB+0.240
 CAD+0.226
ielding+0.225
Neg logit contributions
 moons-0.217
 horm-0.210
 nerv-0.200
 mosqu-0.195
 behavi-0.189
Token a
Token ID257
Feature activation-2.94e-01

Pos logit contributions
 moons+0.379
 horm+0.366
 nerv+0.353
 mosqu+0.341
 behavi+0.332
Neg logit contributions
abase-0.465
rador-0.373
 MB-0.368
 CAD-0.347
ielding-0.344
Token this
Token ID428
Feature activation+6.07e-02

Pos logit contributions
abase+0.186
rador+0.148
 MB+0.147
 CAD+0.138
ielding+0.136
Neg logit contributions
 moons-0.163
 horm-0.158
 nerv-0.152
 mosqu-0.148
 behavi-0.144
Token.
Token ID13
Feature activation-4.85e-01

Pos logit contributions
abase+0.058
rador+0.047
 MB+0.047
 CAD+0.044
ielding+0.044
Neg logit contributions
 moons-0.042
 horm-0.041
 nerv-0.039
 mosqu-0.038
 behavi-0.036
Token This
Token ID770
Feature activation+6.27e-02

Pos logit contributions
 moons+0.390
 horm+0.378
 nerv+0.365
 mosqu+0.352
 behavi+0.345
Neg logit contributions
abase-0.408
rador-0.321
 MB-0.316
 CAD-0.296
ielding-0.295
Token [
Token ID685
Feature activation-9.48e-01

Pos logit contributions
abase+0.056
rador+0.045
 MB+0.044
 CAD+0.042
ielding+0.041
Neg logit contributions
 moons-0.047
 horm-0.046
 nerv-0.044
 mosqu-0.042
 behavi-0.041
Tokenep
Token ID538
Feature activation-3.30e-01

Pos logit contributions
 moons+0.742
 horm+0.718
 nerv+0.692
 mosqu+0.670
 behavi+0.652
Neg logit contributions
abase-0.812
rador-0.644
 MB-0.635
 CAD-0.596
ielding-0.595
Tokenid
Token ID312
Feature activation+3.53e+00

Pos logit contributions
 moons+0.295
 horm+0.288
 nerv+0.280
 mosqu+0.271
 behavi+0.264
Neg logit contributions
abase-0.245
rador-0.185
 MB-0.182
 CAD-0.169
ielding-0.167
Tokenemic
Token ID5314
Feature activation+8.96e-03

Pos logit contributions
abase+2.176
 MB+1.550
rador+1.541
 CAD+1.386
ielding+1.364
Neg logit contributions
 moons-3.607
 horm-3.541
 nerv-3.421
 mosqu-3.342
 behavi-3.316
Token]
Token ID60
Feature activation+2.90e-01

Pos logit contributions
abase+0.007
rador+0.005
 MB+0.005
 CAD+0.005
ielding+0.005
Neg logit contributions
 moons-0.008
 horm-0.008
 nerv-0.008
 mosqu-0.007
 behavi-0.007
Token is
Token ID318
Feature activation+4.58e-01

Pos logit contributions
abase+0.258
rador+0.205
 MB+0.203
 CAD+0.191
ielding+0.189
Neg logit contributions
 moons-0.220
 horm-0.213
 nerv-0.205
 mosqu-0.199
 behavi-0.194
Token happening
Token ID5836
Feature activation+2.46e-01

Pos logit contributions
abase+0.398
rador+0.316
 MB+0.312
 CAD+0.293
ielding+0.291
Neg logit contributions
 moons-0.356
 horm-0.345
 nerv-0.333
 mosqu-0.322
 behavi-0.314
Token.
Token ID13
Feature activation+3.55e-02

Pos logit contributions
abase+0.230
rador+0.186
 MB+0.184
 CAD+0.174
ielding+0.173
Neg logit contributions
 moons-0.175
 horm-0.169
 nerv-0.162
 mosqu-0.156
 behavi-0.152
Token candidate
Token ID4540
Feature activation+7.60e-01

Pos logit contributions
abase+1.308
 MB+1.066
rador+1.066
 CAD+1.001
ielding+0.991
Neg logit contributions
 moons-0.917
 horm-0.897
 nerv-0.854
 mosqu-0.832
 behavi-0.814
Token.
Token ID13
Feature activation+8.31e-03

Pos logit contributions
abase+0.738
 MB+0.600
rador+0.599
 CAD+0.566
ielding+0.559
Neg logit contributions
 moons-0.508
 horm-0.497
 nerv-0.471
 mosqu-0.460
 behavi-0.446
Token
Token ID198
Feature activation+5.33e-02

Pos logit contributions
abase+0.007
rador+0.006
 MB+0.006
 CAD+0.005
ielding+0.005
Neg logit contributions
 moons-0.006
 horm-0.006
 nerv-0.006
 mosqu-0.006
 behavi-0.006
Token
Token ID198
Feature activation+1.38e-01

Pos logit contributions
abase+0.049
rador+0.040
 MB+0.039
ielding+0.036
 CAD+0.036
Neg logit contributions
 moons-0.039
 horm-0.037
 nerv-0.036
 mosqu-0.033
 behavi-0.032
TokenN
Token ID45
Feature activation+1.34e-01

Pos logit contributions
abase+0.125
rador+0.101
 MB+0.099
 CAD+0.094
ielding+0.093
Neg logit contributions
 moons-0.102
 horm-0.098
 nerv-0.094
 mosqu-0.090
 behavi-0.088
Tokenancy
Token ID3883
Feature activation+3.47e+00

Pos logit contributions
abase+0.110
rador+0.085
 MB+0.085
 CAD+0.079
ielding+0.078
Neg logit contributions
 moons-0.111
 horm-0.108
 nerv-0.105
 mosqu-0.102
 behavi-0.099
Token Pelosi
Token ID29611
Feature activation+3.60e-01

Pos logit contributions
abase+2.110
 MB+1.540
rador+1.472
 CAD+1.368
ielding+1.328
Neg logit contributions
 moons-3.541
 horm-3.470
 nerv-3.369
 mosqu-3.349
 behavi-3.298
Token
Token ID198
Feature activation-7.23e-01

Pos logit contributions
abase+0.322
rador+0.258
 MB+0.255
 CAD+0.240
ielding+0.238
Neg logit contributions
 moons-0.270
 horm-0.261
 nerv-0.251
 mosqu-0.243
 behavi-0.237
Token
Token ID198
Feature activation-5.84e-01

Pos logit contributions
 moons+0.510
 horm+0.481
 nerv+0.469
 mosqu+0.420
 behavi+0.413
Neg logit contributions
abase-0.685
rador-0.554
 MB-0.533
ielding-0.508
 CAD-0.504
TokenIn
Token ID818
Feature activation-5.46e-02

Pos logit contributions
 moons+0.405
 horm+0.389
 nerv+0.373
 mosqu+0.356
 behavi+0.346
Neg logit contributions
abase-0.555
rador-0.451
 MB-0.444
 CAD-0.420
ielding-0.417
Token October
Token ID3267
Feature activation+5.98e-01

Pos logit contributions
 moons+0.041
 horm+0.040
 nerv+0.039
 mosqu+0.037
 behavi+0.036
Neg logit contributions
abase-0.048
rador-0.039
 MB-0.038
 CAD-0.036
ielding-0.036
Tokenernel
Token ID7948
Feature activation+6.47e-01

Pos logit contributions
abase+0.594
rador+0.494
 MB+0.490
 CAD+0.466
ielding+0.463
Neg logit contributions
 moons-0.322
 horm-0.309
 nerv-0.294
 mosqu-0.283
 behavi-0.273
Token )
Token ID1267
Feature activation+5.37e-01

Pos logit contributions
abase+0.635
rador+0.518
 MB+0.511
 CAD+0.483
ielding+0.481
Neg logit contributions
 moons-0.431
 horm-0.413
 nerv-0.398
 mosqu-0.376
 behavi-0.366
Token
Token ID198
Feature activation+3.10e-01

Pos logit contributions
abase+0.378
rador+0.283
 MB+0.281
 CAD+0.258
ielding+0.253
Neg logit contributions
 moons-0.502
 horm-0.490
 nerv-0.475
 mosqu-0.465
 behavi-0.455
Token
Token ID198
Feature activation+3.86e-01

Pos logit contributions
abase+0.282
rador+0.226
 MB+0.222
 CAD+0.209
ielding+0.208
Neg logit contributions
 moons-0.229
 horm-0.220
 nerv-0.212
 mosqu-0.201
 behavi-0.197
TokenL
Token ID43
Feature activation+7.76e-02

Pos logit contributions
abase+0.352
rador+0.283
 MB+0.280
 CAD+0.264
ielding+0.261
Neg logit contributions
 moons-0.283
 horm-0.274
 nerv-0.263
 mosqu-0.254
 behavi-0.247
Tokenines
Token ID1127
Feature activation+3.45e+00

Pos logit contributions
abase+0.058
rador+0.044
 MB+0.044
 CAD+0.040
ielding+0.040
Neg logit contributions
 moons-0.070
 horm-0.068
 nerv-0.066
 mosqu-0.064
 behavi-0.063
Token 20
Token ID1160
Feature activation-1.74e-01

Pos logit contributions
abase+2.176
 MB+1.593
rador+1.543
 CAD+1.443
ielding+1.383
Neg logit contributions
 moons-3.450
 horm-3.392
 nerv-3.278
 mosqu-3.234
 behavi-3.192
Token and
Token ID290
Feature activation-3.08e-01

Pos logit contributions
 moons+0.112
 horm+0.108
 nerv+0.103
 mosqu+0.100
 behavi+0.097
Neg logit contributions
abase-0.174
rador-0.143
 MB-0.142
 CAD-0.135
ielding-0.134
Token 21
Token ID2310
Feature activation+1.10e+00

Pos logit contributions
 moons+0.271
 horm+0.264
 nerv+0.255
 mosqu+0.248
 behavi+0.243
Neg logit contributions
abase-0.236
rador-0.181
 MB-0.179
 CAD-0.165
ielding-0.164
Token loads
Token ID15989
Feature activation-3.65e-01

Pos logit contributions
abase+1.045
rador+0.849
 MB+0.848
 CAD+0.800
ielding+0.789
Neg logit contributions
 moons-0.753
 horm-0.732
 nerv-0.698
 mosqu-0.682
 behavi-0.665
Token our
Token ID674
Feature activation+4.37e-01

Pos logit contributions
 moons+0.267
 horm+0.258
 nerv+0.249
 mosqu+0.241
 behavi+0.234
Neg logit contributions
abase-0.334
rador-0.268
 MB-0.264
 CAD-0.249
ielding-0.248
Token
Token ID198
Feature activation+7.09e-01

Pos logit contributions
abase+1.502
 MB+1.196
rador+1.189
 CAD+1.120
ielding+1.101
Neg logit contributions
 moons-1.330
 horm-1.294
 nerv-1.238
 mosqu-1.220
 behavi-1.179
Token
Token ID198
Feature activation+6.02e-01

Pos logit contributions
abase+0.634
rador+0.507
 MB+0.501
 CAD+0.471
ielding+0.467
Neg logit contributions
 moons-0.532
 horm-0.515
 nerv-0.496
 mosqu-0.478
 behavi-0.466
TokenHow
Token ID2437
Feature activation-2.76e-01

Pos logit contributions
abase+0.549
rador+0.442
 MB+0.442
 CAD+0.414
ielding+0.411
Neg logit contributions
 moons-0.437
 horm-0.425
 nerv-0.409
 mosqu-0.401
 behavi-0.389
Token a
Token ID257
Feature activation-5.36e-01

Pos logit contributions
 moons+0.194
 horm+0.188
 nerv+0.180
 mosqu+0.174
 behavi+0.169
Neg logit contributions
abase-0.260
rador-0.210
 MB-0.209
 CAD-0.197
ielding-0.195
Tokenpro
Token ID1676
Feature activation-5.48e-01

Pos logit contributions
 moons+0.380
 horm+0.368
 nerv+0.353
 mosqu+0.342
 behavi+0.332
Neg logit contributions
abase-0.501
rador-0.405
 MB-0.402
 CAD-0.379
ielding-0.375
Tokenpos
Token ID1930
Feature activation+3.43e+00

Pos logit contributions
 moons+0.495
 horm+0.479
 nerv+0.470
 mosqu+0.450
 behavi+0.439
Neg logit contributions
abase-0.404
rador-0.305
 MB-0.300
 CAD-0.278
ielding-0.275
Token that
Token ID326
Feature activation+6.35e-02

Pos logit contributions
abase+2.948
 MB+2.376
rador+2.342
 CAD+2.199
ielding+2.162
Neg logit contributions
 moons-2.603
 horm-2.568
 nerv-2.451
 mosqu-2.412
 behavi-2.338
Token this
Token ID428
Feature activation+5.30e-01

Pos logit contributions
abase+0.058
rador+0.046
 MB+0.046
 CAD+0.043
ielding+0.043
Neg logit contributions
 moons-0.047
 horm-0.045
 nerv-0.043
 mosqu-0.042
 behavi-0.041
Token famous
Token ID5863
Feature activation-4.22e-01

Pos logit contributions
abase+0.479
rador+0.386
 MB+0.385
 CAD+0.361
ielding+0.355
Neg logit contributions
 moons-0.389
 horm-0.377
 nerv-0.362
 mosqu-0.353
 behavi-0.343
Token and
Token ID290
Feature activation+5.33e-01

Pos logit contributions
 moons+0.288
 horm+0.278
 nerv+0.267
 mosqu+0.257
 behavi+0.250
Neg logit contributions
abase-0.405
rador-0.330
 MB-0.327
 CAD-0.309
ielding-0.306
Token very
Token ID845
Feature activation-2.57e-01

Pos logit contributions
abase+0.460
rador+0.365
 MB+0.362
 CAD+0.339
ielding+0.335
Neg logit contributions
 moons-0.415
 horm-0.403
 nerv-0.388
 mosqu-0.377
 behavi-0.367
Token necessary
Token ID3306
Feature activation-3.92e-01

Pos logit contributions
abase+0.280
rador+0.231
 MB+0.230
 CAD+0.217
ielding+0.216
Neg logit contributions
 moons-0.173
 horm-0.167
 nerv-0.159
 mosqu-0.154
 behavi-0.148
Token skills
Token ID4678
Feature activation+2.04e-01

Pos logit contributions
 moons+0.231
 horm+0.222
 nerv+0.211
 mosqu+0.202
 behavi+0.196
Neg logit contributions
abase-0.415
rador-0.344
 MB-0.341
 CAD-0.324
ielding-0.322
Token to
Token ID284
Feature activation+7.40e-03

Pos logit contributions
abase+0.194
rador+0.157
 MB+0.156
 CAD+0.147
ielding+0.146
Neg logit contributions
 moons-0.141
 horm-0.137
 nerv-0.131
 mosqu-0.127
 behavi-0.123
Token analyze
Token ID16602
Feature activation+3.68e-01

Pos logit contributions
abase+0.007
 MB+0.006
rador+0.006
 CAD+0.006
ielding+0.006
Neg logit contributions
 moons-0.005
 horm-0.005
 nerv-0.004
 mosqu-0.004
 behavi-0.004
Token and
Token ID290
Feature activation+4.97e-01

Pos logit contributions
abase+0.343
rador+0.277
 MB+0.276
 CAD+0.260
ielding+0.257
Neg logit contributions
 moons-0.261
 horm-0.253
 nerv-0.243
 mosqu-0.236
 behavi-0.228
Token synthes
Token ID24983
Feature activation+3.41e+00

Pos logit contributions
abase+0.490
rador+0.402
 MB+0.402
 CAD+0.381
ielding+0.376
Neg logit contributions
 moons-0.324
 horm-0.314
 nerv-0.299
 mosqu-0.295
 behavi-0.283
Tokenize
Token ID1096
Feature activation+1.99e-01

Pos logit contributions
abase+1.955
 MB+1.339
rador+1.330
 CAD+1.191
ielding+1.163
Neg logit contributions
 moons-3.644
 horm-3.615
 mosqu-3.490
 nerv-3.474
 behavi-3.411
Token information
Token ID1321
Feature activation+1.00e+00

Pos logit contributions
abase+0.183
rador+0.147
 MB+0.146
 CAD+0.137
ielding+0.136
Neg logit contributions
 moons-0.145
 horm-0.140
 nerv-0.135
 mosqu-0.131
 behavi-0.127
Token and
Token ID290
Feature activation+4.16e-02

Pos logit contributions
abase+0.924
rador+0.744
 MB+0.742
 CAD+0.698
ielding+0.690
Neg logit contributions
 moons-0.719
 horm-0.698
 nerv-0.668
 mosqu-0.652
 behavi-0.630
Token to
Token ID284
Feature activation+6.18e-02

Pos logit contributions
abase+0.040
rador+0.033
 MB+0.033
 CAD+0.031
ielding+0.031
Neg logit contributions
 moons-0.028
 horm-0.027
 nerv-0.026
 mosqu-0.025
 behavi-0.024
Token generate
Token ID7716
Feature activation+8.55e-01

Pos logit contributions
abase+0.062
rador+0.051
 MB+0.051
 CAD+0.048
ielding+0.048
Neg logit contributions
 moons-0.040
 horm-0.038
 nerv-0.036
 mosqu-0.035
 behavi-0.034
Token than
Token ID621
Feature activation-4.13e-01

Pos logit contributions
 moons+1.921
 horm+1.843
 nerv+1.799
 mosqu+1.728
 behavi+1.704
Neg logit contributions
abase-1.822
rador-1.397
 MB-1.344
 CAD-1.262
ielding-1.260
Token 10
Token ID838
Feature activation-8.15e-01

Pos logit contributions
 moons+0.328
 horm+0.320
 nerv+0.310
 mosqu+0.302
 behavi+0.293
Neg logit contributions
abase-0.346
 MB-0.275
rador-0.274
 CAD-0.256
ielding-0.253
Token years
Token ID812
Feature activation-8.37e-01

Pos logit contributions
 moons+0.678
 horm+0.646
 nerv+0.631
 mosqu+0.604
 behavi+0.596
Neg logit contributions
abase-0.687
rador-0.545
 MB-0.483
 CAD-0.474
ielding-0.463
Token in
Token ID287
Feature activation-4.49e-01

Pos logit contributions
 moons+0.612
 horm+0.593
 nerv+0.570
 mosqu+0.552
 behavi+0.537
Neg logit contributions
abase-0.764
rador-0.614
 MB-0.609
 CAD-0.573
ielding-0.568
Token prison
Token ID3770
Feature activation+5.77e-01

Pos logit contributions
 moons+0.361
 horm+0.354
 nerv+0.340
 mosqu+0.331
 behavi+0.323
Neg logit contributions
abase-0.372
 MB-0.301
rador-0.295
 CAD-0.274
ielding-0.268
Token MORE
Token ID12011
Feature activation+3.40e+00

Pos logit contributions
abase+0.429
 MB+0.331
rador+0.324
 CAD+0.303
ielding+0.298
Neg logit contributions
 moons-0.513
 horm-0.502
 nerv-0.483
 mosqu-0.477
 behavi-0.468
Token and
Token ID290
Feature activation+5.69e-01

Pos logit contributions
abase+3.320
 MB+2.760
rador+2.731
ielding+2.609
 CAD+2.597
Neg logit contributions
 moons-2.158
 horm-2.157
 nerv-1.987
 mosqu-1.978
 behavi-1.909
Token Hillary
Token ID5073
Feature activation+1.08e+00

Pos logit contributions
abase+0.526
rador+0.424
 MB+0.422
 CAD+0.397
ielding+0.393
Neg logit contributions
 moons-0.409
 horm-0.396
 nerv-0.380
 mosqu-0.368
 behavi-0.359
Token Clinton
Token ID2605
Feature activation+4.10e-01

Pos logit contributions
abase+1.028
rador+0.834
 MB+0.830
 CAD+0.782
ielding+0.775
Neg logit contributions
 moons-0.751
 horm-0.727
 nerv-0.696
 mosqu-0.677
 behavi-0.657
Token Hillary
Token ID5073
Feature activation+1.35e+00

Pos logit contributions
abase+0.373
 MB+0.299
rador+0.299
 CAD+0.280
ielding+0.277
Neg logit contributions
 moons-0.299
 horm-0.291
 nerv-0.279
 mosqu-0.271
 behavi-0.265
Token Diane
Token ID26542
Feature activation+7.45e-01

Pos logit contributions
abase+0.884
rador+0.646
 MB+0.646
 CAD+0.583
ielding+0.579
Neg logit contributions
 moons-1.330
 horm-1.302
 nerv-1.260
 mosqu-1.241
 behavi-1.219
Token during
Token ID1141
Feature activation-1.35e+00

Pos logit contributions
abase+1.017
rador+0.829
 MB+0.829
 CAD+0.777
ielding+0.771
Neg logit contributions
 moons-0.724
 horm-0.707
 nerv-0.666
 mosqu-0.657
 behavi-0.636
Token this
Token ID428
Feature activation+3.19e-01

Pos logit contributions
 moons+0.959
 horm+0.928
 nerv+0.892
 mosqu+0.856
 behavi+0.833
Neg logit contributions
abase-1.260
rador-1.014
 MB-1.000
ielding-0.945
 CAD-0.943
Token time
Token ID640
Feature activation-8.04e-01

Pos logit contributions
abase+0.302
rador+0.245
 MB+0.243
 CAD+0.229
ielding+0.226
Neg logit contributions
 moons-0.223
 horm-0.216
 nerv-0.207
 mosqu-0.201
 behavi-0.195
Token period
Token ID2278
Feature activation-6.78e-01

Pos logit contributions
 moons+0.525
 horm+0.506
 nerv+0.483
 mosqu+0.467
 behavi+0.452
Neg logit contributions
abase-0.797
rador-0.653
 MB-0.649
 CAD-0.614
ielding-0.609
Token but
Token ID475
Feature activation+5.42e-01

Pos logit contributions
 moons+0.446
 horm+0.430
 nerv+0.410
 mosqu+0.397
 behavi+0.385
Neg logit contributions
abase-0.670
rador-0.548
 MB-0.545
 CAD-0.515
ielding-0.511
Token rather
Token ID2138
Feature activation+3.34e+00

Pos logit contributions
abase+0.486
rador+0.389
 MB+0.388
 CAD+0.363
ielding+0.359
Neg logit contributions
 moons-0.403
 horm-0.391
 nerv-0.376
 mosqu-0.365
 behavi-0.356
Token "
Token ID366
Feature activation-4.77e-01

Pos logit contributions
abase+2.894
 MB+2.357
rador+2.317
 CAD+2.199
ielding+2.133
Neg logit contributions
 moons-2.494
 horm-2.436
 nerv-2.318
 mosqu-2.289
 behavi-2.250
Tokenon
Token ID261
Feature activation-1.77e-01

Pos logit contributions
 moons+0.385
 horm+0.374
 nerv+0.360
 mosqu+0.349
 behavi+0.340
Neg logit contributions
abase-0.398
rador-0.313
 MB-0.310
 CAD-0.290
ielding-0.286
Token the
Token ID262
Feature activation-2.17e-01

Pos logit contributions
 moons+0.128
 horm+0.123
 nerv+0.119
 mosqu+0.114
 behavi+0.111
Neg logit contributions
abase-0.165
rador-0.132
 MB-0.131
 CAD-0.123
ielding-0.123
Token other
Token ID584
Feature activation+1.05e+00

Pos logit contributions
 moons+0.158
 horm+0.153
 nerv+0.147
 mosqu+0.142
 behavi+0.138
Neg logit contributions
abase-0.199
rador-0.160
 MB-0.158
 CAD-0.149
ielding-0.148
Token side
Token ID1735
Feature activation+2.67e-01

Pos logit contributions
abase+1.122
rador+0.934
 MB+0.930
 CAD+0.883
ielding+0.876
Neg logit contributions
 moons-0.603
 horm-0.578
 nerv-0.549
 mosqu-0.528
 behavi-0.508
TokenSilver
Token ID26766
Feature activation+6.22e-01

Pos logit contributions
abase+0.439
rador+0.346
 MB+0.344
 CAD+0.321
ielding+0.318
Neg logit contributions
 moons-0.410
 horm-0.398
 nerv-0.384
 mosqu-0.372
 behavi-0.363
Token Bullet
Token ID18003
Feature activation+1.61e+00

Pos logit contributions
abase+0.452
rador+0.341
 MB+0.336
 CAD+0.310
ielding+0.306
Neg logit contributions
 moons-0.570
 horm-0.556
 nerv-0.539
 mosqu-0.525
 behavi-0.514
Token
Token ID447
Feature activation+1.70e-01

Pos logit contributions
abase+1.444
 MB+1.155
rador+1.145
 CAD+1.080
ielding+1.066
Neg logit contributions
 moons-1.205
 horm-1.169
 nerv-1.120
 mosqu-1.095
 behavi-1.053
Token
Token ID251
Feature activation+2.46e-01

Pos logit contributions
abase+0.135
rador+0.104
 MB+0.103
 CAD+0.096
ielding+0.095
Neg logit contributions
 moons-0.145
 horm-0.141
 nerv-0.136
 mosqu-0.132
 behavi-0.129
Token but
Token ID475
Feature activation+3.33e-01

Pos logit contributions
abase+0.232
rador+0.188
 MB+0.187
 CAD+0.176
ielding+0.175
Neg logit contributions
 moons-0.173
 horm-0.167
 nerv-0.160
 mosqu-0.156
 behavi-0.151
Token rather
Token ID2138
Feature activation+3.32e+00

Pos logit contributions
abase+0.252
rador+0.192
 MB+0.190
 CAD+0.176
ielding+0.174
Neg logit contributions
 moons-0.296
 horm-0.288
 nerv-0.279
 mosqu-0.272
 behavi-0.266
Token a
Token ID257
Feature activation-2.83e-01

Pos logit contributions
abase+2.819
 MB+2.304
rador+2.262
 CAD+2.145
ielding+2.085
Neg logit contributions
 moons-2.536
 horm-2.461
 nerv-2.383
 mosqu-2.327
 behavi-2.253
Token combination
Token ID6087
Feature activation+2.29e+00

Pos logit contributions
 moons+0.216
 horm+0.209
 nerv+0.202
 mosqu+0.195
 behavi+0.190
Neg logit contributions
abase-0.250
rador-0.199
 MB-0.197
 CAD-0.184
ielding-0.183
Token of
Token ID286
Feature activation+6.11e-02

Pos logit contributions
abase+1.885
 MB+1.489
rador+1.480
 CAD+1.385
ielding+1.359
Neg logit contributions
 moons-1.851
 horm-1.798
 nerv-1.738
 mosqu-1.696
 behavi-1.639
Token D
Token ID360
Feature activation+4.89e-01

Pos logit contributions
abase+0.054
rador+0.044
 MB+0.043
 CAD+0.041
ielding+0.040
Neg logit contributions
 moons-0.046
 horm-0.045
 nerv-0.043
 mosqu-0.042
 behavi-0.040
TokenDoS
Token ID46498
Feature activation-9.13e-01

Pos logit contributions
abase+0.516
rador+0.428
 MB+0.427
 CAD+0.404
ielding+0.402
Neg logit contributions
 moons-0.288
 horm-0.276
 nerv-0.264
 mosqu-0.254
 behavi-0.244
Token approach
Token ID3164
Feature activation-5.13e-01

Pos logit contributions
 moons+0.087
 horm+0.084
 nerv+0.081
 mosqu+0.078
 behavi+0.076
Neg logit contributions
abase-0.115
rador-0.093
 MB-0.092
 CAD-0.086
ielding-0.086
Token to
Token ID284
Feature activation-1.85e-01

Pos logit contributions
 moons+0.365
 horm+0.351
 nerv+0.339
 mosqu+0.324
 behavi+0.315
Neg logit contributions
abase-0.479
rador-0.387
 MB-0.383
 CAD-0.361
ielding-0.358
Token designing
Token ID18492
Feature activation+2.57e-01

Pos logit contributions
 moons+0.126
 horm+0.122
 nerv+0.118
 mosqu+0.114
 behavi+0.110
Neg logit contributions
abase-0.177
rador-0.143
 MB-0.143
 CAD-0.135
ielding-0.134
Token X
Token ID1395
Feature activation+1.25e+00

Pos logit contributions
abase+0.241
 MB+0.195
rador+0.195
 CAD+0.184
ielding+0.181
Neg logit contributions
 moons-0.179
 horm-0.174
 nerv-0.167
 mosqu-0.162
 behavi-0.158
Tokene
Token ID68
Feature activation+8.27e-01

Pos logit contributions
abase+1.033
rador+0.809
 MB+0.806
 CAD+0.752
ielding+0.744
Neg logit contributions
 moons-1.011
 horm-0.987
 nerv-0.950
 mosqu-0.926
 behavi-0.913
Tokenod
Token ID375
Feature activation+3.31e+00

Pos logit contributions
abase+0.646
 MB+0.500
rador+0.495
 CAD+0.463
ielding+0.455
Neg logit contributions
 moons-0.709
 horm-0.693
 nerv-0.668
 mosqu-0.655
 behavi-0.644
Tokenr
Token ID81
Feature activation+8.42e-01

Pos logit contributions
abase+2.770
rador+2.170
 MB+2.154
ielding+2.025
 CAD+2.004
Neg logit contributions
 moons-2.676
 horm-2.620
 nerv-2.511
 mosqu-2.483
 behavi-2.463
Tokenifter
Token ID18171
Feature activation+7.68e-01

Pos logit contributions
abase+0.727
rador+0.572
 MB+0.569
 CAD+0.532
ielding+0.527
Neg logit contributions
 moons-0.660
 horm-0.641
 nerv-0.617
 mosqu-0.602
 behavi-0.586
Token was
Token ID373
Feature activation+1.96e-01

Pos logit contributions
abase+0.702
rador+0.564
 MB+0.560
 CAD+0.526
ielding+0.522
Neg logit contributions
 moons-0.561
 horm-0.543
 nerv-0.522
 mosqu-0.506
 behavi-0.493
Token a
Token ID257
Feature activation+8.72e-01

Pos logit contributions
abase+0.170
rador+0.134
 MB+0.133
 CAD+0.124
ielding+0.123
Neg logit contributions
 moons-0.154
 horm-0.149
 nerv-0.144
 mosqu-0.139
 behavi-0.135
Token case
Token ID1339
Feature activation-5.10e-01

Pos logit contributions
abase+0.784
rador+0.628
 MB+0.625
 CAD+0.588
ielding+0.581
Neg logit contributions
 moons-0.645
 horm-0.627
 nerv-0.602
 mosqu-0.588
 behavi-0.572
TokenT
Token ID51
Feature activation-2.52e-01

Pos logit contributions
 moons+0.146
 horm+0.141
 nerv+0.136
 mosqu+0.131
 behavi+0.128
Neg logit contributions
abase-0.180
rador-0.145
 MB-0.143
 CAD-0.135
ielding-0.134
Tokenear
Token ID451
Feature activation+8.89e-01

Pos logit contributions
 moons+0.185
 horm+0.179
 nerv+0.173
 mosqu+0.167
 behavi+0.163
Neg logit contributions
abase-0.231
rador-0.185
 MB-0.184
 CAD-0.173
ielding-0.171
Token
Token ID198
Feature activation-2.96e-01

Pos logit contributions
abase+0.797
rador+0.635
 MB+0.633
 CAD+0.590
ielding+0.587
Neg logit contributions
 moons-0.663
 horm-0.650
 nerv-0.622
 mosqu-0.605
 behavi-0.589
Token
Token ID198
Feature activation-1.87e-01

Pos logit contributions
 moons+0.216
 horm+0.206
 nerv+0.200
 mosqu+0.186
 behavi+0.182
Neg logit contributions
abase-0.272
rador-0.219
 MB-0.213
ielding-0.201
 CAD-0.201
TokenV
Token ID53
Feature activation+9.68e-02

Pos logit contributions
 moons+0.138
 horm+0.133
 nerv+0.128
 mosqu+0.124
 behavi+0.121
Neg logit contributions
abase-0.171
rador-0.137
 MB-0.136
 CAD-0.128
ielding-0.127
Tokenoid
Token ID1868
Feature activation+3.30e+00

Pos logit contributions
abase+0.083
rador+0.065
 MB+0.065
 CAD+0.060
ielding+0.060
Neg logit contributions
 moons-0.077
 horm-0.074
 nerv-0.072
 mosqu-0.069
 behavi-0.068
TokenRay
Token ID19591
Feature activation+1.48e+00

Pos logit contributions
abase+2.947
 MB+2.351
rador+2.349
 CAD+2.202
ielding+2.178
Neg logit contributions
 moons-2.432
 horm-2.376
 nerv-2.289
 mosqu-2.250
 behavi-2.181
Token
Token ID198
Feature activation-8.59e-02

Pos logit contributions
abase+1.318
rador+1.054
 MB+1.051
 CAD+0.986
ielding+0.972
Neg logit contributions
 moons-1.106
 horm-1.076
 nerv-1.032
 mosqu-1.008
 behavi-0.979
Token
Token ID198
Feature activation-9.46e-02

Pos logit contributions
 moons+0.063
 horm+0.060
 nerv+0.058
 mosqu+0.055
 behavi+0.053
Neg logit contributions
abase-0.079
rador-0.063
 MB-0.062
 CAD-0.058
ielding-0.058
TokenJ
Token ID41
Feature activation-4.24e-01

Pos logit contributions
 moons+0.070
 horm+0.067
 nerv+0.065
 mosqu+0.063
 behavi+0.061
Neg logit contributions
abase-0.086
rador-0.069
 MB-0.068
 CAD-0.064
ielding-0.064
TokenKS
Token ID27015
Feature activation-1.56e+00

Pos logit contributions
 moons+0.338
 horm+0.328
 nerv+0.317
 mosqu+0.307
 behavi+0.300
Neg logit contributions
abase-0.360
rador-0.283
 MB-0.281
 CAD-0.262
ielding-0.260
Tokens
Token ID82
Feature activation+3.56e-01

Pos logit contributions
abase+0.271
rador+0.220
 MB+0.217
 CAD+0.203
ielding+0.202
Neg logit contributions
 moons-0.219
 horm-0.213
 nerv-0.205
 mosqu-0.198
 behavi-0.194
Token
Token ID851
Feature activation+9.59e-01

Pos logit contributions
abase+0.320
rador+0.256
 MB+0.256
 CAD+0.239
ielding+0.236
Neg logit contributions
 moons-0.265
 horm-0.258
 nerv-0.248
 mosqu-0.240
 behavi-0.234
Token Cody
Token ID27035
Feature activation+4.79e-01

Pos logit contributions
abase+0.801
rador+0.628
 MB+0.627
 CAD+0.585
ielding+0.575
Neg logit contributions
 moons-0.774
 horm-0.753
 nerv-0.726
 mosqu-0.706
 behavi-0.690
Token Wester
Token ID32104
Feature activation+4.48e-01

Pos logit contributions
abase+0.419
 MB+0.333
rador+0.332
 CAD+0.311
ielding+0.307
Neg logit contributions
 moons-0.367
 horm-0.357
 nerv-0.344
 mosqu-0.335
 behavi-0.327
Tokenlund
Token ID37525
Feature activation+4.15e-01

Pos logit contributions
abase+0.410
rador+0.331
 MB+0.329
 CAD+0.308
ielding+0.305
Neg logit contributions
 moons-0.327
 horm-0.316
 nerv-0.305
 mosqu-0.296
 behavi-0.288
Token (@
Token ID4275
Feature activation+3.27e+00

Pos logit contributions
abase+0.420
rador+0.347
 MB+0.345
 CAD+0.327
ielding+0.323
Neg logit contributions
 moons-0.262
 horm-0.253
 nerv-0.241
 mosqu-0.233
 behavi-0.225
TokenC
Token ID34
Feature activation+1.76e-01

Pos logit contributions
abase+2.528
rador+1.964
 MB+1.917
 CAD+1.796
ielding+1.788
Neg logit contributions
 moons-2.824
 horm-2.764
 nerv-2.670
 mosqu-2.600
 behavi-2.563
Tokenody
Token ID1118
Feature activation+1.57e+00

Pos logit contributions
abase+0.124
rador+0.093
 MB+0.091
 CAD+0.084
ielding+0.083
Neg logit contributions
 moons-0.165
 horm-0.161
 nerv-0.156
 mosqu-0.153
 behavi-0.150
TokenW
Token ID54
Feature activation-5.23e-01

Pos logit contributions
abase+1.345
rador+1.067
 MB+1.060
 CAD+0.989
ielding+0.989
Neg logit contributions
 moons-1.218
 horm-1.186
 nerv-1.150
 mosqu-1.117
 behavi-1.092
Tokenester
Token ID7834
Feature activation+7.17e-01

Pos logit contributions
 moons+0.407
 horm+0.395
 nerv+0.380
 mosqu+0.370
 behavi+0.361
Neg logit contributions
abase-0.454
rador-0.361
 MB-0.357
 CAD-0.334
ielding-0.333
Tokenlund
Token ID37525
Feature activation+1.42e+00

Pos logit contributions
abase+0.473
rador+0.343
 MB+0.338
 CAD+0.308
ielding+0.304
Neg logit contributions
 moons-0.706
 horm-0.688
 nerv-0.669
 mosqu-0.650
 behavi-0.638
Token 411
Token ID43184
Feature activation-1.10e+00

Pos logit contributions
 moons+0.704
 horm+0.683
 nerv+0.664
 mosqu+0.641
 behavi+0.626
Neg logit contributions
abase-0.593
rador-0.455
 MB-0.442
ielding-0.409
 CAD-0.408
Token horsepower
Token ID36696
Feature activation-8.61e-01

Pos logit contributions
 moons+0.838
 horm+0.814
 nerv+0.783
 mosqu+0.760
 behavi+0.741
Neg logit contributions
abase-0.973
rador-0.776
 MB-0.771
 CAD-0.722
ielding-0.715
Token and
Token ID290
Feature activation-4.90e-02

Pos logit contributions
 moons+0.519
 horm+0.497
 nerv+0.475
 mosqu+0.454
 behavi+0.439
Neg logit contributions
abase-0.899
rador-0.745
 MB-0.737
 CAD-0.700
ielding-0.696
Token 4
Token ID604
Feature activation-1.05e-01

Pos logit contributions
 moons+0.045
 horm+0.044
 nerv+0.043
 mosqu+0.042
 behavi+0.041
Neg logit contributions
abase-0.035
rador-0.027
 MB-0.026
 CAD-0.024
ielding-0.024
Token34
Token ID2682
Feature activation+4.08e-02

Pos logit contributions
 moons+0.080
 horm+0.078
 nerv+0.075
 mosqu+0.073
 behavi+0.071
Neg logit contributions
abase-0.093
rador-0.074
 MB-0.073
 CAD-0.069
ielding-0.068
Token lb
Token ID18360
Feature activation-4.26e+00

Pos logit contributions
abase+0.034
rador+0.027
 MB+0.027
 CAD+0.025
ielding+0.025
Neg logit contributions
 moons-0.033
 horm-0.032
 nerv-0.031
 mosqu-0.030
 behavi-0.029
Token.-
Token ID7874
Feature activation-4.49e-01

Pos logit contributions
 moons+2.108
 horm+1.935
 nerv+1.864
 mosqu+1.654
 behavi+1.574
Neg logit contributions
abase-4.890
rador-4.144
 MB-3.993
 CAD-3.840
ielding-3.824
Tokenft
Token ID701
Feature activation-1.28e+00

Pos logit contributions
 moons+0.401
 horm+0.386
 nerv+0.377
 mosqu+0.355
 seiz+0.349
Neg logit contributions
abase-0.338
rador-0.258
 MB-0.252
 CAD-0.232
ielding-0.227
Token.
Token ID13
Feature activation+4.30e-02

Pos logit contributions
 moons+0.777
 horm+0.744
 nerv+0.712
 mosqu+0.682
 behavi+0.659
Neg logit contributions
abase-1.327
rador-1.097
 MB-1.084
 CAD-1.031
ielding-1.022
Token of
Token ID286
Feature activation-1.98e-01

Pos logit contributions
abase+0.035
rador+0.027
 MB+0.027
 CAD+0.025
ielding+0.025
Neg logit contributions
 moons-0.036
 horm-0.035
 nerv-0.034
 mosqu-0.033
 behavi-0.032
Token torque
Token ID26415
Feature activation-9.57e-01

Pos logit contributions
 moons+0.109
 horm+0.105
 nerv+0.099
 mosqu+0.095
 behavi+0.092
Neg logit contributions
abase-0.216
rador-0.180
 MB-0.179
 CAD-0.171
ielding-0.169
Token all
Token ID477
Feature activation-6.22e-02

Pos logit contributions
 moons+0.796
 horm+0.769
 nerv+0.740
 mosqu+0.715
 behavi+0.696
Neg logit contributions
abase-0.906
rador-0.720
 MB-0.709
 CAD-0.666
ielding-0.661
Token minions
Token ID22811
Feature activation-3.77e-01

Pos logit contributions
 moons+0.046
 horm+0.044
 nerv+0.042
 mosqu+0.041
 behavi+0.040
Neg logit contributions
abase-0.057
rador-0.046
 MB-0.045
 CAD-0.043
ielding-0.042
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
 moons+0.247
 horm+0.239
 nerv+0.228
 mosqu+0.220
 behavi+0.213
Neg logit contributions
abase-0.373
rador-0.305
 MB-0.303
 CAD-0.287
ielding-0.285
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
 moons+0.158
 horm+0.153
 nerv+0.148
 mosqu+0.143
 behavi+0.139
Neg logit contributions
abase-0.182
rador-0.145
 MB-0.144
 CAD-0.135
ielding-0.134
Token
Token ID198
Feature activation-2.64e-01

Pos logit contributions
 moons+0.150
 horm+0.143
 nerv+0.139
 mosqu+0.127
 behavi+0.125
Neg logit contributions
abase-0.194
rador-0.157
 MB-0.152
ielding-0.144
 CAD-0.144
TokenIGN
Token ID16284
Feature activation-4.01e+00

Pos logit contributions
 moons+0.168
 horm+0.161
 nerv+0.154
 mosqu+0.148
 behavi+0.143
Neg logit contributions
abase-0.267
rador-0.219
 MB-0.218
 CAD-0.206
ielding-0.205
Token:
Token ID25
Feature activation-1.37e+00

Pos logit contributions
 moons+2.489
 horm+2.247
 nerv+2.230
 Sparrow+1.940
 Quake+1.918
Neg logit contributions
abase-4.103
rador-3.360
 MB-3.202
ielding-3.121
olesc-3.066
Token Sure
Token ID10889
Feature activation-2.27e+00

Pos logit contributions
 moons+1.008
 horm+0.972
 nerv+0.937
 mosqu+0.900
 behavi+0.876
Neg logit contributions
abase-1.240
rador-0.996
 MB-0.980
 CAD-0.922
ielding-0.920
Token.
Token ID13
Feature activation-3.83e-02

Pos logit contributions
 moons+1.579
 horm+1.516
 nerv+1.460
 mosqu+1.397
 behavi+1.366
Neg logit contributions
abase-2.159
rador-1.759
 MB-1.734
 CAD-1.642
ielding-1.630
Token Before
Token ID7413
Feature activation-4.43e-01

Pos logit contributions
 moons+0.029
 horm+0.028
 nerv+0.027
 mosqu+0.027
 behavi+0.026
Neg logit contributions
abase-0.034
 MB-0.027
rador-0.027
 CAD-0.025
ielding-0.025
Token we
Token ID356
Feature activation-1.89e-01

Pos logit contributions
 moons+0.347
 horm+0.337
 nerv+0.325
 mosqu+0.315
 behavi+0.307
Neg logit contributions
abase-0.382
rador-0.302
 MB-0.300
 CAD-0.281
ielding-0.278
TokenAl
Token ID2348
Feature activation-3.64e-01

Pos logit contributions
 moons+0.334
 horm+0.324
 nerv+0.313
 mosqu+0.302
 behavi+0.298
Neg logit contributions
abase-0.324
rador-0.252
 MB-0.249
 CAD-0.232
ielding-0.230
Tokenignment
Token ID16747
Feature activation-1.04e+00

Pos logit contributions
 moons+0.393
 horm+0.383
 nerv+0.375
 mosqu+0.362
 behavi+0.357
Neg logit contributions
abase-0.202
rador-0.136
 MB-0.136
 CAD-0.119
ielding-0.115
Token]
Token ID60
Feature activation+5.11e-01

Pos logit contributions
 moons+0.944
 horm+0.913
 nerv+0.888
 mosqu+0.864
 behavi+0.846
Neg logit contributions
abase-0.764
rador-0.577
 MB-0.566
 CAD-0.522
ielding-0.517
Token::
Token ID3712
Feature activation+1.81e-01

Pos logit contributions
abase+0.381
rador+0.289
 MB+0.283
 CAD+0.261
ielding+0.259
Neg logit contributions
 moons-0.460
 horm-0.445
 nerv-0.433
 mosqu-0.416
 behavi-0.409
TokenCenter
Token ID23656
Feature activation-5.29e-01

Pos logit contributions
abase+0.141
rador+0.109
 MB+0.107
 CAD+0.099
ielding+0.098
Neg logit contributions
 moons-0.157
 horm-0.152
 nerv-0.147
 mosqu-0.143
 behavi-0.140
Token break
Token ID2270
Feature activation-3.77e+00

Pos logit contributions
 moons+0.506
 horm+0.490
 nerv+0.477
 mosqu+0.464
 behavi+0.456
Neg logit contributions
abase-0.365
rador-0.269
 MB-0.262
 CAD-0.240
ielding-0.239
Token }
Token ID1782
Feature activation-6.42e-02

Pos logit contributions
 moons+2.490
 horm+2.383
 nerv+2.304
 mosqu+2.179
 behavi+2.128
Neg logit contributions
abase-3.669
rador-2.974
 MB-2.926
ielding-2.793
 CAD-2.761
Token Left
Token ID9578
Feature activation+1.49e+00

Pos logit contributions
 moons+0.047
 horm+0.046
 nerv+0.044
 mosqu+0.042
 behavi+0.041
Neg logit contributions
abase-0.058
rador-0.047
 MB-0.046
 CAD-0.043
ielding-0.043
Token {
Token ID1391
Feature activation+2.53e+00

Pos logit contributions
abase+1.272
rador+1.007
 MB+0.998
 CAD+0.937
ielding+0.925
Neg logit contributions
 moons-1.171
 horm-1.139
 nerv-1.095
 mosqu-1.067
 behavi-1.038
Token $
Token ID720
Feature activation-2.11e+00

Pos logit contributions
abase+1.587
 MB+1.144
rador+1.135
 CAD+1.032
ielding+0.997
Neg logit contributions
 moons-2.555
 horm-2.512
 nerv-2.432
 mosqu-2.384
 behavi-2.333
Tokens
Token ID82
Feature activation-1.17e-01

Pos logit contributions
 moons+1.439
 horm+1.380
 nerv+1.324
 mosqu+1.273
 behavi+1.240
Neg logit contributions
abase-2.013
rador-1.643
 MB-1.624
 CAD-1.536
ielding-1.521
Token-
Token ID12
Feature activation+1.21e-01

Pos logit contributions
 moons+0.057
 horm+0.055
 nerv+0.054
 mosqu+0.052
 behavi+0.051
Neg logit contributions
abase-0.049
rador-0.037
 MB-0.037
 CAD-0.034
ielding-0.034
Tokenim
Token ID320
Feature activation-2.57e-01

Pos logit contributions
abase+0.109
rador+0.087
 MB+0.087
 CAD+0.081
ielding+0.080
Neg logit contributions
 moons-0.091
 horm-0.088
 nerv-0.085
 mosqu-0.082
 behavi-0.080
Tokenperial
Token ID7629
Feature activation-3.30e-01

Pos logit contributions
 moons+0.235
 horm+0.229
 nerv+0.222
 mosqu+0.216
 behavi+0.211
Neg logit contributions
abase-0.187
rador-0.141
 MB-0.139
 CAD-0.129
ielding-0.127
Tokenist
Token ID396
Feature activation+4.41e-01

Pos logit contributions
 moons+0.282
 horm+0.272
 nerv+0.266
 mosqu+0.257
 behavi+0.250
Neg logit contributions
abase-0.262
rador-0.200
 MB-0.197
 CAD-0.184
ielding-0.183
Token sc
Token ID629
Feature activation-8.23e-01

Pos logit contributions
abase+0.384
rador+0.305
 MB+0.302
 CAD+0.283
ielding+0.280
Neg logit contributions
 moons-0.341
 horm-0.331
 nerv-0.319
 mosqu-0.309
 behavi-0.302
Tokenound
Token ID633
Feature activation-3.73e+00

Pos logit contributions
 moons+0.391
 horm+0.370
 nerv+0.348
 mosqu+0.329
 behavi+0.313
Neg logit contributions
abase-0.963
rador-0.813
 MB-0.809
 CAD-0.775
ielding-0.768
Tokenrel
Token ID2411
Feature activation-1.86e+00

Pos logit contributions
 moons+2.303
 horm+2.197
 nerv+2.063
 mosqu+1.951
 behavi+1.880
Neg logit contributions
abase-3.832
 MB-3.083
rador-3.058
 CAD-2.930
ielding-2.873
Token Vac
Token ID25709
Feature activation+1.35e+00

Pos logit contributions
 moons+1.416
 horm+1.363
 nerv+1.318
 mosqu+1.266
 behavi+1.225
Neg logit contributions
abase-1.642
rador-1.313
 MB-1.280
 CAD-1.214
ielding-1.212
Tokenlav
Token ID18809
Feature activation-9.35e-01

Pos logit contributions
abase+1.343
rador+1.103
 MB+1.097
 CAD+1.035
ielding+1.028
Neg logit contributions
 moons-0.873
 horm-0.849
 nerv-0.808
 mosqu-0.787
 behavi-0.763
Token Ha
Token ID9398
Feature activation+4.76e-01

Pos logit contributions
 moons+0.873
 horm+0.845
 nerv+0.818
 mosqu+0.781
 behavi+0.766
Neg logit contributions
abase-0.676
rador-0.496
 MB-0.470
ielding-0.447
 CAD-0.446
Tokenvel
Token ID626
Feature activation+1.15e-01

Pos logit contributions
abase+0.341
rador+0.255
 MB+0.252
 CAD+0.232
ielding+0.229
Neg logit contributions
 moons-0.442
 horm-0.431
 nerv-0.418
 mosqu-0.407
 behavi-0.399
Token:
Token ID25
Feature activation-5.82e-01

Pos logit contributions
 moons+0.331
 horm+0.320
 nerv+0.308
 mosqu+0.298
 behavi+0.289
Neg logit contributions
abase-0.431
rador-0.348
 MB-0.345
 CAD-0.325
ielding-0.322
Token50
Token ID1120
Feature activation+2.76e-01

Pos logit contributions
 moons+0.412
 horm+0.395
 nerv+0.381
 mosqu+0.359
 behavi+0.350
Neg logit contributions
abase-0.548
rador-0.443
 MB-0.434
 CAD-0.410
ielding-0.410
Token pur
Token ID1308
Feature activation-9.39e-01

Pos logit contributions
abase+0.264
rador+0.216
 MB+0.215
 CAD+0.202
ielding+0.200
Neg logit contributions
 moons-0.189
 horm-0.182
 nerv-0.174
 mosqu-0.169
 behavi-0.165
Tokenak
Token ID461
Feature activation-8.12e-01

Pos logit contributions
 moons+0.682
 horm+0.652
 nerv+0.637
 mosqu+0.593
 seiz+0.578
Neg logit contributions
abase-0.849
rador-0.685
 MB-0.674
 CAD-0.637
ielding-0.629
Tokenushi
Token ID17731
Feature activation+4.04e-02

Pos logit contributions
 moons+0.716
 horm+0.696
 nerv+0.674
 mosqu+0.658
 behavi+0.645
Neg logit contributions
abase-0.623
rador-0.477
 MB-0.470
 CAD-0.435
ielding-0.432
Token wrote
Token ID2630
Feature activation-3.63e+00

Pos logit contributions
abase+0.033
rador+0.026
 MB+0.026
 CAD+0.024
ielding+0.024
Neg logit contributions
 moons-0.033
 horm-0.032
 nerv-0.031
 mosqu-0.030
 behavi-0.030
Token:
Token ID25
Feature activation-1.76e+00

Pos logit contributions
 moons+2.272
 horm+2.084
 nerv+2.076
 Quake+1.763
 Sparrow+1.749
Neg logit contributions
abase-3.686
rador-3.048
 MB-2.887
ielding-2.816
 CAD-2.761
Token
Token ID198
Feature activation-1.79e+00

Pos logit contributions
 moons+1.300
 horm+1.249
 nerv+1.207
 mosqu+1.144
 behavi+1.119
Neg logit contributions
abase-1.600
rador-1.284
 MB-1.260
 CAD-1.187
ielding-1.183
Token
Token ID198
Feature activation-1.75e+00

Pos logit contributions
 moons+1.263
 horm+1.192
 nerv+1.161
 mosqu+1.046
 behavi+1.034
Neg logit contributions
abase-1.688
rador-1.366
 MB-1.314
ielding-1.252
 CAD-1.245
TokenHappy
Token ID25082
Feature activation-4.30e-01

Pos logit contributions
 moons+1.150
 horm+1.106
 nerv+1.057
 mosqu+1.012
 behavi+0.979
Neg logit contributions
abase-1.731
rador-1.421
 MB-1.404
 CAD-1.331
ielding-1.315
Token it
Token ID340
Feature activation-1.29e+00

Pos logit contributions
 moons+0.353
 horm+0.343
 nerv+0.331
 mosqu+0.321
 behavi+0.314
Neg logit contributions
abase-0.354
rador-0.277
 MB-0.274
 CAD-0.256
ielding-0.253
Token this
Token ID428
Feature activation-1.91e-01

Pos logit contributions
 moons+0.136
 horm+0.131
 nerv+0.127
 mosqu+0.122
 behavi+0.119
Neg logit contributions
abase-0.165
rador-0.132
 MB-0.131
 CAD-0.123
ielding-0.122
Token article
Token ID2708
Feature activation+3.36e-01

Pos logit contributions
 moons+0.141
 horm+0.137
 nerv+0.131
 mosqu+0.127
 behavi+0.124
Neg logit contributions
abase-0.174
rador-0.139
 MB-0.138
 CAD-0.130
ielding-0.129
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
abase+0.313
rador+0.253
 MB+0.251
 CAD+0.236
ielding+0.234
Neg logit contributions
 moons-0.240
 horm-0.232
 nerv-0.223
 mosqu-0.216
 behavi-0.210
Token
Token ID198
Feature activation-1.05e-02

Pos logit contributions
abase+0.148
rador+0.118
 MB+0.117
 CAD+0.109
ielding+0.109
Neg logit contributions
 moons-0.126
 horm-0.122
 nerv-0.118
 mosqu-0.114
 behavi-0.111
Token
Token ID198
Feature activation-5.40e-02

Pos logit contributions
 moons+0.008
 horm+0.007
 nerv+0.007
 mosqu+0.007
 behavi+0.006
Neg logit contributions
abase-0.010
rador-0.008
 MB-0.008
 CAD-0.007
ielding-0.007
TokenNOTE
Token ID16580
Feature activation-3.62e+00

Pos logit contributions
 moons+0.039
 horm+0.037
 nerv+0.036
 mosqu+0.034
 behavi+0.034
Neg logit contributions
abase-0.050
rador-0.040
 MB-0.040
 CAD-0.037
ielding-0.037
Token:
Token ID25
Feature activation-3.75e-01

Pos logit contributions
 moons+2.431
 horm+2.338
 nerv+2.268
 mosqu+2.136
 behavi+2.074
Neg logit contributions
abase-3.514
rador-2.850
 MB-2.743
ielding-2.647
 CAD-2.602
Token Also
Token ID4418
Feature activation-8.27e-01

Pos logit contributions
 moons+0.286
 horm+0.277
 nerv+0.267
 mosqu+0.258
 behavi+0.251
Neg logit contributions
abase-0.331
rador-0.264
 MB-0.260
 CAD-0.245
ielding-0.243
Token,
Token ID11
Feature activation-4.64e-01

Pos logit contributions
 moons+0.623
 horm+0.602
 nerv+0.581
 mosqu+0.559
 behavi+0.544
Neg logit contributions
abase-0.739
rador-0.590
 MB-0.580
 CAD-0.547
ielding-0.545
Token it
Token ID340
Feature activation-2.39e-01

Pos logit contributions
 moons+0.330
 horm+0.319
 nerv+0.306
 mosqu+0.296
 behavi+0.287
Neg logit contributions
abase-0.434
rador-0.351
 MB-0.347
 CAD-0.327
ielding-0.325
Token should
Token ID815
Feature activation+1.01e+00

Pos logit contributions
 moons+0.176
 horm+0.171
 nerv+0.164
 mosqu+0.159
 behavi+0.155
Neg logit contributions
abase-0.217
rador-0.174
 MB-0.173
 CAD-0.163
ielding-0.161
Token [
Token ID685
Feature activation+8.88e-02

Pos logit contributions
 moons+0.192
 horm+0.187
 nerv+0.181
 mosqu+0.176
 behavi+0.172
Neg logit contributions
abase-0.182
rador-0.141
 MB-0.140
 CAD-0.130
ielding-0.128
Token10
Token ID940
Feature activation-1.07e+00

Pos logit contributions
abase+0.083
rador+0.067
 MB+0.067
 CAD+0.063
ielding+0.062
Neg logit contributions
 moons-0.063
 horm-0.061
 nerv-0.058
 mosqu-0.056
 behavi-0.055
Token:
Token ID25
Feature activation-1.54e+00

Pos logit contributions
 moons+0.711
 horm+0.665
 nerv+0.649
 mosqu+0.574
 seiz+0.561
Neg logit contributions
abase-1.052
rador-0.861
 MB-0.828
ielding-0.795
 CAD-0.789
Token47
Token ID2857
Feature activation-2.11e+00

Pos logit contributions
 moons+1.066
 horm+1.022
 nerv+0.987
 mosqu+0.952
 behavi+0.916
Neg logit contributions
abase-1.478
rador-1.200
 MB-1.168
 CAD-1.115
ielding-1.110
Token]
Token ID60
Feature activation-1.70e+00

Pos logit contributions
 moons+1.800
 horm+1.681
 nerv+1.667
 Sparrow+1.496
 Quake+1.495
Neg logit contributions
abase-1.685
rador-1.304
 MB-1.210
ielding-1.164
olesc-1.137
Token <@
Token ID32406
Feature activation-3.61e+00

Pos logit contributions
 moons+1.630
 horm+1.588
 nerv+1.542
 mosqu+1.507
 behavi+1.473
Neg logit contributions
abase-1.176
rador-0.869
 MB-0.850
 CAD-0.778
ielding-0.774
Tokent
Token ID83
Feature activation-8.25e-01

Pos logit contributions
 moons+2.749
 horm+2.654
 nerv+2.528
 mosqu+2.438
 seiz+2.352
Neg logit contributions
abase-3.131
rador-2.512
 MB-2.476
 CAD-2.344
ielding-2.287
Tokenay
Token ID323
Feature activation-6.48e-02

Pos logit contributions
 moons+0.677
 horm+0.656
 nerv+0.634
 mosqu+0.622
 behavi+0.610
Neg logit contributions
abase-0.685
rador-0.535
 MB-0.529
 CAD-0.493
ielding-0.492
Tokenl
Token ID75
Feature activation-1.26e+00

Pos logit contributions
 moons+0.052
 horm+0.051
 nerv+0.049
 mosqu+0.047
 behavi+0.046
Neg logit contributions
abase-0.054
rador-0.043
 MB-0.042
 CAD-0.040
ielding-0.039
Tokenort
Token ID419
Feature activation+2.17e-01

Pos logit contributions
 moons+0.805
 horm+0.775
 nerv+0.741
 mosqu+0.713
 behavi+0.690
Neg logit contributions
abase-1.267
rador-1.040
 MB-1.032
 CAD-0.978
ielding-0.970
Tokenot
Token ID313
Feature activation+1.04e+00

Pos logit contributions
abase+0.182
rador+0.143
 MB+0.141
 CAD+0.132
ielding+0.131
Neg logit contributions
 moons-0.175
 horm-0.170
 nerv-0.164
 mosqu-0.160
 behavi-0.156
TokenMI
Token ID8895
Feature activation+7.09e-01

Pos logit contributions
 moons+0.288
 horm+0.276
 nerv+0.263
 mosqu+0.251
 behavi+0.244
Neg logit contributions
abase-0.502
rador-0.415
 MB-0.411
 CAD-0.390
ielding-0.388
Token
Token ID41305
Feature activation+2.52e-01

Pos logit contributions
abase+0.540
rador+0.414
 MB+0.404
 CAD+0.373
ielding+0.370
Neg logit contributions
 moons-0.629
 horm-0.610
 nerv-0.595
 mosqu-0.572
 behavi-0.561
Token24
Token ID1731
Feature activation+4.16e-01

Pos logit contributions
abase+0.185
rador+0.140
 MB+0.136
 CAD+0.126
ielding+0.125
Neg logit contributions
 moons-0.230
 horm-0.223
 nerv-0.218
 mosqu-0.210
 behavi-0.206
Token.
Token ID13
Feature activation-6.53e-01

Pos logit contributions
abase+0.360
rador+0.286
 MB+0.282
 CAD+0.264
ielding+0.262
Neg logit contributions
 moons-0.324
 horm-0.313
 nerv-0.303
 mosqu-0.292
 behavi-0.285
Token99
Token ID2079
Feature activation-1.43e+00

Pos logit contributions
 moons+0.447
 horm+0.430
 nerv+0.415
 mosqu+0.396
 behavi+0.385
Neg logit contributions
abase-0.629
rador-0.511
 MB-0.504
 CAD-0.476
ielding-0.475
Token kg
Token ID14211
Feature activation-3.54e+00

Pos logit contributions
 moons+1.337
 horm+1.289
 nerv+1.267
 mosqu+1.212
 behavi+1.191
Neg logit contributions
abase-1.027
rador-0.771
 MB-0.737
ielding-0.679
 CAD-0.674
Token/
Token ID14
Feature activation-2.26e-01

Pos logit contributions
 moons+2.888
 horm+2.717
 nerv+2.708
 mosqu+2.531
 seiz+2.482
Neg logit contributions
abase-2.927
rador-2.318
 MB-2.201
xes-2.059
ielding-2.046
Tokenm
Token ID76
Feature activation-6.40e-01

Pos logit contributions
 moons+0.177
 horm+0.172
 nerv+0.165
 mosqu+0.160
 behavi+0.156
Neg logit contributions
abase-0.195
rador-0.155
 MB-0.152
 CAD-0.143
ielding-0.142
Token²
Token ID31185
Feature activation+7.11e-02

Pos logit contributions
 moons+0.477
 horm+0.458
 nerv+0.442
 mosqu+0.421
 behavi+0.408
Neg logit contributions
abase-0.575
rador-0.465
 MB-0.454
 CAD-0.426
ielding-0.422
Token),
Token ID828
Feature activation-2.59e-01

Pos logit contributions
abase+0.049
rador+0.037
 MB+0.036
 CAD+0.032
ielding+0.032
Neg logit contributions
 moons-0.068
 horm-0.066
 nerv-0.064
 mosqu-0.062
 behavi-0.061
Token overweight
Token ID22652
Feature activation-8.95e-01

Pos logit contributions
 moons+0.204
 horm+0.198
 nerv+0.192
 mosqu+0.185
 behavi+0.181
Neg logit contributions
abase-0.222
rador-0.175
 MB-0.173
 CAD-0.162
ielding-0.161
Token amazing
Token ID4998
Feature activation+2.19e-01

Pos logit contributions
 moons+0.131
 horm+0.126
 nerv+0.122
 mosqu+0.117
 behavi+0.114
Neg logit contributions
abase-0.161
rador-0.130
 MB-0.128
 CAD-0.120
ielding-0.120
Token I
Token ID314
Feature activation-2.07e-01

Pos logit contributions
abase+0.198
rador+0.159
 MB+0.158
 CAD+0.148
ielding+0.147
Neg logit contributions
 moons-0.162
 horm-0.157
 nerv-0.151
 mosqu-0.146
 behavi-0.142
Token've
Token ID1053
Feature activation-6.71e-02

Pos logit contributions
 moons+0.153
 horm+0.147
 nerv+0.142
 mosqu+0.136
 behavi+0.132
Neg logit contributions
abase-0.189
rador-0.151
 MB-0.149
 CAD-0.140
ielding-0.140
Token been
Token ID587
Feature activation-1.77e-01

Pos logit contributions
 moons+0.052
 horm+0.050
 nerv+0.049
 mosqu+0.046
 seiz+0.045
Neg logit contributions
abase-0.059
rador-0.047
 MB-0.045
ielding-0.043
 CAD-0.043
Token ch
Token ID442
Feature activation+4.97e-01

Pos logit contributions
 moons+0.131
 horm+0.127
 nerv+0.122
 mosqu+0.117
 behavi+0.114
Neg logit contributions
abase-0.161
rador-0.129
 MB-0.128
 CAD-0.120
ielding-0.119
Tokenomp
Token ID3361
Feature activation-3.49e+00

Pos logit contributions
abase+0.435
rador+0.345
 MB+0.343
 CAD+0.320
ielding+0.316
Neg logit contributions
 moons-0.383
 horm-0.370
 nerv-0.358
 mosqu-0.343
 behavi-0.333
Tokening
Token ID278
Feature activation-5.00e-01

Pos logit contributions
 moons+2.697
 horm+2.526
 nerv+2.470
 mosqu+2.281
 behavi+2.270
Neg logit contributions
abase-3.086
rador-2.454
 MB-2.386
 CAD-2.221
ielding-2.196
Token at
Token ID379
Feature activation+3.26e-01

Pos logit contributions
 moons+0.456
 horm+0.439
 nerv+0.428
 mosqu+0.411
 behavi+0.405
Neg logit contributions
abase-0.367
rador-0.279
 MB-0.273
ielding-0.253
 CAD-0.251
Token the
Token ID262
Feature activation-7.76e-02

Pos logit contributions
abase+0.298
rador+0.240
 MB+0.237
 CAD+0.223
ielding+0.222
Neg logit contributions
 moons-0.239
 horm-0.230
 nerv-0.222
 mosqu-0.214
 behavi-0.208
Token bit
Token ID1643
Feature activation+3.28e-01

Pos logit contributions
 moons+0.077
 horm+0.075
 nerv+0.073
 mosqu+0.071
 behavi+0.070
Neg logit contributions
abase-0.051
rador-0.037
 MB-0.036
 CAD-0.033
ielding-0.032
Token for
Token ID329
Feature activation+5.91e-02

Pos logit contributions
abase+0.310
rador+0.251
 MB+0.248
 CAD+0.234
ielding+0.232
Neg logit contributions
 moons-0.230
 horm-0.222
 nerv-0.214
 mosqu-0.205
 behavi-0.200
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
 moons+0.598
 horm+0.576
 nerv+0.552
 mosqu+0.531
 behavi+0.516
Neg logit contributions
abase-0.875
rador-0.714
 MB-0.708
 CAD-0.669
ielding-0.664
Token I
Token ID314
Feature activation-2.79e-01

Pos logit contributions
abase+0.100
rador+0.080
 MB+0.080
 CAD+0.075
ielding+0.074
Neg logit contributions
 moons-0.084
 horm-0.082
 nerv-0.079
 mosqu-0.076
 behavi-0.074
Token had
Token ID550
Feature activation+3.54e-01

Pos logit contributions
 moons+0.198
 horm+0.191
 nerv+0.184
 mosqu+0.177
 behavi+0.172
Neg logit contributions
abase-0.261
rador-0.211
 MB-0.209
 CAD-0.197
ielding-0.196
Token the
Token ID262
Feature activation-9.27e-01

Pos logit contributions
abase+0.313
rador+0.249
 MB+0.245
 CAD+0.230
ielding+0.230
Neg logit contributions
 moons-0.271
 horm-0.262
 nerv-0.253
 mosqu-0.244
 behavi-0.237
Token 10
Token ID838
Feature activation-9.86e-01

Pos logit contributions
 moons+0.706
 horm+0.681
 nerv+0.657
 mosqu+0.634
 behavi+0.616
Neg logit contributions
abase-0.820
rador-0.654
 MB-0.642
ielding-0.606
 CAD-0.605
Token"
Token ID1
Feature activation-3.46e+00

Pos logit contributions
 moons+0.770
 horm+0.747
 nerv+0.721
 mosqu+0.699
 behavi+0.681
Neg logit contributions
abase-0.852
rador-0.675
 MB-0.669
 CAD-0.626
ielding-0.620
Token 150
Token ID6640
Feature activation-2.48e-02

Pos logit contributions
 moons+2.594
 horm+2.478
 nerv+2.393
 mosqu+2.289
 seiz+2.235
Neg logit contributions
abase-3.077
rador-2.457
 MB-2.370
ielding-2.290
 CAD-2.256
Token watt
Token ID40114
Feature activation-6.47e-01

Pos logit contributions
 moons+0.017
 horm+0.017
 nerv+0.016
 mosqu+0.015
 behavi+0.015
Neg logit contributions
abase-0.024
rador-0.019
 MB-0.019
 CAD-0.018
ielding-0.018
Token J
Token ID449
Feature activation-1.59e-02

Pos logit contributions
 moons+0.488
 horm+0.471
 nerv+0.454
 mosqu+0.438
 behavi+0.426
Neg logit contributions
abase-0.577
rador-0.461
 MB-0.453
 CAD-0.427
ielding-0.426
TokenBL
Token ID9148
Feature activation-1.77e-01

Pos logit contributions
 moons+0.012
 horm+0.012
 nerv+0.011
 mosqu+0.011
 behavi+0.010
Neg logit contributions
abase-0.014
rador-0.011
 MB-0.011
 CAD-0.011
ielding-0.011
Token before
Token ID878
Feature activation+1.19e-01

Pos logit contributions
 moons+0.135
 horm+0.131
 nerv+0.127
 mosqu+0.123
 behavi+0.119
Neg logit contributions
abase-0.155
rador-0.124
 MB-0.122
 CAD-0.115
ielding-0.114
Token this
Token ID428
Feature activation-6.97e-01

Pos logit contributions
 moons+0.363
 horm+0.351
 nerv+0.338
 mosqu+0.326
 behavi+0.318
Neg logit contributions
abase-0.427
rador-0.341
 MB-0.336
 CAD-0.316
ielding-0.314
Token thing
Token ID1517
Feature activation-6.67e-01

Pos logit contributions
 moons+0.522
 horm+0.506
 nerv+0.486
 mosqu+0.469
 behavi+0.458
Neg logit contributions
abase-0.626
rador-0.501
 MB-0.495
 CAD-0.464
ielding-0.462
Token.
Token ID13
Feature activation-4.22e-01

Pos logit contributions
 moons+0.468
 horm+0.452
 nerv+0.434
 mosqu+0.419
 behavi+0.407
Neg logit contributions
abase-0.629
rador-0.510
 MB-0.505
 CAD-0.476
ielding-0.472
Token
Token ID198
Feature activation-1.61e-01

Pos logit contributions
 moons+0.331
 horm+0.320
 nerv+0.309
 mosqu+0.298
 behavi+0.291
Neg logit contributions
abase-0.364
rador-0.288
 MB-0.283
 CAD-0.265
ielding-0.264
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
 moons+0.116
 horm+0.110
 nerv+0.107
 mosqu+0.098
 behavi+0.096
Neg logit contributions
abase-0.150
rador-0.121
 MB-0.117
ielding-0.111
 CAD-0.111
TokenIGN
Token ID16284
Feature activation-3.39e+00

Pos logit contributions
 moons+0.082
 horm+0.080
 nerv+0.076
 mosqu+0.074
 behavi+0.072
Neg logit contributions
abase-0.112
rador-0.091
 MB-0.090
 CAD-0.085
ielding-0.085
Token:
Token ID25
Feature activation-1.29e+00

Pos logit contributions
 moons+2.135
 horm+1.949
 nerv+1.926
 Sparrow+1.669
 Quake+1.649
Neg logit contributions
abase-3.446
rador-2.821
 MB-2.697
ielding-2.619
 CAD-2.572
Token The
Token ID383
Feature activation-7.30e-01

Pos logit contributions
 moons+0.949
 horm+0.914
 nerv+0.881
 mosqu+0.844
 behavi+0.821
Neg logit contributions
abase-1.178
rador-0.949
 MB-0.930
ielding-0.876
 CAD-0.876
Token armour
Token ID18588
Feature activation-4.47e-01

Pos logit contributions
 moons+0.506
 horm+0.488
 nerv+0.468
 mosqu+0.451
 behavi+0.439
Neg logit contributions
abase-0.696
rador-0.565
 MB-0.559
 CAD-0.528
ielding-0.524
Token option
Token ID3038
Feature activation+1.10e+00

Pos logit contributions
 moons+0.330
 horm+0.320
 nerv+0.307
 mosqu+0.296
 behavi+0.289
Neg logit contributions
abase-0.406
rador-0.326
 MB-0.322
 CAD-0.303
ielding-0.301
Token
Token ID447
Feature activation-1.72e-02

Pos logit contributions
abase+0.976
rador+0.777
 MB+0.774
 CAD+0.725
ielding+0.716
Neg logit contributions
 moons-0.828
 horm-0.804
 nerv-0.773
 mosqu-0.754
 behavi-0.734
Tokenieving
Token ID30749
Feature activation-7.72e-01

Pos logit contributions
 moons+0.558
 horm+0.537
 nerv+0.521
 mosqu+0.501
 seiz+0.489
Neg logit contributions
abase-0.593
rador-0.468
 MB-0.467
 CAD-0.434
ielding-0.426
Token Hollywood
Token ID8502
Feature activation-1.75e-01

Pos logit contributions
 moons+0.593
 horm+0.572
 nerv+0.555
 mosqu+0.533
 behavi+0.519
Neg logit contributions
abase-0.680
rador-0.541
 MB-0.531
 CAD-0.499
ielding-0.498
Token agent
Token ID5797
Feature activation-1.63e+00

Pos logit contributions
 moons+0.131
 horm+0.127
 nerv+0.123
 mosqu+0.118
 behavi+0.115
Neg logit contributions
abase-0.157
rador-0.126
 MB-0.124
 CAD-0.117
ielding-0.116
Token and
Token ID290
Feature activation-6.70e-01

Pos logit contributions
 moons+1.266
 horm+1.217
 nerv+1.184
 mosqu+1.138
 behavi+1.106
Neg logit contributions
abase-1.417
rador-1.126
 MB-1.103
 CAD-1.037
ielding-1.033
Token anthrop
Token ID17911
Feature activation-2.99e-01

Pos logit contributions
 moons+0.496
 horm+0.477
 nerv+0.464
 mosqu+0.444
 behavi+0.433
Neg logit contributions
abase-0.610
rador-0.489
 MB-0.481
 CAD-0.453
ielding-0.451
Tokenomorphic
Token ID46374
Feature activation-3.38e+00

Pos logit contributions
 moons+0.298
 horm+0.290
 nerv+0.284
 mosqu+0.276
 behavi+0.269
Neg logit contributions
abase-0.193
rador-0.139
 MB-0.137
 CAD-0.125
ielding-0.123
Token cat
Token ID3797
Feature activation-8.90e-01

Pos logit contributions
 moons+2.489
 horm+2.376
 nerv+2.325
 mosqu+2.183
 behavi+2.114
Neg logit contributions
abase-3.113
rador-2.468
 MB-2.392
ielding-2.295
 CAD-2.260
Token Princess
Token ID8449
Feature activation+5.46e-01

Pos logit contributions
 moons+0.653
 horm+0.630
 nerv+0.607
 mosqu+0.586
 behavi+0.570
Neg logit contributions
abase-0.812
rador-0.651
 MB-0.645
 CAD-0.608
ielding-0.603
Token Carolyn
Token ID43450
Feature activation+2.79e-01

Pos logit contributions
abase+0.465
rador+0.367
 MB+0.363
 CAD+0.340
ielding+0.337
Neg logit contributions
 moons-0.432
 horm-0.419
 nerv-0.405
 mosqu-0.393
 behavi-0.383
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
abase+0.267
rador+0.217
 MB+0.217
 CAD+0.204
ielding+0.202
Neg logit contributions
 moons-0.190
 horm-0.185
 nerv-0.176
 mosqu-0.171
 behavi-0.166
Token She
Token ID1375
Feature activation-4.11e-01

Pos logit contributions
abase+0.100
rador+0.079
 MB+0.078
 CAD+0.074
ielding+0.073
Neg logit contributions
 moons-0.086
 horm-0.084
 nerv-0.081
 mosqu-0.078
 behavi-0.076
Token that
Token ID326
Feature activation+2.04e-02

Pos logit contributions
 moons+0.246
 horm+0.238
 nerv+0.229
 mosqu+0.221
 behavi+0.215
Neg logit contributions
abase-0.293
rador-0.235
 MB-0.231
 CAD-0.217
ielding-0.217
Token is
Token ID318
Feature activation-1.27e-01

Pos logit contributions
abase+0.018
rador+0.014
 MB+0.014
 CAD+0.013
ielding+0.013
Neg logit contributions
 moons-0.016
 horm-0.015
 nerv-0.015
 mosqu-0.014
 behavi-0.014
Token,
Token ID11
Feature activation+5.12e-01

Pos logit contributions
 moons+0.103
 horm+0.100
 nerv+0.096
 mosqu+0.094
 behavi+0.091
Neg logit contributions
abase-0.106
rador-0.083
 MB-0.082
 CAD-0.077
ielding-0.076
Token for
Token ID329
Feature activation+4.46e-01

Pos logit contributions
abase+0.464
rador+0.372
 MB+0.369
 CAD+0.347
ielding+0.343
Neg logit contributions
 moons-0.379
 horm-0.367
 nerv-0.353
 mosqu-0.342
 behavi-0.333
Token Michael
Token ID3899
Feature activation-5.65e-01

Pos logit contributions
abase+0.398
rador+0.318
 MB+0.315
 CAD+0.295
ielding+0.293
Neg logit contributions
 moons-0.336
 horm-0.325
 nerv-0.313
 mosqu-0.303
 behavi-0.295
Token Ign
Token ID16583
Feature activation-3.37e+00

Pos logit contributions
 moons+0.445
 horm+0.431
 nerv+0.415
 mosqu+0.401
 behavi+0.390
Neg logit contributions
abase-0.485
rador-0.385
 MB-0.376
 CAD-0.354
ielding-0.352
Tokenat
Token ID265
Feature activation+1.99e-01

Pos logit contributions
 moons+2.706
 horm+2.560
 nerv+2.544
 seiz+2.342
 mosqu+2.241
Neg logit contributions
abase-2.756
rador-2.119
 MB-2.030
 CAD-1.954
ielding-1.853
Tokenie
Token ID494
Feature activation-4.06e-01

Pos logit contributions
abase+0.194
rador+0.158
 MB+0.156
 CAD+0.149
ielding+0.147
Neg logit contributions
 moons-0.133
 horm-0.128
 nerv-0.123
 mosqu-0.117
 behavi-0.114
Tokenff
Token ID487
Feature activation-1.19e+00

Pos logit contributions
 moons+0.356
 horm+0.345
 nerv+0.335
 mosqu+0.324
 behavi+0.318
Neg logit contributions
abase-0.313
rador-0.242
 MB-0.233
 CAD-0.217
ielding-0.215
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
 moons+0.851
 horm+0.820
 nerv+0.791
 mosqu+0.761
 behavi+0.741
Neg logit contributions
abase-1.108
rador-0.895
 MB-0.882
 CAD-0.833
ielding-0.827
Token At
Token ID1629
Feature activation-3.87e-01

Pos logit contributions
abase+0.013
 MB+0.010
rador+0.010
 CAD+0.009
ielding+0.009
Neg logit contributions
 moons-0.011
 horm-0.011
 nerv-0.010
 mosqu-0.010
 behavi-0.010
Tokenm
Token ID76
Feature activation-1.39e+00

Pos logit contributions
 moons+1.466
 horm+1.424
 nerv+1.371
 mosqu+1.322
 behavi+1.281
Neg logit contributions
abase-1.594
rador-1.265
 MB-1.254
 CAD-1.179
ielding-1.159
Tokenew
Token ID413
Feature activation-1.55e+00

Pos logit contributions
 moons+1.105
 horm+1.074
 nerv+1.040
 mosqu+0.999
 seiz+0.966
Neg logit contributions
abase-1.157
rador-0.911
 MB-0.907
 CAD-0.849
ielding-0.835
Token2
Token ID17
Feature activation+3.93e-01

Pos logit contributions
 moons+1.241
 horm+1.201
 nerv+1.161
 mosqu+1.113
 seiz+1.078
Neg logit contributions
abase-1.308
rador-1.028
 MB-1.022
 CAD-0.957
ielding-0.938
Tokenking
Token ID3364
Feature activation-4.10e-02

Pos logit contributions
abase+0.334
rador+0.263
 MB+0.261
 CAD+0.244
ielding+0.241
Neg logit contributions
 moons-0.312
 horm-0.303
 nerv-0.292
 mosqu-0.283
 behavi-0.276
Token>
Token ID29
Feature activation-7.84e-01

Pos logit contributions
 moons+0.036
 horm+0.035
 nerv+0.034
 mosqu+0.033
 behavi+0.032
Neg logit contributions
abase-0.032
rador-0.024
 MB-0.024
 CAD-0.022
ielding-0.022
Token OM
Token ID32468
Feature activation-3.32e+00

Pos logit contributions
 moons+0.541
 horm+0.523
 nerv+0.502
 mosqu+0.484
 behavi+0.471
Neg logit contributions
abase-0.748
rador-0.607
 MB-0.602
 CAD-0.568
ielding-0.563
TokenFG
Token ID30386
Feature activation-4.37e-01

Pos logit contributions
 moons+2.400
 horm+2.303
 nerv+2.239
 mosqu+2.142
 behavi+2.074
Neg logit contributions
abase-3.067
rador-2.475
 MB-2.410
ielding-2.281
 CAD-2.262
Token<|endoftext|>
Token ID50256
Feature activation-4.37e-01

Pos logit contributions
 moons+0.359
 horm+0.349
 nerv+0.337
 mosqu+0.327
 behavi+0.319
Neg logit contributions
abase-0.361
rador-0.282
 MB-0.279
 CAD-0.260
ielding-0.258
TokenBy
Token ID3886
Feature activation+3.86e-01

Pos logit contributions
 moons+0.325
 horm+0.314
 nerv+0.301
 mosqu+0.290
 behavi+0.282
Neg logit contributions
abase-0.393
rador-0.315
 MB-0.311
 CAD-0.293
ielding-0.290
Token Andrew
Token ID6858
Feature activation+2.89e-01

Pos logit contributions
abase+0.331
rador+0.262
 MB+0.259
 CAD+0.243
ielding+0.240
Neg logit contributions
 moons-0.304
 horm-0.295
 nerv-0.284
 mosqu-0.276
 behavi-0.269
Token Benson
Token ID33940
Feature activation-2.55e-01

Pos logit contributions
abase+0.251
rador+0.199
 MB+0.198
 CAD+0.185
ielding+0.183
Neg logit contributions
 moons-0.224
 horm-0.217
 nerv-0.210
 mosqu-0.203
 behavi-0.198
Tokenoring
Token ID3255
Feature activation-5.44e-01

Pos logit contributions
abase+0.046
rador+0.032
 MB+0.032
 CAD+0.028
ielding+0.028
Neg logit contributions
 moons-0.081
 horm-0.079
 nerv-0.077
 mosqu-0.075
 behavi-0.074
Token fans
Token ID3296
Feature activation+1.25e+00

Pos logit contributions
 moons+0.396
 horm+0.384
 nerv+0.369
 mosqu+0.358
 behavi+0.348
Neg logit contributions
abase-0.497
rador-0.400
 MB-0.398
 CAD-0.374
ielding-0.371
Token wanting
Token ID10291
Feature activation-7.23e-01

Pos logit contributions
abase+1.133
 MB+0.911
rador+0.906
 CAD+0.852
ielding+0.849
Neg logit contributions
 moons-0.904
 horm-0.892
 nerv-0.839
 mosqu-0.830
 behavi-0.804
Token his
Token ID465
Feature activation+6.77e-01

Pos logit contributions
 moons+0.512
 horm+0.494
 nerv+0.475
 mosqu+0.459
 behavi+0.446
Neg logit contributions
abase-0.678
rador-0.548
 MB-0.543
 CAD-0.512
ielding-0.507
Token aut
Token ID1960
Feature activation-2.98e-01

Pos logit contributions
abase+0.655
 MB+0.536
rador+0.533
 CAD+0.506
ielding+0.499
Neg logit contributions
 moons-0.450
 horm-0.439
 nerv-0.417
 mosqu-0.407
 behavi-0.393
Tokenograph
Token ID2384
Feature activation-3.32e+00

Pos logit contributions
 moons+0.265
 horm+0.258
 nerv+0.250
 mosqu+0.243
 behavi+0.238
Neg logit contributions
abase-0.225
rador-0.171
 MB-0.169
 CAD-0.156
ielding-0.155
Token,
Token ID11
Feature activation+3.18e-01

Pos logit contributions
 moons+2.250
 horm+2.120
 nerv+2.070
 mosqu+1.956
 behavi+1.902
Neg logit contributions
abase-3.217
rador-2.627
 MB-2.551
 CAD-2.436
ielding-2.432
Token and
Token ID290
Feature activation-8.56e-02

Pos logit contributions
abase+0.308
rador+0.251
 MB+0.250
 CAD+0.236
ielding+0.234
Neg logit contributions
 moons-0.214
 horm-0.208
 nerv-0.198
 mosqu-0.192
 behavi-0.186
Token so
Token ID523
Feature activation-6.80e-01

Pos logit contributions
 moons+0.059
 horm+0.057
 nerv+0.055
 mosqu+0.053
 behavi+0.051
Neg logit contributions
abase-0.082
rador-0.067
 MB-0.066
 CAD-0.062
ielding-0.062
Token he
Token ID339
Feature activation-3.36e-01

Pos logit contributions
 moons+0.476
 horm+0.457
 nerv+0.441
 mosqu+0.422
 behavi+0.412
Neg logit contributions
abase-0.646
rador-0.524
 MB-0.516
 CAD-0.489
ielding-0.484
Token drinks
Token ID11758
Feature activation-2.46e-01

Pos logit contributions
 moons+0.247
 horm+0.239
 nerv+0.230
 mosqu+0.222
 behavi+0.216
Neg logit contributions
abase-0.306
rador-0.246
 MB-0.243
 CAD-0.229
ielding-0.227
Token a
Token ID257
Feature activation+1.17e-01

Pos logit contributions
abase+1.286
rador+1.026
 MB+1.022
 CAD+0.958
ielding+0.948
Neg logit contributions
 moons-1.101
 horm-1.070
 nerv-1.028
 mosqu-1.000
 behavi-0.973
Token massive
Token ID4858
Feature activation+3.42e-01

Pos logit contributions
abase+0.108
rador+0.086
 MB+0.085
 CAD+0.080
ielding+0.079
Neg logit contributions
 moons-0.086
 horm-0.082
 nerv-0.080
 mosqu-0.076
 behavi-0.074
Token audience
Token ID5386
Feature activation+3.20e-01

Pos logit contributions
abase+0.314
rador+0.252
 MB+0.248
 CAD+0.234
ielding+0.232
Neg logit contributions
 moons-0.250
 horm-0.241
 nerv-0.233
 mosqu-0.223
 behavi-0.217
Token --
Token ID1377
Feature activation-6.23e-01

Pos logit contributions
abase+0.313
rador+0.255
 MB+0.255
 CAD+0.241
ielding+0.238
Neg logit contributions
 moons-0.212
 horm-0.206
 nerv-0.196
 mosqu-0.191
 behavi-0.184
Token and
Token ID290
Feature activation+6.03e-01

Pos logit contributions
 moons+0.424
 horm+0.410
 nerv+0.392
 mosqu+0.379
 behavi+0.368
Neg logit contributions
abase-0.601
rador-0.489
 MB-0.485
 CAD-0.459
ielding-0.455
Token whichever
Token ID26204
Feature activation-3.32e+00

Pos logit contributions
abase+0.567
rador+0.458
 MB+0.458
 CAD+0.431
ielding+0.426
Neg logit contributions
 moons-0.420
 horm-0.409
 nerv-0.392
 mosqu-0.381
 behavi-0.370
Token prevailed
Token ID34429
Feature activation-2.71e-03

Pos logit contributions
 moons+2.703
 horm+2.592
 nerv+2.523
 mosqu+2.406
 behavi+2.350
Neg logit contributions
abase-2.797
rador-2.204
 MB-2.089
ielding-1.995
 CAD-1.994
Token would
Token ID561
Feature activation-1.01e-03

Pos logit contributions
 moons+0.002
 horm+0.002
 nerv+0.002
 mosqu+0.002
 behavi+0.002
Neg logit contributions
abase-0.003
 MB-0.002
rador-0.002
 CAD-0.002
ielding-0.002
Token be
Token ID307
Feature activation-3.06e-01

Pos logit contributions
 moons+0.001
 horm+0.001
 nerv+0.001
 mosqu+0.001
 behavi+0.001
Neg logit contributions
abase-0.001
rador-0.001
 MB-0.001
 CAD-0.001
ielding-0.001
Token required
Token ID2672
Feature activation-5.83e-01

Pos logit contributions
 moons+0.222
 horm+0.215
 nerv+0.207
 mosqu+0.199
 behavi+0.194
Neg logit contributions
abase-0.281
rador-0.227
 MB-0.224
 CAD-0.211
ielding-0.210
Token to
Token ID284
Feature activation-3.01e-01

Pos logit contributions
 moons+0.406
 horm+0.392
 nerv+0.376
 mosqu+0.362
 behavi+0.352
Neg logit contributions
abase-0.555
rador-0.450
 MB-0.444
 CAD-0.420
ielding-0.417
Token in
Token ID287
Feature activation-1.79e-01

Pos logit contributions
 moons+0.350
 horm+0.339
 nerv+0.326
 mosqu+0.315
 behavi+0.306
Neg logit contributions
abase-0.463
rador-0.374
 MB-0.372
 CAD-0.350
ielding-0.346
Token January
Token ID3269
Feature activation+8.52e-01

Pos logit contributions
 moons+0.143
 horm+0.139
 nerv+0.134
 mosqu+0.130
 behavi+0.127
Neg logit contributions
abase-0.151
rador-0.119
 MB-0.118
 CAD-0.110
ielding-0.109
Token,
Token ID11
Feature activation-2.64e-01

Pos logit contributions
abase+0.761
 MB+0.609
rador+0.608
 CAD+0.570
ielding+0.562
Neg logit contributions
 moons-0.637
 horm-0.621
 nerv-0.595
 mosqu-0.581
 behavi-0.565
Token three
Token ID1115
Feature activation-2.25e-01

Pos logit contributions
 moons+0.180
 horm+0.175
 nerv+0.167
 mosqu+0.162
 behavi+0.157
Neg logit contributions
abase-0.254
rador-0.207
 MB-0.205
 CAD-0.194
ielding-0.192
Token weeks
Token ID2745
Feature activation+1.30e+00

Pos logit contributions
 moons+0.161
 horm+0.157
 nerv+0.150
 mosqu+0.146
 behavi+0.141
Neg logit contributions
abase-0.208
rador-0.168
 MB-0.167
 CAD-0.157
ielding-0.156
Token ahead
Token ID4058
Feature activation-3.29e+00

Pos logit contributions
abase+1.256
 MB+1.024
rador+1.019
 CAD+0.970
ielding+0.955
Neg logit contributions
 moons-0.871
 horm-0.848
 nerv-0.803
 mosqu-0.788
 behavi-0.761
Token of
Token ID286
Feature activation-3.33e-01

Pos logit contributions
 moons+2.386
 horm+2.217
 nerv+2.192
 mosqu+1.953
 behavi+1.942
Neg logit contributions
abase-3.066
rador-2.469
 MB-2.343
ielding-2.267
 CAD-2.217
Token its
Token ID663
Feature activation-7.22e-02

Pos logit contributions
 moons+0.247
 horm+0.241
 nerv+0.231
 mosqu+0.224
 behavi+0.218
Neg logit contributions
abase-0.299
 MB-0.239
rador-0.239
 CAD-0.225
ielding-0.222
Token normal
Token ID3487
Feature activation-8.04e-02

Pos logit contributions
 moons+0.050
 horm+0.049
 nerv+0.047
 mosqu+0.045
 behavi+0.044
Neg logit contributions
abase-0.068
 MB-0.055
rador-0.055
 CAD-0.052
ielding-0.051
Token security
Token ID2324
Feature activation-3.67e-01

Pos logit contributions
 moons+0.050
 horm+0.049
 nerv+0.046
 mosqu+0.045
 behavi+0.043
Neg logit contributions
abase-0.082
rador-0.067
 MB-0.067
 CAD-0.064
ielding-0.063
Token updates
Token ID5992
Feature activation-1.35e-01

Pos logit contributions
 moons+0.229
 horm+0.220
 nerv+0.210
 mosqu+0.202
 behavi+0.195
Neg logit contributions
abase-0.375
rador-0.309
 MB-0.307
 CAD-0.291
ielding-0.289
Token within
Token ID1626
Feature activation-3.67e-01

Pos logit contributions
 moons+0.162
 horm+0.157
 nerv+0.150
 mosqu+0.146
 behavi+0.141
Neg logit contributions
abase-0.234
rador-0.191
 MB-0.190
 CAD-0.180
ielding-0.177
Token 2
Token ID362
Feature activation+2.58e-02

Pos logit contributions
 moons+0.315
 horm+0.306
 nerv+0.296
 mosqu+0.288
 behavi+0.281
Neg logit contributions
abase-0.289
rador-0.223
 MB-0.220
 CAD-0.204
ielding-0.202
Token weeks
Token ID2745
Feature activation+1.48e+00

Pos logit contributions
abase+0.022
rador+0.017
 MB+0.017
 CAD+0.016
ielding+0.016
Neg logit contributions
 moons-0.020
 horm-0.020
 nerv-0.019
 mosqu-0.018
 behavi-0.018
Token.
Token ID13
Feature activation-6.59e-01

Pos logit contributions
abase+1.436
 MB+1.174
rador+1.168
 CAD+1.110
ielding+1.091
Neg logit contributions
 moons-0.990
 horm-0.966
 nerv-0.916
 mosqu-0.898
 behavi-0.866
Token This
Token ID770
Feature activation-5.35e-01

Pos logit contributions
 moons+0.510
 horm+0.495
 nerv+0.477
 mosqu+0.462
 behavi+0.450
Neg logit contributions
abase-0.574
rador-0.456
 MB-0.451
 CAD-0.423
ielding-0.419
Token sub
Token ID850
Feature activation-3.26e+00

Pos logit contributions
 moons+0.401
 horm+0.388
 nerv+0.374
 mosqu+0.362
 behavi+0.352
Neg logit contributions
abase-0.479
rador-0.383
 MB-0.379
 CAD-0.356
ielding-0.353
Token sounds
Token ID5238
Feature activation-4.43e-01

Pos logit contributions
 moons+2.314
 horm+2.234
 nerv+2.145
 mosqu+2.056
 behavi+1.997
Neg logit contributions
abase-3.016
rador-2.433
 MB-2.407
 CAD-2.282
ielding-2.274
Token amazing
Token ID4998
Feature activation-1.90e-01

Pos logit contributions
 moons+0.339
 horm+0.330
 nerv+0.317
 mosqu+0.308
 behavi+0.301
Neg logit contributions
abase-0.388
rador-0.308
 MB-0.307
 CAD-0.288
ielding-0.284
Token.
Token ID13
Feature activation-8.42e-02

Pos logit contributions
 moons+0.122
 horm+0.119
 nerv+0.113
 mosqu+0.110
 behavi+0.106
Neg logit contributions
abase-0.190
rador-0.156
 MB-0.156
 CAD-0.147
ielding-0.146
Token It
Token ID632
Feature activation-9.52e-01

Pos logit contributions
 moons+0.066
 horm+0.064
 nerv+0.062
 mosqu+0.060
 behavi+0.058
Neg logit contributions
abase-0.073
rador-0.058
 MB-0.057
 CAD-0.053
ielding-0.053
Token really
Token ID1107
Feature activation-9.63e-03

Pos logit contributions
 moons+0.706
 horm+0.682
 nerv+0.657
 mosqu+0.635
 behavi+0.618
Neg logit contributions
abase-0.861
rador-0.690
 MB-0.683
 CAD-0.642
ielding-0.637
Token
Token ID447
Feature activation+4.84e-02

Pos logit contributions
abase+0.151
rador+0.119
 MB+0.119
 CAD+0.111
ielding+0.109
Neg logit contributions
 moons-0.141
 horm-0.137
 nerv-0.132
 mosqu-0.128
 behavi-0.125
Token
Token ID247
Feature activation+1.79e-01

Pos logit contributions
abase+0.043
rador+0.034
 MB+0.033
 CAD+0.032
ielding+0.031
Neg logit contributions
 moons-0.037
 horm-0.036
 nerv-0.035
 mosqu-0.033
 behavi-0.033
Tokens
Token ID82
Feature activation+1.82e-01

Pos logit contributions
abase+0.163
rador+0.131
 MB+0.130
 CAD+0.122
ielding+0.121
Neg logit contributions
 moons-0.130
 horm-0.127
 nerv-0.122
 mosqu-0.118
 behavi-0.114
Token presidency
Token ID12112
Feature activation+4.66e-01

Pos logit contributions
abase+0.190
rador+0.157
 MB+0.157
 CAD+0.149
ielding+0.147
Neg logit contributions
 moons-0.108
 horm-0.105
 nerv-0.100
 mosqu-0.097
 behavi-0.093
Token,
Token ID11
Feature activation-4.50e-02

Pos logit contributions
abase+0.453
rador+0.370
 MB+0.368
 CAD+0.348
ielding+0.344
Neg logit contributions
 moons-0.311
 horm-0.303
 nerv-0.287
 mosqu-0.279
 behavi-0.271
Token whichever
Token ID26204
Feature activation-3.25e+00

Pos logit contributions
 moons+0.032
 horm+0.031
 nerv+0.030
 mosqu+0.029
 behavi+0.028
Neg logit contributions
abase-0.042
rador-0.034
 MB-0.034
 CAD-0.032
ielding-0.031
Token comes
Token ID2058
Feature activation-1.69e-01

Pos logit contributions
 moons+2.521
 horm+2.440
 nerv+2.354
 mosqu+2.268
 behavi+2.211
Neg logit contributions
abase-2.843
rador-2.265
 MB-2.196
ielding-2.085
 CAD-2.073
Token first
Token ID717
Feature activation-5.66e-01

Pos logit contributions
 moons+0.111
 horm+0.108
 nerv+0.103
 mosqu+0.101
 behavi+0.097
Neg logit contributions
abase-0.166
 MB-0.135
rador-0.135
 CAD-0.128
ielding-0.126
Token.
Token ID13
Feature activation-2.83e-01

Pos logit contributions
 moons+0.365
 horm+0.352
 nerv+0.336
 mosqu+0.324
 behavi+0.314
Neg logit contributions
abase-0.565
rador-0.464
 MB-0.461
 CAD-0.436
ielding-0.432
Token Po
Token ID7695
Feature activation-3.56e-01

Pos logit contributions
 moons+0.213
 horm+0.207
 nerv+0.199
 mosqu+0.194
 behavi+0.189
Neg logit contributions
abase-0.252
rador-0.201
 MB-0.201
 CAD-0.188
ielding-0.185
Tokenetic
Token ID5139
Feature activation+1.28e+00

Pos logit contributions
 moons+0.282
 horm+0.273
 nerv+0.264
 mosqu+0.256
 behavi+0.250
Neg logit contributions
abase-0.304
rador-0.240
 MB-0.238
 CAD-0.222
ielding-0.220
Token the
Token ID262
Feature activation-5.67e-03

Pos logit contributions
 moons+0.227
 horm+0.219
 nerv+0.210
 mosqu+0.202
 behavi+0.196
Neg logit contributions
abase-0.345
rador-0.283
 MB-0.280
 CAD-0.265
ielding-0.263
Token question
Token ID1808
Feature activation+4.38e-01

Pos logit contributions
 moons+0.004
 horm+0.004
 nerv+0.004
 mosqu+0.004
 behavi+0.003
Neg logit contributions
abase-0.005
rador-0.004
 MB-0.004
 CAD-0.004
ielding-0.004
Token?
Token ID30
Feature activation-3.58e-02

Pos logit contributions
abase+0.384
rador+0.305
 MB+0.303
 CAD+0.283
ielding+0.281
Neg logit contributions
 moons-0.336
 horm-0.327
 nerv-0.315
 mosqu-0.306
 behavi-0.298
Token
Token ID198
Feature activation-3.99e-01

Pos logit contributions
 moons+0.027
 horm+0.026
 nerv+0.025
 mosqu+0.024
 behavi+0.024
Neg logit contributions
abase-0.032
rador-0.026
 MB-0.025
 CAD-0.024
ielding-0.024
Token
Token ID198
Feature activation-3.57e-01

Pos logit contributions
 moons+0.286
 horm+0.271
 nerv+0.263
 mosqu+0.241
 behavi+0.236
Neg logit contributions
abase-0.373
rador-0.301
 MB-0.291
ielding-0.276
 CAD-0.275
TokenIGN
Token ID16284
Feature activation-3.20e+00

Pos logit contributions
 moons+0.242
 horm+0.234
 nerv+0.224
 mosqu+0.216
 behavi+0.210
Neg logit contributions
abase-0.346
rador-0.282
 MB-0.280
 CAD-0.264
ielding-0.262
Token:
Token ID25
Feature activation-1.07e+00

Pos logit contributions
 moons+2.011
 horm+1.834
 nerv+1.811
 Sparrow+1.572
 kills+1.547
Neg logit contributions
abase-3.263
rador-2.675
 MB-2.549
ielding-2.482
 CAD-2.435
Token Just
Token ID2329
Feature activation-3.70e-01

Pos logit contributions
 moons+0.783
 horm+0.756
 nerv+0.728
 mosqu+0.701
 behavi+0.682
Neg logit contributions
abase-0.971
rador-0.781
 MB-0.770
 CAD-0.725
ielding-0.721
Token about
Token ID546
Feature activation-8.89e-01

Pos logit contributions
 moons+0.268
 horm+0.259
 nerv+0.249
 mosqu+0.241
 behavi+0.234
Neg logit contributions
abase-0.341
rador-0.274
 MB-0.272
 CAD-0.256
ielding-0.254
Token the
Token ID262
Feature activation-6.07e-01

Pos logit contributions
 moons+0.655
 horm+0.636
 nerv+0.611
 mosqu+0.593
 behavi+0.577
Neg logit contributions
abase-0.805
rador-0.644
 MB-0.641
 CAD-0.602
ielding-0.595
Token key
Token ID1994
Feature activation+5.47e-02

Pos logit contributions
 moons+0.437
 horm+0.423
 nerv+0.406
 mosqu+0.393
 behavi+0.382
Neg logit contributions
abase-0.562
rador-0.453
 MB-0.449
 CAD-0.423
ielding-0.419
Token November
Token ID3389
Feature activation+2.22e-01

Pos logit contributions
 moons+0.523
 horm+0.503
 nerv+0.486
 mosqu+0.465
 behavi+0.453
Neg logit contributions
abase-0.629
rador-0.503
 MB-0.493
ielding-0.466
 CAD-0.464
Token 2016
Token ID1584
Feature activation-1.01e+00

Pos logit contributions
abase+0.193
rador+0.153
 MB+0.152
 CAD+0.142
ielding+0.141
Neg logit contributions
 moons-0.172
 horm-0.167
 nerv-0.161
 mosqu-0.156
 behavi-0.152
Token,
Token ID11
Feature activation+1.07e-01

Pos logit contributions
 moons+0.753
 horm+0.723
 nerv+0.701
 mosqu+0.673
 behavi+0.655
Neg logit contributions
abase-0.903
rador-0.723
 MB-0.712
 CAD-0.671
ielding-0.667
Token featured
Token ID8096
Feature activation-1.70e-01

Pos logit contributions
abase+0.096
rador+0.077
 MB+0.076
 CAD+0.071
ielding+0.071
Neg logit contributions
 moons-0.081
 horm-0.078
 nerv-0.075
 mosqu-0.072
 behavi-0.070
Token the
Token ID262
Feature activation-2.32e-01

Pos logit contributions
 moons+0.129
 horm+0.124
 nerv+0.120
 mosqu+0.116
 behavi+0.113
Neg logit contributions
abase-0.152
rador-0.121
 MB-0.119
 CAD-0.112
ielding-0.112
Token rather
Token ID2138
Feature activation+2.32e+00

Pos logit contributions
 moons+0.164
 horm+0.158
 nerv+0.152
 mosqu+0.146
 behavi+0.142
Neg logit contributions
abase-0.219
rador-0.177
 MB-0.175
 CAD-0.165
ielding-0.164
Token violent
Token ID6590
Feature activation+3.31e-02

Pos logit contributions
abase+2.088
 MB+1.683
rador+1.675
 CAD+1.576
ielding+1.547
Neg logit contributions
 moons-1.693
 horm-1.654
 nerv-1.571
 mosqu-1.546
 behavi-1.504
Token mating
Token ID31993
Feature activation-1.62e+00

Pos logit contributions
abase+0.032
rador+0.026
 MB+0.025
 CAD+0.024
ielding+0.024
Neg logit contributions
 moons-0.023
 horm-0.022
 nerv-0.021
 mosqu-0.020
 behavi-0.020
Token fights
Token ID11418
Feature activation+3.29e-01

Pos logit contributions
 moons+1.192
 horm+1.146
 nerv+1.107
 mosqu+1.068
 behavi+1.041
Neg logit contributions
abase-1.488
rador-1.194
 MB-1.179
 CAD-1.113
ielding-1.105
Token of
Token ID286
Feature activation-2.15e-01

Pos logit contributions
abase+0.302
 MB+0.243
rador+0.243
 CAD+0.228
ielding+0.226
Neg logit contributions
 moons-0.236
 horm-0.231
 nerv-0.219
 mosqu-0.216
 behavi-0.209
Token snow
Token ID6729
Feature activation+3.73e-01

Pos logit contributions
 moons+0.161
 horm+0.156
 nerv+0.150
 mosqu+0.145
 behavi+0.141
Neg logit contributions
abase-0.194
rador-0.155
 MB-0.153
 CAD-0.144
ielding-0.143
Token survey
Token ID5526
Feature activation-1.78e+00

Pos logit contributions
 moons+0.458
 horm+0.442
 nerv+0.421
 mosqu+0.404
 behavi+0.392
Neg logit contributions
abase-0.748
rador-0.614
 MB-0.613
 CAD-0.581
ielding-0.575
Token
Token ID198
Feature activation-2.99e-01

Pos logit contributions
 moons+1.249
 horm+1.200
 nerv+1.159
 mosqu+1.114
 behavi+1.085
Neg logit contributions
abase-1.673
rador-1.357
 MB-1.333
 CAD-1.260
ielding-1.253
Token
Token ID198
Feature activation-2.05e-01

Pos logit contributions
 moons+0.217
 horm+0.207
 nerv+0.201
 mosqu+0.187
 behavi+0.183
Neg logit contributions
abase-0.275
rador-0.222
 MB-0.216
ielding-0.204
 CAD-0.204
Token2
Token ID17
Feature activation-5.01e-01

Pos logit contributions
 moons+0.154
 horm+0.149
 nerv+0.143
 mosqu+0.139
 behavi+0.135
Neg logit contributions
abase-0.183
rador-0.147
 MB-0.145
 CAD-0.136
ielding-0.135
Token,
Token ID11
Feature activation-2.60e-01

Pos logit contributions
 moons+0.380
 horm+0.366
 nerv+0.354
 mosqu+0.342
 behavi+0.333
Neg logit contributions
abase-0.445
rador-0.356
 MB-0.350
 CAD-0.330
ielding-0.328
Token600
Token ID8054
Feature activation+2.10e+00

Pos logit contributions
 moons+0.208
 horm+0.201
 nerv+0.195
 mosqu+0.188
 behavi+0.183
Neg logit contributions
abase-0.220
rador-0.174
 MB-0.171
 CAD-0.160
ielding-0.159
Token years
Token ID812
Feature activation+5.58e-01

Pos logit contributions
abase+1.875
 MB+1.500
rador+1.480
 CAD+1.405
ielding+1.373
Neg logit contributions
 moons-1.568
 horm-1.534
 nerv-1.466
 mosqu-1.423
 behavi-1.398
Token Age
Token ID7129
Feature activation+1.35e-01

Pos logit contributions
abase+0.462
rador+0.361
 MB+0.359
 CAD+0.335
ielding+0.330
Neg logit contributions
 moons-0.456
 horm-0.444
 nerv-0.428
 mosqu-0.416
 behavi-0.406
Token of
Token ID286
Feature activation+7.84e-03

Pos logit contributions
abase+0.122
rador+0.099
 MB+0.097
 CAD+0.091
ielding+0.090
Neg logit contributions
 moons-0.100
 horm-0.096
 nerv-0.093
 mosqu-0.089
 behavi-0.087
Token the
Token ID262
Feature activation+4.06e-01

Pos logit contributions
abase+0.007
rador+0.006
 MB+0.006
 CAD+0.005
ielding+0.005
Neg logit contributions
 moons-0.006
 horm-0.005
 nerv-0.005
 mosqu-0.005
 behavi-0.005
Token world
Token ID995
Feature activation+4.46e-01

Pos logit contributions
abase+0.329
rador+0.256
 MB+0.252
 CAD+0.235
ielding+0.233
Neg logit contributions
 moons-0.340
 horm-0.329
 nerv-0.318
 mosqu-0.309
 behavi-0.301
Token nearly
Token ID3016
Feature activation+8.02e-01

Pos logit contributions
 moons+0.613
 horm+0.589
 nerv+0.569
 mosqu+0.547
 behavi+0.534
Neg logit contributions
abase-0.747
rador-0.598
 MB-0.586
 CAD-0.553
ielding-0.553
Token 50
Token ID2026
Feature activation+6.87e-02

Pos logit contributions
abase+0.712
rador+0.568
 MB+0.565
 CAD+0.530
ielding+0.524
Neg logit contributions
 moons-0.605
 horm-0.587
 nerv-0.565
 mosqu-0.548
 behavi-0.534
Token products
Token ID3186
Feature activation-4.38e-01

Pos logit contributions
abase+0.059
rador+0.047
 MB+0.046
 CAD+0.043
ielding+0.043
Neg logit contributions
 moons-0.054
 horm-0.052
 nerv-0.050
 mosqu-0.049
 behavi-0.048
Token over
Token ID625
Feature activation-7.56e-01

Pos logit contributions
 moons+0.310
 horm+0.299
 nerv+0.288
 mosqu+0.278
 behavi+0.270
Neg logit contributions
abase-0.410
rador-0.332
 MB-0.328
 CAD-0.310
ielding-0.307
Token the
Token ID262
Feature activation+3.35e-01

Pos logit contributions
 moons+0.559
 horm+0.539
 nerv+0.519
 mosqu+0.501
 behavi+0.488
Neg logit contributions
abase-0.685
rador-0.550
 MB-0.542
 CAD-0.510
ielding-0.509
Token past
Token ID1613
Feature activation+2.15e+00

Pos logit contributions
abase+0.323
rador+0.263
 MB+0.261
 CAD+0.247
ielding+0.244
Neg logit contributions
 moons-0.226
 horm-0.220
 nerv-0.210
 mosqu-0.203
 behavi-0.197
Token few
Token ID1178
Feature activation-6.55e-01

Pos logit contributions
abase+1.856
 MB+1.480
rador+1.468
 CAD+1.388
ielding+1.357
Neg logit contributions
 moons-1.643
 horm-1.614
 nerv-1.549
 mosqu-1.516
 behavi-1.476
Token years
Token ID812
Feature activation+6.57e-01

Pos logit contributions
 moons+0.482
 horm+0.463
 nerv+0.447
 mosqu+0.431
 behavi+0.419
Neg logit contributions
abase-0.599
rador-0.482
 MB-0.474
 CAD-0.446
ielding-0.444
Token,
Token ID11
Feature activation-5.67e-02

Pos logit contributions
abase+0.606
 MB+0.487
rador+0.486
 CAD+0.458
ielding+0.452
Neg logit contributions
 moons-0.473
 horm-0.461
 nerv-0.439
 mosqu-0.429
 behavi-0.416
Token from
Token ID422
Feature activation+6.02e-01

Pos logit contributions
 moons+0.036
 horm+0.035
 nerv+0.033
 mosqu+0.032
 behavi+0.031
Neg logit contributions
abase-0.057
rador-0.047
 MB-0.046
 CAD-0.044
ielding-0.044
Token massive
Token ID4858
Feature activation-1.92e-01

Pos logit contributions
abase+0.538
rador+0.431
 MB+0.428
 CAD+0.402
ielding+0.396
Neg logit contributions
 moons-0.450
 horm-0.437
 nerv-0.420
 mosqu-0.407
 behavi-0.397
Token>
Token ID29
Feature activation+2.32e+00

Pos logit contributions
abase+2.095
rador+1.593
 MB+1.582
 CAD+1.461
ielding+1.437
Neg logit contributions
 moons-2.510
 horm-2.450
 nerv-2.371
 mosqu-2.315
 behavi-2.261
Token or
Token ID393
Feature activation-4.68e-01

Pos logit contributions
abase+1.880
rador+1.464
 MB+1.459
 CAD+1.356
ielding+1.341
Neg logit contributions
 moons-1.927
 horm-1.879
 nerv-1.812
 mosqu-1.766
 behavi-1.723
Token <
Token ID1279
Feature activation+3.54e-01

Pos logit contributions
 moons+0.400
 horm+0.388
 nerv+0.376
 mosqu+0.364
 behavi+0.356
Neg logit contributions
abase-0.371
rador-0.288
 MB-0.282
 CAD-0.263
ielding-0.261
TokenTab
Token ID33349
Feature activation+1.55e+00

Pos logit contributions
abase+0.307
rador+0.243
 MB+0.241
 CAD+0.226
ielding+0.224
Neg logit contributions
 moons-0.275
 horm-0.267
 nerv-0.258
 mosqu-0.250
 behavi-0.244
Token>)
Token ID43734
Feature activation+1.81e+00

Pos logit contributions
abase+1.044
rador+0.765
 MB+0.754
 CAD+0.688
ielding+0.680
Neg logit contributions
 moons-1.505
 horm-1.467
 nerv-1.426
 mosqu-1.389
 behavi-1.362
Token {
Token ID1391
Feature activation+2.82e+00

Pos logit contributions
abase+1.612
 MB+1.289
rador+1.289
 CAD+1.208
ielding+1.191
Neg logit contributions
 moons-1.358
 horm-1.324
 nerv-1.268
 mosqu-1.236
 behavi-1.201
Tokenvi
Token ID8903
Feature activation+7.90e-01

Pos logit contributions
abase+2.478
 MB+1.974
rador+1.964
 CAD+1.840
ielding+1.821
Neg logit contributions
 moons-2.117
 horm-2.083
 nerv-2.004
 mosqu-1.948
 behavi-1.879
Token:
Token ID25
Feature activation+5.46e-01

Pos logit contributions
abase+0.732
rador+0.590
 MB+0.586
 CAD+0.551
ielding+0.546
Neg logit contributions
 moons-0.568
 horm-0.549
 nerv-0.528
 mosqu-0.511
 behavi-0.497
Token|
Token ID91
Feature activation-6.19e-01

Pos logit contributions
abase+0.477
rador+0.379
 MB+0.377
 CAD+0.352
ielding+0.349
Neg logit contributions
 moons-0.420
 horm-0.409
 nerv-0.393
 mosqu-0.381
 behavi-0.372
Tokenvim
Token ID31124
Feature activation-6.47e-01

Pos logit contributions
 moons+0.356
 horm+0.342
 nerv+0.325
 mosqu+0.311
 behavi+0.300
Neg logit contributions
abase-0.663
rador-0.551
 MB-0.547
 CAD-0.520
ielding-0.516
Token:
Token ID25
Feature activation+2.19e-01

Pos logit contributions
 moons+0.456
 horm+0.439
 nerv+0.423
 mosqu+0.403
 behavi+0.393
Neg logit contributions
abase-0.608
rador-0.492
 MB-0.486
 CAD-0.459
ielding-0.456
Token approach
Token ID3164
Feature activation-5.13e-01

Pos logit contributions
 moons+0.087
 horm+0.084
 nerv+0.081
 mosqu+0.078
 behavi+0.076
Neg logit contributions
abase-0.115
rador-0.093
 MB-0.092
 CAD-0.086
ielding-0.086
Token to
Token ID284
Feature activation-1.85e-01

Pos logit contributions
 moons+0.365
 horm+0.351
 nerv+0.339
 mosqu+0.324
 behavi+0.315
Neg logit contributions
abase-0.479
rador-0.387
 MB-0.383
 CAD-0.361
ielding-0.358
Token designing
Token ID18492
Feature activation+2.57e-01

Pos logit contributions
 moons+0.126
 horm+0.122
 nerv+0.118
 mosqu+0.114
 behavi+0.110
Neg logit contributions
abase-0.177
rador-0.143
 MB-0.143
 CAD-0.135
ielding-0.134
Token X
Token ID1395
Feature activation+1.25e+00

Pos logit contributions
abase+0.241
 MB+0.195
rador+0.195
 CAD+0.184
ielding+0.181
Neg logit contributions
 moons-0.179
 horm-0.174
 nerv-0.167
 mosqu-0.162
 behavi-0.158
Tokene
Token ID68
Feature activation+8.27e-01

Pos logit contributions
abase+1.033
rador+0.809
 MB+0.806
 CAD+0.752
ielding+0.744
Neg logit contributions
 moons-1.011
 horm-0.987
 nerv-0.950
 mosqu-0.926
 behavi-0.913
Tokenod
Token ID375
Feature activation+3.31e+00

Pos logit contributions
abase+0.646
 MB+0.500
rador+0.495
 CAD+0.463
ielding+0.455
Neg logit contributions
 moons-0.709
 horm-0.693
 nerv-0.668
 mosqu-0.655
 behavi-0.644
Tokenr
Token ID81
Feature activation+8.42e-01

Pos logit contributions
abase+2.770
rador+2.170
 MB+2.154
ielding+2.025
 CAD+2.004
Neg logit contributions
 moons-2.676
 horm-2.620
 nerv-2.511
 mosqu-2.483
 behavi-2.463
Tokenifter
Token ID18171
Feature activation+7.68e-01

Pos logit contributions
abase+0.727
rador+0.572
 MB+0.569
 CAD+0.532
ielding+0.527
Neg logit contributions
 moons-0.660
 horm-0.641
 nerv-0.617
 mosqu-0.602
 behavi-0.586
Token was
Token ID373
Feature activation+1.96e-01

Pos logit contributions
abase+0.702
rador+0.564
 MB+0.560
 CAD+0.526
ielding+0.522
Neg logit contributions
 moons-0.561
 horm-0.543
 nerv-0.522
 mosqu-0.506
 behavi-0.493
Token a
Token ID257
Feature activation+8.72e-01

Pos logit contributions
abase+0.170
rador+0.134
 MB+0.133
 CAD+0.124
ielding+0.123
Neg logit contributions
 moons-0.154
 horm-0.149
 nerv-0.144
 mosqu-0.139
 behavi-0.135
Token case
Token ID1339
Feature activation-5.10e-01

Pos logit contributions
abase+0.784
rador+0.628
 MB+0.625
 CAD+0.588
ielding+0.581
Neg logit contributions
 moons-0.645
 horm-0.627
 nerv-0.602
 mosqu-0.588
 behavi-0.572
Token the
Token ID262
Feature activation-2.32e-01

Pos logit contributions
 moons+0.092
 horm+0.089
 nerv+0.086
 mosqu+0.082
 behavi+0.080
Neg logit contributions
abase-0.117
rador-0.094
 MB-0.092
 CAD-0.087
ielding-0.087
Token one
Token ID530
Feature activation+5.37e-01

Pos logit contributions
 moons+0.180
 horm+0.176
 nerv+0.169
 mosqu+0.167
 behavi+0.162
Neg logit contributions
abase-0.198
 MB-0.158
rador-0.157
 CAD-0.147
ielding-0.145
Token that
Token ID326
Feature activation-1.16e-01

Pos logit contributions
abase+0.502
 MB+0.404
rador+0.404
 CAD+0.379
ielding+0.375
Neg logit contributions
 moons-0.381
 horm-0.371
 nerv-0.355
 mosqu-0.349
 behavi-0.338
Token I
Token ID314
Feature activation-2.33e-01

Pos logit contributions
 moons+0.087
 horm+0.085
 nerv+0.081
 mosqu+0.080
 behavi+0.078
Neg logit contributions
abase-0.104
 MB-0.083
rador-0.083
 CAD-0.078
ielding-0.076
Token find
Token ID1064
Feature activation+2.98e-02

Pos logit contributions
 moons+0.170
 horm+0.164
 nerv+0.158
 mosqu+0.153
 behavi+0.148
Neg logit contributions
abase-0.214
rador-0.172
 MB-0.171
 CAD-0.161
ielding-0.159
Token the
Token ID262
Feature activation+1.15e-02

Pos logit contributions
abase+0.028
rador+0.022
 MB+0.022
ielding+0.021
 CAD+0.021
Neg logit contributions
 moons-0.021
 horm-0.020
 nerv-0.020
 mosqu-0.019
 behavi-0.018
Token most
Token ID749
Feature activation+3.28e-01

Pos logit contributions
abase+0.011
rador+0.009
 MB+0.008
 CAD+0.008
ielding+0.008
Neg logit contributions
 moons-0.008
 horm-0.008
 nerv-0.008
 mosqu-0.007
 behavi-0.007
Token annoying
Token ID15774
Feature activation+9.41e-01

Pos logit contributions
abase+0.328
rador+0.269
 MB+0.266
 CAD+0.252
ielding+0.250
Neg logit contributions
 moons-0.213
 horm-0.205
 nerv-0.196
 mosqu-0.188
 behavi-0.182
Token/
Token ID14
Feature activation-6.76e-01

Pos logit contributions
abase+0.705
 MB+0.540
rador+0.536
 CAD+0.499
ielding+0.488
Neg logit contributions
 moons-0.837
 horm-0.823
 nerv-0.792
 mosqu-0.789
 behavi-0.768
Tokendist
Token ID17080
Feature activation+5.20e-02

Pos logit contributions
 moons+0.632
 horm+0.612
 nerv+0.595
 mosqu+0.574
 behavi+0.565
Neg logit contributions
abase-0.481
rador-0.357
 MB-0.353
 CAD-0.324
ielding-0.319
Tokenract
Token ID974
Feature activation-1.07e+00

Pos logit contributions
abase+0.048
rador+0.038
 MB+0.038
 CAD+0.036
ielding+0.035
Neg logit contributions
 moons-0.038
 horm-0.036
 nerv-0.035
 mosqu-0.034
 seiz-0.032
Token platform
Token ID3859
Feature activation+1.58e+00

Pos logit contributions
abase+0.406
rador+0.326
 MB+0.325
 CAD+0.306
ielding+0.303
Neg logit contributions
 moons-0.318
 horm-0.308
 nerv-0.296
 mosqu-0.287
 behavi-0.279
Tokening
Token ID278
Feature activation+2.92e-01

Pos logit contributions
abase+1.251
 MB+0.973
rador+0.969
 CAD+0.897
ielding+0.891
Neg logit contributions
 moons-1.334
 horm-1.305
 nerv-1.259
 mosqu-1.231
 behavi-1.196
Token that
Token ID326
Feature activation-5.94e-01

Pos logit contributions
abase+0.275
rador+0.222
 MB+0.221
 CAD+0.208
ielding+0.206
Neg logit contributions
 moons-0.205
 horm-0.199
 nerv-0.190
 mosqu-0.184
 behavi-0.179
Token under
Token ID739
Feature activation+4.94e-01

Pos logit contributions
 moons+0.412
 horm+0.396
 nerv+0.382
 mosqu+0.367
 behavi+0.357
Neg logit contributions
abase-0.567
rador-0.459
 MB-0.452
 CAD-0.429
ielding-0.425
Tokenline
Token ID1370
Feature activation+2.59e-01

Pos logit contributions
abase+0.367
rador+0.278
 MB+0.274
 CAD+0.253
ielding+0.251
Neg logit contributions
 moons-0.447
 horm-0.435
 nerv-0.422
 mosqu-0.410
 behavi-0.401
Token the
Token ID262
Feature activation+3.73e-01

Pos logit contributions
abase+0.232
rador+0.185
 MB+0.184
 CAD+0.173
ielding+0.171
Neg logit contributions
 moons-0.194
 horm-0.188
 nerv-0.181
 mosqu-0.175
 behavi-0.171
Token original
Token ID2656
Feature activation+2.20e-01

Pos logit contributions
abase+0.348
rador+0.281
 MB+0.278
 CAD+0.262
ielding+0.260
Neg logit contributions
 moons-0.266
 horm-0.257
 nerv-0.247
 mosqu-0.239
 behavi-0.232
Token game
Token ID983
Feature activation+4.22e-01

Pos logit contributions
abase+0.209
 MB+0.170
rador+0.170
 CAD+0.160
ielding+0.158
Neg logit contributions
 moons-0.151
 horm-0.147
 nerv-0.140
 mosqu-0.136
 behavi-0.132
Token.
Token ID13
Feature activation+4.36e-02

Pos logit contributions
abase+0.400
rador+0.325
 MB+0.323
 CAD+0.305
ielding+0.302
Neg logit contributions
 moons-0.293
 horm-0.284
 nerv-0.271
 mosqu-0.263
 behavi-0.254
Token Much
Token ID13111
Feature activation+4.88e-01

Pos logit contributions
abase+0.038
rador+0.030
 MB+0.030
 CAD+0.028
ielding+0.028
Neg logit contributions
 moons-0.034
 horm-0.033
 nerv-0.031
 mosqu-0.030
 behavi-0.030
Token of
Token ID286
Feature activation+1.60e-01

Pos logit contributions
abase+0.439
rador+0.351
 MB+0.348
 CAD+0.327
ielding+0.324
Neg logit contributions
 moons-0.363
 horm-0.352
 nerv-0.339
 mosqu-0.328
 behavi-0.319
Tokenz
Token ID89
Feature activation-9.73e-03

Pos logit contributions
 moons+0.101
 horm+0.097
 nerv+0.093
 mosqu+0.090
 behavi+0.087
Neg logit contributions
abase-0.148
rador-0.121
 MB-0.120
 CAD-0.113
ielding-0.112
Token has
Token ID468
Feature activation-2.30e-01

Pos logit contributions
 moons+0.007
 horm+0.007
 nerv+0.006
 mosqu+0.006
 behavi+0.006
Neg logit contributions
abase-0.009
rador-0.007
 MB-0.007
 CAD-0.007
ielding-0.007
Token denied
Token ID6699
Feature activation+1.47e-01

Pos logit contributions
 moons+0.171
 horm+0.165
 nerv+0.159
 mosqu+0.153
 behavi+0.150
Neg logit contributions
abase-0.208
rador-0.167
 MB-0.165
 CAD-0.155
ielding-0.154
Token he
Token ID339
Feature activation-4.10e-01

Pos logit contributions
abase+0.136
rador+0.110
 MB+0.109
 CAD+0.103
ielding+0.102
Neg logit contributions
 moons-0.105
 horm-0.102
 nerv-0.098
 mosqu-0.095
 behavi-0.092
Token coerced
Token ID48474
Feature activation-5.22e-01

Pos logit contributions
 moons+0.317
 horm+0.306
 nerv+0.296
 mosqu+0.285
 behavi+0.278
Neg logit contributions
abase-0.358
rador-0.284
 MB-0.280
 CAD-0.264
ielding-0.261
Token La
Token ID4689
Feature activation+6.92e-01

Pos logit contributions
 moons+0.391
 horm+0.378
 nerv+0.364
 mosqu+0.353
 behavi+0.343
Neg logit contributions
abase-0.469
rador-0.375
 MB-0.372
 CAD-0.349
ielding-0.346
TokenFeb
Token ID15146
Feature activation-9.61e-01

Pos logit contributions
abase+0.534
rador+0.409
 MB+0.400
 CAD+0.374
ielding+0.370
Neg logit contributions
 moons-0.604
 horm-0.587
 nerv-0.566
 mosqu-0.547
 behavi-0.533
Tokenre
Token ID260
Feature activation-1.52e+00

Pos logit contributions
 moons+0.767
 horm+0.739
 nerv+0.713
 mosqu+0.672
 behavi+0.652
Neg logit contributions
abase-0.810
 MB-0.629
rador-0.627
 CAD-0.585
ielding-0.574
Token into
Token ID656
Feature activation-1.06e+00

Pos logit contributions
 moons+0.974
 horm+0.935
 nerv+0.899
 mosqu+0.859
 behavi+0.834
Neg logit contributions
abase-1.526
rador-1.254
 MB-1.240
 CAD-1.177
ielding-1.168
Token filing
Token ID12180
Feature activation+4.24e-02

Pos logit contributions
 moons+0.644
 horm+0.618
 nerv+0.591
 mosqu+0.563
 behavi+0.546
Neg logit contributions
abase-1.097
rador-0.906
 MB-0.894
 CAD-0.850
ielding-0.846
Token the
Token ID262
Feature activation-1.49e-01

Pos logit contributions
abase+0.038
rador+0.030
 MB+0.030
 CAD+0.028
ielding+0.028
Neg logit contributions
 moons-0.032
 horm-0.031
 nerv-0.029
 mosqu-0.029
 behavi-0.028
Tokens
Token ID82
Feature activation+6.71e-01

Pos logit contributions
 moons+0.183
 horm+0.177
 nerv+0.170
 mosqu+0.165
 behavi+0.160
Neg logit contributions
abase-0.237
rador-0.191
 MB-0.190
 CAD-0.178
ielding-0.177
Token a
Token ID257
Feature activation-4.16e-01

Pos logit contributions
abase+0.582
rador+0.462
 MB+0.460
 CAD+0.431
ielding+0.424
Neg logit contributions
 moons-0.518
 horm-0.505
 nerv-0.483
 mosqu-0.472
 behavi-0.460
Token moving
Token ID3867
Feature activation-6.61e-01

Pos logit contributions
 moons+0.316
 horm+0.307
 nerv+0.295
 mosqu+0.286
 behavi+0.279
Neg logit contributions
abase-0.367
rador-0.293
 MB-0.290
 CAD-0.272
ielding-0.269
Token target
Token ID2496
Feature activation-4.81e-01

Pos logit contributions
 moons+0.488
 horm+0.474
 nerv+0.454
 mosqu+0.443
 behavi+0.430
Neg logit contributions
abase-0.596
rador-0.478
 MB-0.477
 CAD-0.447
ielding-0.440
Token because
Token ID780
Feature activation-8.24e-01

Pos logit contributions
 moons+0.334
 horm+0.324
 nerv+0.309
 mosqu+0.301
 behavi+0.291
Neg logit contributions
abase-0.458
rador-0.371
 MB-0.369
 CAD-0.347
ielding-0.344
Token it
Token ID340
Feature activation+5.98e-02

Pos logit contributions
 moons+0.624
 horm+0.597
 nerv+0.582
 mosqu+0.556
 behavi+0.542
Neg logit contributions
abase-0.736
rador-0.591
 MB-0.576
 CAD-0.543
ielding-0.543
Token keeps
Token ID7622
Feature activation+2.21e-02

Pos logit contributions
abase+0.054
rador+0.043
 MB+0.043
 CAD+0.040
ielding+0.040
Neg logit contributions
 moons-0.044
 horm-0.043
 nerv-0.041
 mosqu-0.040
 behavi-0.039
Token changing
Token ID5609
Feature activation-6.02e-02

Pos logit contributions
abase+0.020
rador+0.016
 MB+0.016
 CAD+0.015
ielding+0.015
Neg logit contributions
 moons-0.016
 horm-0.016
 nerv-0.015
 mosqu-0.015
 behavi-0.014
Token.
Token ID13
Feature activation-2.39e-01

Pos logit contributions
 moons+0.041
 horm+0.040
 nerv+0.038
 mosqu+0.037
 behavi+0.036
Neg logit contributions
abase-0.057
 MB-0.047
rador-0.046
 CAD-0.044
ielding-0.043
Token
Token ID198
Feature activation-7.28e-01

Pos logit contributions
 moons+0.183
 horm+0.176
 nerv+0.171
 mosqu+0.163
 behavi+0.160
Neg logit contributions
abase-0.210
rador-0.167
 MB-0.164
ielding-0.154
 CAD-0.154
Token
Token ID198
Feature activation-6.37e-01

Pos logit contributions
 moons+0.516
 horm+0.487
 nerv+0.475
 mosqu+0.429
 behavi+0.422
Neg logit contributions
abase-0.685
rador-0.554
 MB-0.533
ielding-0.509
 CAD-0.506
Token Drive
Token ID9974
Feature activation+8.41e-01

Pos logit contributions
abase+0.171
rador+0.137
 MB+0.136
 CAD+0.128
ielding+0.127
Neg logit contributions
 moons-0.136
 horm-0.132
 nerv-0.127
 mosqu-0.123
 behavi-0.120
Token In
Token ID554
Feature activation+9.88e-02

Pos logit contributions
abase+0.639
 MB+0.484
rador+0.484
 CAD+0.448
ielding+0.443
Neg logit contributions
 moons-0.739
 horm-0.722
 nerv-0.700
 mosqu-0.679
 behavi-0.667
Token.
Token ID13
Feature activation-3.22e-01

Pos logit contributions
abase+0.091
rador+0.074
 MB+0.073
 CAD+0.069
ielding+0.068
Neg logit contributions
 moons-0.071
 horm-0.069
 nerv-0.066
 mosqu-0.064
 behavi-0.062
Token
Token ID198
Feature activation-3.67e-01

Pos logit contributions
 moons+0.245
 horm+0.236
 nerv+0.228
 mosqu+0.220
 behavi+0.214
Neg logit contributions
abase-0.285
rador-0.227
 MB-0.224
 CAD-0.210
ielding-0.209
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
 moons+0.263
 horm+0.250
 nerv+0.243
 mosqu+0.223
 behavi+0.218
Neg logit contributions
abase-0.341
rador-0.276
 MB-0.267
ielding-0.253
 CAD-0.253
TokenCall
Token ID14134
Feature activation+5.65e-01

Pos logit contributions
 moons+0.186
 horm+0.180
 nerv+0.173
 mosqu+0.167
 behavi+0.163
Neg logit contributions
abase-0.201
rador-0.159
 MB-0.157
 CAD-0.147
ielding-0.145
Token 440
Token ID33879
Feature activation-7.30e-01

Pos logit contributions
abase+0.482
rador+0.381
 MB+0.376
 CAD+0.352
ielding+0.350
Neg logit contributions
 moons-0.447
 horm-0.433
 nerv-0.418
 mosqu-0.405
 behavi-0.395
Token-
Token ID12
Feature activation+1.78e-01

Pos logit contributions
 moons+0.639
 horm+0.616
 nerv+0.599
 mosqu+0.583
 behavi+0.569
Neg logit contributions
abase-0.568
rador-0.434
 MB-0.424
 CAD-0.395
ielding-0.393
Token327
Token ID34159
Feature activation+6.63e-01

Pos logit contributions
abase+0.155
rador+0.123
 MB+0.122
 CAD+0.114
ielding+0.113
Neg logit contributions
 moons-0.138
 horm-0.134
 nerv-0.129
 mosqu-0.125
 behavi-0.122
Token-
Token ID12
Feature activation+4.75e-01

Pos logit contributions
abase+0.505
rador+0.386
 MB+0.378
 CAD+0.350
ielding+0.348
Neg logit contributions
 moons-0.587
 horm-0.569
 nerv-0.552
 mosqu-0.532
 behavi-0.521
Token9
Token ID24
Feature activation-1.78e-02

Pos logit contributions
abase+0.439
rador+0.354
 MB+0.351
 CAD+0.330
ielding+0.327
Neg logit contributions
 moons-0.343
 horm-0.331
 nerv-0.319
 mosqu-0.308
 behavi-0.300
Tokenin
Token ID259
Feature activation-2.93e-01

Pos logit contributions
 moons+0.687
 horm+0.661
 nerv+0.640
 mosqu+0.618
 behavi+0.603
Neg logit contributions
abase-0.661
rador-0.514
 MB-0.508
 CAD-0.472
ielding-0.468
Token support
Token ID1104
Feature activation-2.98e-01

Pos logit contributions
 moons+0.190
 horm+0.183
 nerv+0.175
 mosqu+0.169
 behavi+0.164
Neg logit contributions
abase-0.293
rador-0.240
 MB-0.238
 CAD-0.225
ielding-0.224
Token for
Token ID329
Feature activation-4.20e-01

Pos logit contributions
 moons+0.232
 horm+0.225
 nerv+0.217
 mosqu+0.210
 behavi+0.205
Neg logit contributions
abase-0.258
rador-0.204
 MB-0.202
 CAD-0.189
ielding-0.188
Token Snap
Token ID16026
Feature activation+2.42e-01

Pos logit contributions
 moons+0.264
 horm+0.253
 nerv+0.242
 mosqu+0.232
 behavi+0.225
Neg logit contributions
abase-0.428
rador-0.353
 MB-0.348
 CAD-0.330
ielding-0.329
Token.
Token ID13
Feature activation-2.13e-02

Pos logit contributions
abase+0.242
rador+0.198
 MB+0.197
 CAD+0.186
ielding+0.185
Neg logit contributions
 moons-0.157
 horm-0.152
 nerv-0.145
 mosqu-0.140
 behavi-0.135
Token Meanwhile
Token ID11214
Feature activation-1.72e+00

Pos logit contributions
 moons+0.016
 horm+0.016
 nerv+0.015
 mosqu+0.015
 behavi+0.014
Neg logit contributions
abase-0.019
rador-0.015
 MB-0.015
 CAD-0.014
ielding-0.014
Token Flat
Token ID21939
Feature activation+5.18e-01

Pos logit contributions
 moons+1.290
 horm+1.226
 nerv+1.191
 mosqu+1.152
 behavi+1.110
Neg logit contributions
abase-1.551
rador-1.247
 MB-1.216
ielding-1.149
 CAD-1.145
Tokenpak
Token ID41091
Feature activation-1.22e-01

Pos logit contributions
abase+0.347
rador+0.254
 MB+0.251
 CAD+0.228
ielding+0.225
Neg logit contributions
 moons-0.505
 horm-0.494
 nerv-0.479
 mosqu-0.469
 behavi-0.460
Token has
Token ID468
Feature activation+6.27e-01

Pos logit contributions
 moons+0.087
 horm+0.085
 nerv+0.081
 mosqu+0.079
 behavi+0.077
Neg logit contributions
abase-0.112
rador-0.090
 MB-0.090
 CAD-0.085
ielding-0.084
Token not
Token ID407
Feature activation-1.31e-01

Pos logit contributions
abase+0.551
rador+0.438
 MB+0.434
 CAD+0.407
ielding+0.403
Neg logit contributions
 moons-0.480
 horm-0.465
 nerv-0.449
 mosqu-0.435
 behavi-0.423
Token enjoyed
Token ID8359
Feature activation-1.06e-01

Pos logit contributions
 moons+0.096
 horm+0.093
 nerv+0.089
 mosqu+0.086
 behavi+0.084
Neg logit contributions
abase-0.119
rador-0.095
 MB-0.094
 CAD-0.089
ielding-0.088
Token stats
Token ID9756
Feature activation+2.89e-01

Pos logit contributions
 moons+0.311
 horm+0.302
 nerv+0.291
 mosqu+0.282
 behavi+0.275
Neg logit contributions
abase-0.346
rador-0.274
 MB-0.272
 CAD-0.255
ielding-0.252
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
abase+0.267
rador+0.215
 MB+0.214
 CAD+0.202
ielding+0.200
Neg logit contributions
 moons-0.207
 horm-0.202
 nerv-0.193
 mosqu-0.188
 behavi-0.182
Token including
Token ID1390
Feature activation+2.19e-02

Pos logit contributions
 moons+0.108
 horm+0.105
 nerv+0.100
 mosqu+0.097
 behavi+0.094
Neg logit contributions
abase-0.156
rador-0.127
 MB-0.126
 CAD-0.119
ielding-0.118
Token last
Token ID938
Feature activation-8.83e-01

Pos logit contributions
abase+0.018
rador+0.015
 MB+0.014
 CAD+0.013
ielding+0.013
Neg logit contributions
 moons-0.018
 horm-0.017
 nerv-0.017
 mosqu-0.016
 behavi-0.016
Token week
Token ID1285
Feature activation+2.43e-01

Pos logit contributions
 moons+0.677
 horm+0.652
 nerv+0.631
 mosqu+0.607
 behavi+0.591
Neg logit contributions
abase-0.779
rador-0.622
 MB-0.611
 CAD-0.574
ielding-0.573
Token against
Token ID1028
Feature activation-2.94e-01

Pos logit contributions
abase+0.224
rador+0.180
 MB+0.178
 CAD+0.168
ielding+0.166
Neg logit contributions
 moons-0.176
 horm-0.170
 nerv-0.163
 mosqu-0.158
 behavi-0.153
Token San
Token ID2986
Feature activation+2.39e-01

Pos logit contributions
 moons+0.226
 horm+0.219
 nerv+0.211
 mosqu+0.205
 behavi+0.200
Neg logit contributions
abase-0.258
rador-0.205
 MB-0.203
 CAD-0.190
ielding-0.189
Token Diego
Token ID9500
Feature activation+1.90e-01

Pos logit contributions
abase+0.222
rador+0.179
 MB+0.177
 CAD+0.167
ielding+0.165
Neg logit contributions
 moons-0.172
 horm-0.166
 nerv-0.160
 mosqu-0.154
 behavi-0.150
Token when
Token ID618
Feature activation+2.40e-01

Pos logit contributions
abase+0.183
rador+0.149
 MB+0.148
 CAD+0.139
ielding+0.138
Neg logit contributions
 moons-0.130
 horm-0.126
 nerv-0.120
 mosqu-0.116
 behavi-0.113
Token he
Token ID339
Feature activation+4.76e-01

Pos logit contributions
abase+0.229
rador+0.186
 MB+0.184
 CAD+0.174
ielding+0.172
Neg logit contributions
 moons-0.166
 horm-0.160
 nerv-0.154
 mosqu-0.148
 behavi-0.144
Token scored
Token ID7781
Feature activation+9.07e-01

Pos logit contributions
abase+0.462
rador+0.377
 MB+0.372
 CAD+0.352
ielding+0.349
Neg logit contributions
 moons-0.323
 horm-0.309
 nerv-0.299
 mosqu-0.285
 behavi-0.276
TokenT
Token ID51
Feature activation+3.10e-01

Pos logit contributions
abase+0.571
rador+0.462
 MB+0.456
 CAD+0.433
ielding+0.429
Neg logit contributions
 moons-0.453
 horm-0.431
 nerv-0.416
 mosqu-0.406
 behavi-0.392
Tokenunes
Token ID4015
Feature activation+1.94e+00

Pos logit contributions
abase+0.254
rador+0.199
 MB+0.196
 CAD+0.183
ielding+0.181
Neg logit contributions
 moons-0.256
 horm-0.249
 nerv-0.241
 mosqu-0.234
 behavi-0.228
Token feed
Token ID3745
Feature activation+4.06e-01

Pos logit contributions
abase+1.460
rador+1.117
 MB+1.107
 CAD+1.020
ielding+1.007
Neg logit contributions
 moons-1.723
 horm-1.688
 nerv-1.631
 mosqu-1.593
 behavi-1.553
Token)
Token ID8
Feature activation-8.32e-01

Pos logit contributions
abase+0.295
rador+0.221
 MB+0.217
 CAD+0.200
ielding+0.198
Neg logit contributions
 moons-0.374
 horm-0.364
 nerv-0.353
 mosqu-0.343
 behavi-0.336
Token
Token ID198
Feature activation+3.61e-02

Pos logit contributions
 moons+0.600
 horm+0.579
 nerv+0.556
 mosqu+0.539
 behavi+0.524
Neg logit contributions
abase-0.769
rador-0.618
 MB-0.611
 CAD-0.576
ielding-0.573
Token
Token ID198
Feature activation-3.64e-02

Pos logit contributions
abase+0.033
rador+0.027
 MB+0.026
 CAD+0.025
ielding+0.025
Neg logit contributions
 moons-0.026
 horm-0.025
 nerv-0.024
 mosqu-0.023
 behavi-0.022
TokenIf
Token ID1532
Feature activation+2.61e-01

Pos logit contributions
 moons+0.025
 horm+0.024
 nerv+0.023
 mosqu+0.022
 behavi+0.021
Neg logit contributions
abase-0.035
rador-0.029
 MB-0.028
 CAD-0.027
ielding-0.027
Token you
Token ID345
Feature activation+2.49e-01

Pos logit contributions
abase+0.217
rador+0.170
 MB+0.168
 CAD+0.157
ielding+0.155
Neg logit contributions
 moons-0.212
 horm-0.206
 nerv-0.199
 mosqu-0.193
 behavi-0.188
Token have
Token ID423
Feature activation-4.40e-01

Pos logit contributions
abase+0.229
rador+0.184
 MB+0.183
 CAD+0.173
ielding+0.170
Neg logit contributions
 moons-0.180
 horm-0.175
 nerv-0.168
 mosqu-0.163
 behavi-0.159
Token a
Token ID257
Feature activation-1.83e-01

Pos logit contributions
 moons+0.303
 horm+0.291
 nerv+0.280
 mosqu+0.269
 behavi+0.261
Neg logit contributions
abase-0.422
rador-0.344
 MB-0.338
 CAD-0.320
ielding-0.319
Token moment
Token ID2589
Feature activation-9.57e-02

Pos logit contributions
 moons+0.129
 horm+0.124
 nerv+0.120
 mosqu+0.115
 behavi+0.112
Neg logit contributions
abase-0.172
rador-0.139
 MB-0.138
 CAD-0.130
ielding-0.129
Token exponentially
Token ID35529
Feature activation+1.45e-02

Pos logit contributions
 moons+0.153
 horm+0.148
 nerv+0.142
 mosqu+0.137
 behavi+0.133
Neg logit contributions
abase-0.207
rador-0.167
 MB-0.166
 CAD-0.156
ielding-0.155
Token,
Token ID11
Feature activation+2.72e-01

Pos logit contributions
abase+0.014
 MB+0.011
rador+0.011
 CAD+0.011
ielding+0.010
Neg logit contributions
 moons-0.010
 horm-0.010
 nerv-0.009
 mosqu-0.009
 behavi-0.009
Token with
Token ID351
Feature activation-2.19e-01

Pos logit contributions
abase+0.269
rador+0.220
 MB+0.220
 CAD+0.208
ielding+0.206
Neg logit contributions
 moons-0.176
 horm-0.170
 nerv-0.163
 mosqu-0.158
 behavi-0.153
Token implications
Token ID10939
Feature activation-1.07e-01

Pos logit contributions
 moons+0.164
 horm+0.159
 nerv+0.153
 mosqu+0.148
 behavi+0.144
Neg logit contributions
abase-0.197
rador-0.158
 MB-0.156
 CAD-0.146
ielding-0.145
Token for
Token ID329
Feature activation-8.52e-01

Pos logit contributions
 moons+0.084
 horm+0.082
 nerv+0.079
 mosqu+0.077
 behavi+0.075
Neg logit contributions
abase-0.092
rador-0.073
 MB-0.073
 CAD-0.068
ielding-0.067
Token our
Token ID674
Feature activation-6.14e-01

Pos logit contributions
 moons+0.621
 horm+0.600
 nerv+0.576
 mosqu+0.556
 behavi+0.542
Neg logit contributions
abase-0.783
rador-0.630
 MB-0.622
 CAD-0.585
ielding-0.582
Token common
Token ID2219
Feature activation+7.02e-01

Pos logit contributions
 moons+0.421
 horm+0.406
 nerv+0.389
 mosqu+0.374
 behavi+0.364
Neg logit contributions
abase-0.591
rador-0.481
 MB-0.475
 CAD-0.449
ielding-0.446
Token security
Token ID2324
Feature activation+7.68e-01

Pos logit contributions
abase+0.703
rador+0.576
 MB+0.574
 CAD+0.543
ielding+0.539
Neg logit contributions
 moons-0.450
 horm-0.435
 nerv-0.416
 mosqu-0.402
 behavi-0.387
Token.
Token ID13
Feature activation+3.62e-03

Pos logit contributions
abase+0.737
rador+0.599
 MB+0.595
 CAD+0.563
ielding+0.558
Neg logit contributions
 moons-0.524
 horm-0.507
 nerv-0.485
 mosqu-0.470
 behavi-0.455
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
abase+0.003
rador+0.003
 MB+0.003
 CAD+0.002
ielding+0.002
Neg logit contributions
 moons-0.003
 horm-0.003
 nerv-0.003
 mosqu-0.003
 behavi-0.002
Token
Token ID198
Feature activation+1.89e-01

Pos logit contributions
abase+0.139
rador+0.112
 MB+0.109
 CAD+0.103
ielding+0.103
Neg logit contributions
 moons-0.113
 horm-0.108
 nerv-0.105
 mosqu-0.099
 behavi-0.097
Token.
Token ID13
Feature activation-1.62e-01

Pos logit contributions
 moons+0.221
 horm+0.214
 nerv+0.205
 mosqu+0.198
 behavi+0.192
Neg logit contributions
abase-0.314
rador-0.256
 MB-0.254
 CAD-0.240
ielding-0.237
Token On
Token ID1550
Feature activation+1.42e-01

Pos logit contributions
 moons+0.122
 horm+0.118
 nerv+0.114
 mosqu+0.110
 behavi+0.107
Neg logit contributions
abase-0.144
rador-0.115
 MB-0.114
 CAD-0.107
ielding-0.106
Token 28
Token ID2579
Feature activation-5.02e-01

Pos logit contributions
abase+0.115
rador+0.089
 MB+0.087
 CAD+0.081
ielding+0.081
Neg logit contributions
 moons-0.120
 horm-0.116
 nerv-0.112
 mosqu-0.108
 behavi-0.106
Token April
Token ID3035
Feature activation+2.82e-01

Pos logit contributions
 moons+0.375
 horm+0.361
 nerv+0.349
 mosqu+0.336
 behavi+0.327
Neg logit contributions
abase-0.451
rador-0.361
 MB-0.356
 CAD-0.335
ielding-0.333
Token,
Token ID11
Feature activation-4.39e-02

Pos logit contributions
abase+0.246
rador+0.195
 MB+0.193
 CAD+0.181
ielding+0.180
Neg logit contributions
 moons-0.218
 horm-0.211
 nerv-0.204
 mosqu-0.197
 behavi-0.192
Token European
Token ID3427
Feature activation-3.66e-01

Pos logit contributions
 moons+0.032
 horm+0.030
 nerv+0.029
 mosqu+0.028
 behavi+0.027
Neg logit contributions
abase-0.041
rador-0.033
 MB-0.032
 CAD-0.031
ielding-0.031
Token Court
Token ID3078
Feature activation-1.16e+00

Pos logit contributions
 moons+0.258
 horm+0.248
 nerv+0.238
 mosqu+0.229
 behavi+0.223
Neg logit contributions
abase-0.346
rador-0.279
 MB-0.275
 CAD-0.260
ielding-0.258
Token of
Token ID286
Feature activation+3.79e-01

Pos logit contributions
 moons+0.875
 horm+0.847
 nerv+0.816
 mosqu+0.787
 behavi+0.765
Neg logit contributions
abase-1.036
rador-0.820
 MB-0.808
 CAD-0.761
ielding-0.761
Token Human
Token ID5524
Feature activation+5.12e-01

Pos logit contributions
abase+0.335
rador+0.266
 MB+0.261
 CAD+0.247
ielding+0.245
Neg logit contributions
 moons-0.289
 horm-0.280
 nerv-0.270
 mosqu-0.260
 behavi-0.254
Token Rights
Token ID6923
Feature activation-4.45e-02

Pos logit contributions
abase+0.490
rador+0.398
 MB+0.395
 CAD+0.372
ielding+0.369
Neg logit contributions
 moons-0.352
 horm-0.340
 nerv-0.327
 mosqu-0.315
 behavi-0.306
Token demanded
Token ID12284
Feature activation+3.61e-01

Pos logit contributions
 moons+0.031
 horm+0.030
 nerv+0.029
 mosqu+0.028
 behavi+0.027
Neg logit contributions
abase-0.042
rador-0.034
 MB-0.034
 CAD-0.032
ielding-0.032
Token
Token ID198
Feature activation-3.76e-01

Pos logit contributions
 moons+0.006
 horm+0.005
 nerv+0.005
 mosqu+0.005
 behavi+0.005
Neg logit contributions
abase-0.007
rador-0.005
 MB-0.005
 CAD-0.005
ielding-0.005
Token
Token ID198
Feature activation-2.40e-01

Pos logit contributions
 moons+0.272
 horm+0.259
 nerv+0.252
 mosqu+0.233
 behavi+0.228
Neg logit contributions
abase-0.349
rador-0.281
 MB-0.273
ielding-0.259
 CAD-0.258
TokenHow
Token ID2437
Feature activation-5.14e-01

Pos logit contributions
 moons+0.175
 horm+0.169
 nerv+0.163
 mosqu+0.156
 behavi+0.152
Neg logit contributions
abase-0.220
rador-0.177
 MB-0.174
 CAD-0.164
ielding-0.163
Token in
Token ID287
Feature activation+8.73e-01

Pos logit contributions
 moons+0.376
 horm+0.363
 nerv+0.350
 mosqu+0.338
 behavi+0.329
Neg logit contributions
abase-0.469
rador-0.377
 MB-0.373
 CAD-0.351
ielding-0.349
Token the
Token ID262
Feature activation+3.54e-02

Pos logit contributions
abase+0.784
rador+0.628
 MB+0.625
 CAD+0.586
ielding+0.580
Neg logit contributions
 moons-0.651
 horm-0.629
 nerv-0.607
 mosqu-0.589
 behavi-0.572
Token hell
Token ID5968
Feature activation-2.22e+00

Pos logit contributions
abase+0.033
rador+0.027
 MB+0.026
 CAD+0.025
ielding+0.025
Neg logit contributions
 moons-0.025
 horm-0.024
 nerv-0.023
 mosqu-0.023
 behavi-0.022
Token could
Token ID714
Feature activation-9.19e-01

Pos logit contributions
 moons+1.492
 horm+1.425
 nerv+1.379
 mosqu+1.307
 behavi+1.282
Neg logit contributions
abase-2.165
rador-1.767
 MB-1.731
ielding-1.647
 CAD-1.640
Token a
Token ID257
Feature activation+1.91e-02

Pos logit contributions
 moons+0.713
 horm+0.690
 nerv+0.665
 mosqu+0.638
 behavi+0.624
Neg logit contributions
abase-0.803
rador-0.636
 MB-0.622
ielding-0.586
 CAD-0.584
Token man
Token ID582
Feature activation+8.84e-01

Pos logit contributions
abase+0.017
rador+0.014
 MB+0.014
 CAD+0.013
ielding+0.013
Neg logit contributions
 moons-0.014
 horm-0.014
 nerv-0.013
 mosqu-0.013
 behavi-0.012
Token enjoy
Token ID2883
Feature activation-8.58e-01

Pos logit contributions
abase+0.840
rador+0.679
 MB+0.675
 CAD+0.637
ielding+0.630
Neg logit contributions
 moons-0.614
 horm-0.596
 nerv-0.569
 mosqu-0.556
 behavi-0.540
Token being
Token ID852
Feature activation-5.43e-01

Pos logit contributions
 moons+0.627
 horm+0.604
 nerv+0.582
 mosqu+0.560
 behavi+0.546
Neg logit contributions
abase-0.789
rador-0.633
 MB-0.624
 CAD-0.588
ielding-0.587
Token 07
Token ID8753
Feature activation-2.00e-01

Pos logit contributions
 moons+0.647
 horm+0.627
 nerv+0.610
 mosqu+0.587
 behavi+0.574
Neg logit contributions
abase-0.502
rador-0.377
 MB-0.362
ielding-0.337
 CAD-0.334
Token:
Token ID25
Feature activation-6.31e-01

Pos logit contributions
 moons+0.140
 horm+0.134
 nerv+0.129
 mosqu+0.122
 behavi+0.118
Neg logit contributions
abase-0.190
rador-0.154
 MB-0.151
 CAD-0.143
ielding-0.142
Token44
Token ID2598
Feature activation-3.27e-01

Pos logit contributions
 moons+0.391
 horm+0.375
 nerv+0.358
 mosqu+0.340
 behavi+0.329
Neg logit contributions
abase-0.647
rador-0.534
 MB-0.527
 CAD-0.501
ielding-0.498
Token Se
Token ID1001
Feature activation-1.67e+00

Pos logit contributions
 moons+0.221
 horm+0.214
 nerv+0.205
 mosqu+0.198
 behavi+0.193
Neg logit contributions
abase-0.315
rador-0.257
 MB-0.256
 CAD-0.241
ielding-0.238
Tokeneker
Token ID28233
Feature activation-9.27e-01

Pos logit contributions
 moons+1.369
 horm+1.339
 nerv+1.290
 mosqu+1.246
 behavi+1.210
Neg logit contributions
abase-1.349
rador-1.061
 MB-1.047
 CAD-0.979
ielding-0.962
Token wrote
Token ID2630
Feature activation-2.87e+00

Pos logit contributions
 moons+0.711
 horm+0.690
 nerv+0.664
 mosqu+0.644
 behavi+0.628
Neg logit contributions
abase-0.813
rador-0.647
 MB-0.641
 CAD-0.601
ielding-0.595
Token:
Token ID25
Feature activation-1.52e+00

Pos logit contributions
 moons+1.816
 horm+1.669
 nerv+1.658
 Sparrow+1.404
 Quake+1.400
Neg logit contributions
abase-2.900
rador-2.385
 MB-2.277
ielding-2.210
 CAD-2.173
Token
Token ID198
Feature activation-1.72e+00

Pos logit contributions
 moons+1.102
 horm+1.053
 nerv+1.021
 mosqu+0.950
 behavi+0.931
Neg logit contributions
abase-1.398
rador-1.125
 MB-1.098
 CAD-1.036
ielding-1.035
Token
Token ID198
Feature activation-1.68e+00

Pos logit contributions
 moons+1.205
 horm+1.134
 nerv+1.107
 mosqu+0.985
 behavi+0.976
Neg logit contributions
abase-1.629
rador-1.322
 MB-1.268
ielding-1.210
 CAD-1.201
TokenCl
Token ID2601
Feature activation-9.04e-01

Pos logit contributions
 moons+1.131
 horm+1.090
 nerv+1.044
 mosqu+0.998
 behavi+0.969
Neg logit contributions
abase-1.623
rador-1.326
 MB-1.313
 CAD-1.244
ielding-1.231
Tokenarity
Token ID6806
Feature activation+2.76e-01

Pos logit contributions
 moons+0.780
 horm+0.757
 nerv+0.734
 mosqu+0.709
 behavi+0.691
Neg logit contributions
abase-0.704
rador-0.542
 MB-0.538
 CAD-0.499
ielding-0.489
Token you
Token ID345
Feature activation-1.66e-01

Pos logit contributions
 moons+0.082
 horm+0.080
 nerv+0.077
 mosqu+0.074
 behavi+0.072
Neg logit contributions
abase-0.094
rador-0.075
 MB-0.074
 CAD-0.069
ielding-0.069
Token
Token ID447
Feature activation-4.00e-01

Pos logit contributions
 moons+0.123
 horm+0.119
 nerv+0.114
 mosqu+0.111
 behavi+0.108
Neg logit contributions
abase-0.150
rador-0.120
 MB-0.119
 CAD-0.112
ielding-0.111
Token
Token ID247
Feature activation-4.24e-01

Pos logit contributions
 moons+0.297
 horm+0.288
 nerv+0.277
 mosqu+0.266
 behavi+0.258
Neg logit contributions
abase-0.361
rador-0.289
 MB-0.284
 CAD-0.269
ielding-0.266
Tokenre
Token ID260
Feature activation-1.87e-01

Pos logit contributions
 moons+0.360
 horm+0.350
 nerv+0.338
 mosqu+0.331
 behavi+0.324
Neg logit contributions
abase-0.338
rador-0.262
 MB-0.260
 CAD-0.241
ielding-0.239
Token not
Token ID407
Feature activation+2.65e-01

Pos logit contributions
 moons+0.140
 horm+0.135
 nerv+0.131
 mosqu+0.125
 behavi+0.122
Neg logit contributions
abase-0.168
rador-0.135
 MB-0.133
 CAD-0.125
ielding-0.124
Token just
Token ID655
Feature activation-2.47e+00

Pos logit contributions
abase+0.236
rador+0.188
 MB+0.187
 CAD+0.176
ielding+0.174
Neg logit contributions
 moons-0.199
 horm-0.193
 nerv-0.186
 mosqu-0.180
 behavi-0.176
Token waiting
Token ID4953
Feature activation+3.32e-01

Pos logit contributions
 moons+1.813
 horm+1.733
 nerv+1.702
 mosqu+1.606
 behavi+1.576
Neg logit contributions
abase-2.253
rador-1.819
 MB-1.771
 CAD-1.676
ielding-1.675
Token for
Token ID329
Feature activation+1.27e+00

Pos logit contributions
abase+0.286
rador+0.226
 MB+0.224
 CAD+0.210
ielding+0.208
Neg logit contributions
 moons-0.260
 horm-0.253
 nerv-0.244
 mosqu-0.237
 behavi-0.231
Token a
Token ID257
Feature activation+1.06e-01

Pos logit contributions
abase+1.112
 MB+0.890
rador+0.882
 CAD+0.827
ielding+0.810
Neg logit contributions
 moons-0.968
 horm-0.948
 nerv-0.904
 mosqu-0.888
 behavi-0.866
Token surprise
Token ID5975
Feature activation+7.12e-01

Pos logit contributions
abase+0.099
rador+0.080
 MB+0.079
 CAD+0.074
ielding+0.074
Neg logit contributions
 moons-0.075
 horm-0.073
 nerv-0.070
 mosqu-0.067
 behavi-0.065
Token
Token ID851
Feature activation+6.35e-02

Pos logit contributions
abase+0.662
rador+0.533
 MB+0.533
 CAD+0.501
ielding+0.494
Neg logit contributions
 moons-0.507
 horm-0.493
 nerv-0.470
 mosqu-0.458
 behavi-0.445
Token [
Token ID685
Feature activation-5.39e-02

Pos logit contributions
 moons+0.124
 horm+0.121
 nerv+0.117
 mosqu+0.114
 behavi+0.111
Neg logit contributions
abase-0.113
rador-0.087
 MB-0.087
 CAD-0.080
ielding-0.079
Token10
Token ID940
Feature activation-9.32e-01

Pos logit contributions
 moons+0.038
 horm+0.037
 nerv+0.035
 mosqu+0.034
 behavi+0.033
Neg logit contributions
abase-0.051
rador-0.041
 MB-0.041
 CAD-0.038
ielding-0.038
Token:
Token ID25
Feature activation-1.45e+00

Pos logit contributions
 moons+0.624
 horm+0.585
 nerv+0.570
 mosqu+0.507
 behavi+0.495
Neg logit contributions
abase-0.915
rador-0.749
 MB-0.721
ielding-0.691
 CAD-0.686
Token47
Token ID2857
Feature activation-1.95e+00

Pos logit contributions
 moons+1.025
 horm+0.986
 nerv+0.951
 mosqu+0.921
 behavi+0.888
Neg logit contributions
abase-1.362
rador-1.102
 MB-1.073
 CAD-1.023
ielding-1.018
Token]
Token ID60
Feature activation-1.63e+00

Pos logit contributions
 moons+1.677
 horm+1.572
 nerv+1.557
 Sparrow+1.397
 Quake+1.394
Neg logit contributions
abase-1.547
rador-1.196
 MB-1.111
ielding-1.066
olesc-1.038
Token <
Token ID1279
Feature activation-2.19e+00

Pos logit contributions
 moons+1.502
 horm+1.463
 nerv+1.419
 mosqu+1.384
 behavi+1.352
Neg logit contributions
abase-1.177
rador-0.885
 MB-0.867
 CAD-0.799
ielding-0.794
Tokenabal
Token ID44349
Feature activation-3.23e-01

Pos logit contributions
 moons+1.704
 horm+1.654
 nerv+1.590
 mosqu+1.535
 behavi+1.485
Neg logit contributions
abase-1.865
rador-1.482
 MB-1.474
 CAD-1.387
ielding-1.360
Tokenicious
Token ID6243
Feature activation+4.88e-01

Pos logit contributions
 moons+0.254
 horm+0.247
 nerv+0.238
 mosqu+0.230
 behavi+0.225
Neg logit contributions
abase-0.277
rador-0.219
 MB-0.217
 CAD-0.203
ielding-0.201
Tokens
Token ID82
Feature activation-7.83e-01

Pos logit contributions
abase+0.409
rador+0.322
 MB+0.319
 CAD+0.297
ielding+0.295
Neg logit contributions
 moons-0.393
 horm-0.382
 nerv-0.369
 mosqu-0.358
 behavi-0.349
Token>
Token ID29
Feature activation-1.22e+00

Pos logit contributions
 moons+0.605
 horm+0.586
 nerv+0.565
 mosqu+0.546
 behavi+0.530
Neg logit contributions
abase-0.682
rador-0.541
 MB-0.537
 CAD-0.504
ielding-0.498
Token lol
Token ID19462
Feature activation-1.23e+00

Pos logit contributions
 moons+0.874
 horm+0.845
 nerv+0.812
 mosqu+0.785
 behavi+0.764
Neg logit contributions
abase-1.139
rador-0.919
 MB-0.912
 CAD-0.859
ielding-0.851
Token the
Token ID262
Feature activation+2.02e-01

Pos logit contributions
abase+0.118
rador+0.095
 MB+0.094
 CAD+0.089
ielding+0.088
Neg logit contributions
 moons-0.094
 horm-0.091
 nerv-0.088
 mosqu-0.085
 behavi-0.083
Token trial
Token ID4473
Feature activation-5.11e-01

Pos logit contributions
abase+0.195
rador+0.159
 MB+0.158
 CAD+0.149
ielding+0.148
Neg logit contributions
 moons-0.137
 horm-0.132
 nerv-0.126
 mosqu-0.122
 behavi-0.118
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
 moons+0.371
 horm+0.359
 nerv+0.344
 mosqu+0.334
 behavi+0.325
Neg logit contributions
abase-0.470
rador-0.379
 MB-0.377
 CAD-0.355
ielding-0.351
Token As
Token ID1081
Feature activation+4.71e-01

Pos logit contributions
 moons+0.154
 horm+0.149
 nerv+0.144
 mosqu+0.139
 behavi+0.136
Neg logit contributions
abase-0.181
rador-0.144
 MB-0.142
 CAD-0.133
ielding-0.133
Token you
Token ID345
Feature activation-6.76e-01

Pos logit contributions
abase+0.416
rador+0.332
 MB+0.326
 CAD+0.306
ielding+0.305
Neg logit contributions
 moons-0.360
 horm-0.348
 nerv-0.337
 mosqu-0.324
 behavi-0.316
Token may
Token ID743
Feature activation-2.15e+00

Pos logit contributions
 moons+0.507
 horm+0.490
 nerv+0.472
 mosqu+0.455
 behavi+0.443
Neg logit contributions
abase-0.606
rador-0.484
 MB-0.479
 CAD-0.450
ielding-0.447
Token recall
Token ID10014
Feature activation-8.02e-01

Pos logit contributions
 moons+1.768
 horm+1.693
 nerv+1.649
 mosqu+1.559
 behavi+1.523
Neg logit contributions
abase-1.765
rador-1.389
 MB-1.364
ielding-1.258
 CAD-1.255
Token,
Token ID11
Feature activation-2.63e-01

Pos logit contributions
 moons+0.610
 horm+0.589
 nerv+0.569
 mosqu+0.548
 behavi+0.536
Neg logit contributions
abase-0.713
rador-0.568
 MB-0.554
ielding-0.525
 CAD-0.522
Token on
Token ID319
Feature activation+3.90e-01

Pos logit contributions
 moons+0.195
 horm+0.189
 nerv+0.182
 mosqu+0.176
 behavi+0.171
Neg logit contributions
abase-0.238
rador-0.191
 MB-0.188
 CAD-0.177
ielding-0.176
Token Monday
Token ID3321
Feature activation-5.48e-02

Pos logit contributions
abase+0.332
rador+0.262
 MB+0.258
 CAD+0.242
ielding+0.240
Neg logit contributions
 moons-0.310
 horm-0.300
 nerv-0.290
 mosqu-0.281
 behavi-0.274
Token it
Token ID340
Feature activation+3.28e-01

Pos logit contributions
 moons+0.042
 horm+0.040
 nerv+0.039
 mosqu+0.038
 behavi+0.037
Neg logit contributions
abase-0.049
rador-0.039
 MB-0.038
ielding-0.036
 CAD-0.036