TOP ACTIVATIONS
MAX = 1.096

sway the system through ult im at ums , are based
, height = 600 ) gray = c v 2 .
He was given an ult im atum and a day to
? is Sh ag gy s most
News Alert s Keep an eye out for an email to
Update , 3 : 01 p . m .
20 cents per kil ow att - hour , electricity from
website . M ISS ING 2 - Y EAR
other . Glow - in - the - dark football s
Does One - on - One Out reach Make You
draw ing . String Al ignment ] :: Near } }
be 66 IEEE 802 . 11 b gn E SS ID
original image Download : Figure 1 . Maze and task description
on Twitter . <|endoftext|> Q : Sebastian , last year you
. Update , 3 : 01 p . m
G AL AX Y VOL . 2 . However , even
U PDATED 2 : 35 p . m .:
Volume () ; return f Mass ; } Ass
performance , would give them enough space to sign at least
being warned to keep an eye out for two scams working

MIN ACTIVATIONS
MIN = -1.147

- and - soc iety , community - organ isations ,
marine - biology , conservation , environment , oceans - and
- and - f inance , aust ral ia
: beef - c attle , rural , business - econom
biology , conservation , environment , oceans - and - ree
Topics : marine - biology , conservation , environment , oceans
- and - ree fs , water - poll ution ,
, community - organ isations , electricity - energy - and
- c attle , rural , business - econom ics -
, water - poll ution , environmental - impact , environmental
S + \ s + "( \ S +) "] '
impact , environmental - management , environmental - technology , q
ution , environmental - impact , environmental - management , environmental
ale wil kins i ), after Australian explorer , natural ist
366 . Topics : community - and - soc
- and - ut ilities , family - and - children
management , environmental - technology , q ld First
them ". Topics : marine - biology , conservation
with all this Al J our g ensen and Ge za
groups @ peace cor ps connect . org . The deadline

INTERVAL 0.536 - 1.096
CONTAINS 0.301%

safety . It 's right up there with be avers and
was available for 802 . 11 g devices . However ,
Division National Forest swap the concrete for trees , and
from antagon istic states , but from our own foreign service
support their already - te et ering legislative agenda if there

INTERVAL -0.025 - 0.536
CONTAINS 55.099%

category which could capture the economic middle in India . While
to sort its financial position . The company has warned it
S EC UN DA S EC UN D
Charlie and the Chocolate Factory , from the poverty - str
that you still get awesome stuff and cool experiences .

INTERVAL -0.586 - -0.025
CONTAINS 44.445%

в а т ь .
. Gordon Reid ( 108 ) ( 20 )
near the portal to R al n oth only
low - lying areas started flooding over the last few weeks
, has not addressed the rumors , but brother Eric backed

INTERVAL -1.147 - -0.586
CONTAINS 0.155%

were play - testing . One was a Thought st eal
cell , as shown in Figure 3 . Figure
a crater on planet Venus in her honor .[ 55 ]
of which way they were going . As part of the
do two main things . One is to create a shared
Token sway
Token ID20009
Feature activation+2.22e-01

Pos logit contributions
arcity+0.058
 Cage+0.048
Hardware+0.048
 Sisters+0.047
τ+0.046
Neg logit contributions
anka-0.044
plom-0.043
 glitter-0.043
agen-0.042
 interpol-0.041
Token the
Token ID262
Feature activation+2.35e-01

Pos logit contributions
arcity+1.164
Hardware+0.955
 Cage+0.955
 Sisters+0.928
τ+0.912
Neg logit contributions
anka-0.942
plom-0.914
 glitter-0.899
agen-0.893
 interpol-0.857
Token system
Token ID1080
Feature activation+1.75e-01

Pos logit contributions
arcity+1.326
 Cage+1.104
Hardware+1.102
 Sisters+1.073
τ+1.063
Neg logit contributions
anka-0.902
plom-0.873
 glitter-0.853
agen-0.851
 interpol-0.809
Token through
Token ID832
Feature activation+2.00e-01

Pos logit contributions
arcity+0.933
 Cage+0.771
Hardware+0.770
 Sisters+0.749
τ+0.738
Neg logit contributions
anka-0.726
plom-0.705
agen-0.689
 glitter-0.687
 interpol-0.659
Token ult
Token ID3789
Feature activation+7.97e-02

Pos logit contributions
arcity+1.074
 Cage+0.892
Hardware+0.888
 Sisters+0.864
τ+0.852
Neg logit contributions
anka-0.822
plom-0.800
 glitter-0.782
agen-0.778
 interpol-0.749
Tokenim
Token ID320
Feature activation+1.00e+00

Pos logit contributions
arcity+0.417
 Cage+0.352
Hardware+0.349
 Sisters+0.342
τ+0.333
Neg logit contributions
anka-0.333
plom-0.328
agen-0.320
 glitter-0.311
 interpol-0.297
Tokenat
Token ID265
Feature activation+3.82e-01

Pos logit contributions
arcity+4.910
 Cage+3.974
Hardware+3.924
 Sisters+3.823
τ+3.798
Neg logit contributions
anka-4.453
plom-4.289
 glitter-4.255
agen-4.174
 interpol-4.096
Tokenums
Token ID5700
Feature activation+4.14e-01

Pos logit contributions
arcity+1.580
 Cage+1.243
Hardware+1.224
 Sisters+1.191
τ+1.160
Neg logit contributions
anka-2.025
plom-1.977
agen-1.940
 glitter-1.930
 interpol-1.873
Token,
Token ID11
Feature activation+2.89e-01

Pos logit contributions
arcity+2.132
 Cage+1.765
Hardware+1.746
 Sisters+1.709
τ+1.675
Neg logit contributions
anka-1.784
plom-1.732
agen-1.690
 glitter-1.682
 interpol-1.620
Token are
Token ID389
Feature activation+4.18e-01

Pos logit contributions
arcity+1.562
 Cage+1.298
Hardware+1.293
 Sisters+1.258
τ+1.237
Neg logit contributions
anka-1.176
plom-1.143
 glitter-1.123
agen-1.109
 interpol-1.076
Token based
Token ID1912
Feature activation+4.00e-01

Pos logit contributions
arcity+2.266
 Cage+1.882
Hardware+1.875
 Sisters+1.828
τ+1.797
Neg logit contributions
anka-1.688
plom-1.646
 glitter-1.612
agen-1.605
 interpol-1.550
Token,
Token ID837
Feature activation+8.71e-02

Pos logit contributions
arcity+2.869
 Cage+2.455
Hardware+2.429
 Sisters+2.383
τ+2.343
Neg logit contributions
anka-1.828
plom-1.774
agen-1.703
 glitter-1.701
 interpol-1.620
Token height
Token ID6001
Feature activation+5.32e-01

Pos logit contributions
arcity+0.415
 Cage+0.336
Hardware+0.333
 Sisters+0.323
τ+0.318
Neg logit contributions
anka-0.410
plom-0.397
 glitter-0.392
agen-0.390
 interpol-0.379
Token =
Token ID796
Feature activation+1.91e-01

Pos logit contributions
arcity+2.121
 Cage+1.675
Hardware+1.655
 Sisters+1.595
τ+1.559
Neg logit contributions
anka-2.880
plom-2.825
 glitter-2.753
agen-2.751
 interpol-2.665
Token 600
Token ID10053
Feature activation+2.36e-01

Pos logit contributions
arcity+1.165
 Cage+0.997
Hardware+0.986
 Sisters+0.969
τ+0.951
Neg logit contributions
anka-0.634
plom-0.611
agen-0.591
 glitter-0.585
 interpol-0.555
Token )
Token ID1267
Feature activation+7.93e-02

Pos logit contributions
arcity+1.292
 Cage+1.077
Hardware+1.066
 Sisters+1.046
τ+1.027
Neg logit contributions
anka-0.945
plom-0.911
agen-0.892
 glitter-0.886
 interpol-0.853
Token gray
Token ID12768
Feature activation+9.81e-01

Pos logit contributions
arcity+0.569
 Cage+0.499
Hardware+0.496
 Sisters+0.489
τ+0.481
Neg logit contributions
anka-0.175
plom-0.169
agen-0.159
 glitter-0.153
 interpol-0.141
Token =
Token ID796
Feature activation+1.30e-01

Pos logit contributions
arcity+3.501
 Cage+2.778
Hardware+2.755
 Sisters+2.626
Drive+2.601
Neg logit contributions
anka-5.511
plom-5.471
 glitter-5.297
agen-5.279
 interpol-5.121
Token c
Token ID269
Feature activation+1.09e-01

Pos logit contributions
arcity+0.741
 Cage+0.620
Hardware+0.617
 Sisters+0.604
τ+0.596
Neg logit contributions
anka-0.492
plom-0.476
agen-0.463
 glitter-0.462
 interpol-0.445
Tokenv
Token ID85
Feature activation-3.74e-02

Pos logit contributions
arcity+0.712
 Cage+0.616
Hardware+0.610
 Sisters+0.601
τ+0.592
Neg logit contributions
anka-0.318
plom-0.303
agen-0.293
 glitter-0.289
 interpol-0.274
Token2
Token ID17
Feature activation+2.92e-01

Pos logit contributions
anka+0.152
plom+0.146
agen+0.143
 glitter+0.141
 interpol+0.137
Neg logit contributions
arcity-0.205
 Cage-0.169
Hardware-0.165
 Sisters-0.164
τ-0.159
Token.
Token ID764
Feature activation+1.65e-01

Pos logit contributions
arcity+1.641
 Cage+1.381
Hardware+1.368
 Sisters+1.342
τ+1.319
Neg logit contributions
anka-1.118
plom-1.080
agen-1.051
 glitter-1.045
 interpol-1.002
Token He
Token ID679
Feature activation+2.72e-02

Pos logit contributions
anka+0.425
plom+0.410
agen+0.402
 glitter+0.398
 interpol+0.384
Neg logit contributions
arcity-0.488
 Cage-0.393
Hardware-0.390
 Sisters-0.383
τ-0.372
Token was
Token ID373
Feature activation-5.05e-02

Pos logit contributions
arcity+0.142
Hardware+0.117
 Cage+0.116
 Sisters+0.114
Drive+0.111
Neg logit contributions
anka-0.117
plom-0.113
agen-0.110
 glitter-0.110
 interpol-0.106
Token given
Token ID1813
Feature activation-9.15e-02

Pos logit contributions
anka+0.208
plom+0.202
 glitter+0.197
agen+0.194
 interpol+0.189
Neg logit contributions
arcity-0.273
Hardware-0.227
 Cage-0.224
 Sisters-0.219
τ-0.215
Token an
Token ID281
Feature activation+1.39e-01

Pos logit contributions
anka+0.390
plom+0.374
 glitter+0.370
agen+0.365
 interpol+0.354
Neg logit contributions
arcity-0.479
Hardware-0.397
 Cage-0.389
 Sisters-0.382
Drive-0.376
Token ult
Token ID3789
Feature activation+9.15e-02

Pos logit contributions
arcity+0.806
 Cage+0.679
Hardware+0.678
 Sisters+0.661
τ+0.652
Neg logit contributions
anka-0.517
plom-0.496
agen-0.484
 glitter-0.479
 interpol-0.462
Tokenim
Token ID320
Feature activation+9.69e-01

Pos logit contributions
arcity+0.472
 Cage+0.391
Hardware+0.389
 Sisters+0.380
τ+0.372
Neg logit contributions
anka-0.394
plom-0.383
agen-0.374
 glitter-0.368
 interpol-0.355
Tokenatum
Token ID21307
Feature activation-4.54e-02

Pos logit contributions
arcity+2.227
 Cage+1.329
Hardware+1.191
 Sisters+1.113
τ+1.112
Neg logit contributions
anka-6.789
 glitter-6.693
plom-6.676
agen-6.552
 interpol-6.530
Token and
Token ID290
Feature activation-9.57e-02

Pos logit contributions
anka+0.189
plom+0.183
agen+0.178
 glitter+0.178
 interpol+0.171
Neg logit contributions
arcity-0.241
Hardware-0.199
 Cage-0.199
 Sisters-0.193
τ-0.190
Token a
Token ID257
Feature activation-2.38e-01

Pos logit contributions
anka+0.405
plom+0.389
 glitter+0.381
agen+0.377
 interpol+0.367
Neg logit contributions
arcity-0.505
Hardware-0.419
 Cage-0.408
 Sisters-0.404
τ-0.395
Token day
Token ID1110
Feature activation-5.22e-02

Pos logit contributions
anka+0.942
plom+0.909
 glitter+0.893
agen+0.881
 interpol+0.843
Neg logit contributions
arcity-1.315
Hardware-1.098
 Cage-1.082
 Sisters-1.059
τ-1.045
Token to
Token ID284
Feature activation-5.79e-02

Pos logit contributions
anka+0.203
plom+0.196
agen+0.192
 glitter+0.190
 interpol+0.182
Neg logit contributions
arcity-0.290
 Cage-0.243
Hardware-0.243
 Sisters-0.237
τ-0.232
Token?
Token ID30
Feature activation+3.09e-02

Pos logit contributions
arcity+0.115
 Cage+0.092
Hardware+0.092
 Sisters+0.089
Drive+0.087
Neg logit contributions
anka-0.116
plom-0.112
agen-0.111
 glitter-0.110
 interpol-0.106
Token
Token ID447
Feature activation+1.59e-01

Pos logit contributions
arcity+0.153
 Cage+0.122
Hardware+0.122
 Sisters+0.118
τ+0.117
Neg logit contributions
anka-0.140
plom-0.134
 glitter-0.133
agen-0.133
 interpol-0.128
Token
Token ID251
Feature activation+8.71e-02

Pos logit contributions
arcity+0.918
 Cage+0.775
Hardware+0.766
 Sisters+0.755
Drive+0.738
Neg logit contributions
anka-0.586
plom-0.563
agen-0.551
 glitter-0.549
 interpol-0.522
Token is
Token ID318
Feature activation+2.47e-01

Pos logit contributions
arcity+0.424
 Cage+0.341
Hardware+0.340
 Sisters+0.329
τ+0.324
Neg logit contributions
anka-0.402
plom-0.387
 glitter-0.384
agen-0.380
 interpol-0.368
Token Sh
Token ID911
Feature activation-2.01e-02

Pos logit contributions
arcity+1.315
Hardware+1.086
 Cage+1.085
 Sisters+1.055
τ+1.040
Neg logit contributions
anka-1.030
plom-0.994
 glitter-0.980
agen-0.971
 interpol-0.937
Tokenag
Token ID363
Feature activation+9.64e-01

Pos logit contributions
anka+0.083
plom+0.079
agen+0.078
 glitter+0.076
 interpol+0.073
Neg logit contributions
arcity-0.108
 Cage-0.091
Hardware-0.090
 Sisters-0.088
τ-0.086
Tokengy
Token ID1360
Feature activation+8.20e-02

Pos logit contributions
arcity+4.845
 Cage+4.039
Hardware+4.009
 Sisters+3.956
τ+3.843
Neg logit contributions
anka-4.064
plom-4.016
agen-3.896
 glitter-3.856
 interpol-3.757
Token
Token ID447
Feature activation+3.54e-01

Pos logit contributions
arcity+0.393
 Cage+0.312
Hardware+0.310
 Sisters+0.301
τ+0.297
Neg logit contributions
anka-0.389
plom-0.373
 glitter-0.370
agen-0.367
 interpol-0.354
Token
Token ID247
Feature activation+1.97e-01

Pos logit contributions
arcity+2.025
 Cage+1.712
Hardware+1.695
 Sisters+1.663
τ+1.636
Neg logit contributions
anka-1.318
plom-1.273
agen-1.237
 glitter-1.230
 interpol-1.178
Tokens
Token ID82
Feature activation+1.09e-01

Pos logit contributions
arcity+0.992
 Cage+0.810
Hardware+0.805
 Sisters+0.784
τ+0.768
Neg logit contributions
anka-0.875
plom-0.846
agen-0.828
 glitter-0.825
 interpol-0.794
Token most
Token ID749
Feature activation-9.04e-02

Pos logit contributions
arcity+0.606
 Cage+0.504
Hardware+0.503
 Sisters+0.490
τ+0.484
Neg logit contributions
anka-0.431
plom-0.415
 glitter-0.406
agen-0.405
 interpol-0.389
Token News
Token ID3000
Feature activation+3.07e-01

Pos logit contributions
arcity+2.188
 Cage+1.791
Hardware+1.769
 Sisters+1.730
τ+1.693
Neg logit contributions
anka-2.052
plom-1.994
agen-1.948
 glitter-1.939
 interpol-1.873
Token Alert
Token ID23276
Feature activation-2.93e-02

Pos logit contributions
arcity+1.616
 Cage+1.344
Hardware+1.330
 Sisters+1.305
τ+1.279
Neg logit contributions
anka-1.286
plom-1.246
agen-1.214
 glitter-1.210
 interpol-1.165
Tokens
Token ID82
Feature activation+2.69e-02

Pos logit contributions
anka+0.119
plom+0.116
agen+0.113
 glitter+0.112
 interpol+0.108
Neg logit contributions
arcity-0.157
 Cage-0.131
Hardware-0.130
 Sisters-0.126
τ-0.125
Token Keep
Token ID9175
Feature activation-2.98e-01

Pos logit contributions
arcity+0.135
 Cage+0.111
Hardware+0.110
 Sisters+0.108
τ+0.106
Neg logit contributions
anka-0.119
plom-0.116
agen-0.113
 glitter-0.112
 interpol-0.108
Token an
Token ID281
Feature activation+3.09e-01

Pos logit contributions
anka+1.210
plom+1.181
agen+1.149
 glitter+1.144
 interpol+1.102
Neg logit contributions
arcity-1.597
Hardware-1.341
 Cage-1.329
 Sisters-1.295
τ-1.285
Token eye
Token ID4151
Feature activation+9.55e-01

Pos logit contributions
arcity+1.932
 Cage+1.656
Hardware+1.646
 Sisters+1.614
τ+1.592
Neg logit contributions
anka-0.993
plom-0.953
agen-0.924
 glitter-0.916
 interpol-0.870
Token out
Token ID503
Feature activation+3.97e-01

Pos logit contributions
arcity+4.553
 Cage+3.840
 Sisters+3.720
Hardware+3.709
τ+3.579
Neg logit contributions
anka-4.289
plom-4.191
agen-4.079
 glitter-3.969
 interpol-3.890
Token for
Token ID329
Feature activation+4.36e-01

Pos logit contributions
arcity+2.042
 Cage+1.695
Hardware+1.672
 Sisters+1.644
τ+1.607
Neg logit contributions
anka-1.698
plom-1.653
agen-1.611
 glitter-1.600
 interpol-1.544
Token an
Token ID281
Feature activation+1.38e-01

Pos logit contributions
arcity+2.325
 Cage+1.934
Hardware+1.917
 Sisters+1.875
τ+1.845
Neg logit contributions
anka-1.804
plom-1.746
agen-1.702
 glitter-1.695
 interpol-1.630
Token email
Token ID3053
Feature activation+1.34e-01

Pos logit contributions
arcity+0.785
 Cage+0.663
Hardware+0.660
 Sisters+0.643
τ+0.637
Neg logit contributions
anka-0.518
plom-0.498
agen-0.488
 glitter-0.480
 interpol-0.463
Token to
Token ID284
Feature activation+1.32e-01

Pos logit contributions
arcity+0.743
 Cage+0.623
Hardware+0.622
 Sisters+0.605
τ+0.599
Neg logit contributions
anka-0.520
plom-0.505
agen-0.489
 glitter-0.488
 interpol-0.470
Token
Token ID198
Feature activation+2.83e-01

Pos logit contributions
arcity+0.757
 Cage+0.591
Hardware+0.587
 Sisters+0.567
τ+0.554
Neg logit contributions
anka-0.933
plom-0.907
agen-0.890
 glitter-0.887
 interpol-0.859
Token
Token ID198
Feature activation+2.21e-01

Pos logit contributions
arcity+1.209
 Cage+0.939
Hardware+0.925
 Sisters+0.901
τ+0.881
Neg logit contributions
anka-1.475
plom-1.436
agen-1.412
 glitter-1.403
 interpol-1.361
TokenUpdate
Token ID10260
Feature activation+2.70e-01

Pos logit contributions
arcity+1.041
 Cage+0.828
 Sisters+0.798
Hardware+0.796
 RI+0.771
Neg logit contributions
anka-1.071
plom-1.043
agen-1.027
 glitter-1.010
 interpol-0.974
Token,
Token ID11
Feature activation+2.87e-01

Pos logit contributions
arcity+1.298
 Cage+1.052
Hardware+1.044
 Sisters+1.015
τ+0.998
Neg logit contributions
anka-1.260
plom-1.224
agen-1.201
 glitter-1.192
 interpol-1.156
Token 3
Token ID513
Feature activation+8.77e-01

Pos logit contributions
arcity+1.369
Hardware+1.094
 Cage+1.090
 Sisters+1.050
τ+1.046
Neg logit contributions
anka-1.361
plom-1.316
 glitter-1.296
agen-1.294
 interpol-1.259
Token:
Token ID25
Feature activation+9.45e-01

Pos logit contributions
arcity+3.530
 Cage+2.765
Hardware+2.717
 Sisters+2.670
τ+2.579
Neg logit contributions
anka-4.716
plom-4.618
agen-4.502
 glitter-4.483
 interpol-4.361
Token01
Token ID486
Feature activation+6.03e-01

Pos logit contributions
arcity+4.305
 Cage+3.601
Hardware+3.532
 Sisters+3.472
τ+3.376
Neg logit contributions
anka-4.527
plom-4.428
agen-4.294
 glitter-4.288
 interpol-4.132
Token p
Token ID279
Feature activation+2.61e-01

Pos logit contributions
arcity+2.821
 Cage+2.284
Hardware+2.259
 Sisters+2.201
τ+2.156
Neg logit contributions
anka-2.879
plom-2.801
agen-2.743
 glitter-2.730
 interpol-2.640
Token.
Token ID13
Feature activation+3.54e-01

Pos logit contributions
arcity+1.414
 Cage+1.171
Hardware+1.159
 Sisters+1.136
τ+1.116
Neg logit contributions
anka-1.066
plom-1.024
agen-1.009
 glitter-0.992
 interpol-0.956
Tokenm
Token ID76
Feature activation+1.85e-01

Pos logit contributions
arcity+1.754
 Cage+1.439
Hardware+1.422
 Sisters+1.390
τ+1.362
Neg logit contributions
anka-1.592
plom-1.547
agen-1.512
 glitter-1.503
 interpol-1.451
Token.
Token ID13
Feature activation+4.01e-01

Pos logit contributions
arcity+0.913
 Cage+0.753
Hardware+0.741
 Sisters+0.728
τ+0.711
Neg logit contributions
anka-0.830
plom-0.806
 glitter-0.791
agen-0.779
 interpol-0.760
Token 20
Token ID1160
Feature activation+1.02e-01

Pos logit contributions
arcity+0.115
 Cage+0.093
Hardware+0.093
Drive+0.089
 Sisters+0.089
Neg logit contributions
anka-0.097
plom-0.095
 glitter-0.094
agen-0.094
 interpol-0.092
Token cents
Token ID16059
Feature activation+3.03e-01

Pos logit contributions
arcity+0.546
 Cage+0.456
Hardware+0.453
 Sisters+0.440
Drive+0.432
Neg logit contributions
anka-0.412
plom-0.401
agen-0.392
 glitter-0.388
 interpol-0.375
Token per
Token ID583
Feature activation+2.18e-01

Pos logit contributions
arcity+1.507
 Cage+1.233
Hardware+1.223
 Sisters+1.193
τ+1.167
Neg logit contributions
anka-1.352
plom-1.323
agen-1.300
 glitter-1.289
 interpol-1.249
Token kil
Token ID8769
Feature activation+1.85e-01

Pos logit contributions
arcity+1.252
Hardware+1.045
 Cage+1.043
 Sisters+1.018
τ+1.001
Neg logit contributions
anka-0.822
plom-0.794
agen-0.776
 glitter-0.770
 interpol-0.739
Tokenow
Token ID322
Feature activation+4.21e-01

Pos logit contributions
arcity+0.771
 Cage+0.609
Hardware+0.601
 Sisters+0.588
τ+0.567
Neg logit contributions
anka-0.985
plom-0.958
agen-0.946
 glitter-0.931
 interpol-0.909
Tokenatt
Token ID1078
Feature activation+9.43e-01

Pos logit contributions
arcity+2.195
 Cage+1.826
Hardware+1.811
 Sisters+1.778
τ+1.733
Neg logit contributions
anka-1.790
plom-1.729
agen-1.701
 glitter-1.670
 interpol-1.619
Token-
Token ID12
Feature activation+4.28e-01

Pos logit contributions
arcity+4.794
 Cage+3.959
Hardware+3.915
 Sisters+3.842
τ+3.809
Neg logit contributions
anka-4.014
plom-3.936
 glitter-3.804
agen-3.721
 interpol-3.606
Tokenhour
Token ID9769
Feature activation+3.57e-01

Pos logit contributions
arcity+2.093
 Cage+1.708
Hardware+1.684
 Sisters+1.649
τ+1.599
Neg logit contributions
anka-1.975
plom-1.913
agen-1.885
 glitter-1.851
 interpol-1.801
Token,
Token ID11
Feature activation+1.60e-01

Pos logit contributions
arcity+1.850
 Cage+1.527
Hardware+1.514
 Sisters+1.482
τ+1.449
Neg logit contributions
anka-1.529
plom-1.482
agen-1.461
 glitter-1.448
 interpol-1.404
Token electricity
Token ID8744
Feature activation-8.99e-02

Pos logit contributions
arcity+0.863
Hardware+0.714
 Cage+0.710
 Sisters+0.696
τ+0.684
Neg logit contributions
anka-0.650
 glitter-0.625
plom-0.624
agen-0.617
 interpol-0.605
Token from
Token ID422
Feature activation+1.96e-01

Pos logit contributions
anka+0.346
plom+0.333
 glitter+0.330
agen+0.330
 interpol+0.324
Neg logit contributions
arcity-0.501
 Cage-0.419
Hardware-0.418
 Sisters-0.405
τ-0.398
Token website
Token ID3052
Feature activation-2.89e-01

Pos logit contributions
anka+0.693
plom+0.666
 glitter+0.664
agen+0.663
 interpol+0.638
Neg logit contributions
arcity-0.608
Hardware-0.475
 Cage-0.466
 Sisters-0.452
τ-0.451
Token.
Token ID13
Feature activation+6.52e-02

Pos logit contributions
anka+1.150
plom+1.103
 glitter+1.082
agen+1.082
 interpol+1.037
Neg logit contributions
arcity-1.588
 Cage-1.316
Hardware-1.304
 Sisters-1.280
τ-1.255
Token
Token ID198
Feature activation-4.93e-02

Pos logit contributions
arcity+0.284
 Cage+0.225
Hardware+0.222
 Sisters+0.216
τ+0.211
Neg logit contributions
anka-0.333
plom-0.324
agen-0.317
 glitter-0.316
 interpol-0.306
Token
Token ID198
Feature activation+1.96e-02

Pos logit contributions
anka+0.247
plom+0.238
agen+0.236
 glitter+0.234
 interpol+0.226
Neg logit contributions
arcity-0.224
 Cage-0.174
Hardware-0.171
 Sisters-0.168
τ-0.164
TokenM
Token ID44
Feature activation+5.03e-02

Pos logit contributions
arcity+0.091
 Cage+0.072
 Sisters+0.069
Hardware+0.069
 RI+0.067
Neg logit contributions
anka-0.097
plom-0.094
agen-0.092
 glitter-0.091
 interpol-0.088
TokenISS
Token ID16744
Feature activation+9.23e-01

Pos logit contributions
arcity+0.259
 Cage+0.215
Hardware+0.213
 Sisters+0.207
τ+0.203
Neg logit contributions
anka-0.218
plom-0.210
agen-0.207
 glitter-0.203
 interpol-0.195
TokenING
Token ID2751
Feature activation+2.89e-01

Pos logit contributions
arcity+4.354
 Cage+3.606
Hardware+3.552
 Sisters+3.494
 RI+3.433
Neg logit contributions
anka-4.262
plom-4.153
agen-4.025
 glitter-4.014
 interpol-3.905
Token 2
Token ID362
Feature activation+1.05e-01

Pos logit contributions
arcity+1.312
 Cage+1.035
Hardware+1.030
 Sisters+0.996
τ+0.982
Neg logit contributions
anka-1.430
plom-1.390
 glitter-1.372
agen-1.365
 interpol-1.321
Token-
Token ID12
Feature activation+1.54e-02

Pos logit contributions
arcity+0.491
 Cage+0.392
Hardware+0.389
 Sisters+0.372
τ+0.370
Neg logit contributions
anka-0.500
plom-0.489
 glitter-0.481
agen-0.477
 interpol-0.462
TokenY
Token ID56
Feature activation+1.42e-02

Pos logit contributions
arcity+0.073
 Cage+0.058
Hardware+0.057
 Sisters+0.056
τ+0.055
Neg logit contributions
anka-0.073
plom-0.071
agen-0.070
 glitter-0.069
 interpol-0.067
TokenEAR
Token ID17133
Feature activation+3.83e-01

Pos logit contributions
arcity+0.094
Hardware+0.081
 Cage+0.081
 Sisters+0.079
τ+0.079
Neg logit contributions
anka-0.040
agen-0.037
plom-0.037
 glitter-0.036
 interpol-0.033
Token other
Token ID584
Feature activation-1.19e-01

Pos logit contributions
arcity+0.251
 Cage+0.210
Hardware+0.208
 Sisters+0.204
τ+0.200
Neg logit contributions
anka-0.185
plom-0.179
agen-0.175
 glitter-0.174
 interpol-0.167
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
anka+0.495
plom+0.474
 glitter+0.470
agen+0.467
 interpol+0.443
Neg logit contributions
arcity-0.640
Hardware-0.524
 Cage-0.523
 Sisters-0.507
Drive-0.501
Token Glow
Token ID45929
Feature activation-1.69e-01

Pos logit contributions
arcity+0.901
Hardware+0.715
 Cage+0.711
τ+0.684
 Sisters+0.679
Neg logit contributions
anka-0.840
plom-0.812
 glitter-0.798
agen-0.796
 interpol-0.763
Token-
Token ID12
Feature activation+1.64e-01

Pos logit contributions
anka+0.726
plom+0.700
 glitter+0.697
agen+0.690
 interpol+0.653
Neg logit contributions
arcity-0.881
 Cage-0.722
Hardware-0.720
 Sisters-0.697
τ-0.685
Tokenin
Token ID259
Feature activation+1.07e-01

Pos logit contributions
arcity+0.810
 Cage+0.662
Hardware+0.655
 Sisters+0.642
τ+0.626
Neg logit contributions
anka-0.745
plom-0.723
agen-0.711
 glitter-0.708
 interpol-0.677
Token-
Token ID12
Feature activation+9.11e-01

Pos logit contributions
arcity+0.578
 Cage+0.487
Hardware+0.478
 Sisters+0.472
τ+0.463
Neg logit contributions
anka-0.427
plom-0.416
agen-0.403
 glitter-0.396
 interpol-0.385
Tokenthe
Token ID1169
Feature activation+3.28e-01

Pos logit contributions
arcity+3.023
 Cage+2.300
Hardware+2.275
τ+2.132
Drive+2.111
Neg logit contributions
anka-5.454
plom-5.349
agen-5.206
 glitter-5.200
 interpol-5.141
Token-
Token ID12
Feature activation+7.09e-01

Pos logit contributions
arcity+1.831
 Cage+1.540
Hardware+1.525
 Sisters+1.495
τ+1.470
Neg logit contributions
anka-1.267
plom-1.225
agen-1.193
 glitter-1.186
 interpol-1.137
Tokendark
Token ID21953
Feature activation+3.29e-01

Pos logit contributions
arcity+3.922
 Cage+3.367
Hardware+3.322
 Sisters+3.235
τ+3.206
Neg logit contributions
anka-2.693
plom-2.626
agen-2.530
 glitter-2.508
 interpol-2.444
Token football
Token ID4346
Feature activation-1.28e-01

Pos logit contributions
arcity+1.768
 Cage+1.467
Hardware+1.458
 Sisters+1.420
τ+1.399
Neg logit contributions
anka-1.355
plom-1.310
 glitter-1.282
agen-1.278
 interpol-1.225
Tokens
Token ID82
Feature activation-2.03e-01

Pos logit contributions
anka+0.526
plom+0.510
 glitter+0.507
agen+0.497
 interpol+0.478
Neg logit contributions
arcity-0.689
 Cage-0.567
Hardware-0.566
 Sisters-0.546
Drive-0.539
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
arcity+0.767
 Cage+0.600
Hardware+0.580
 Sisters+0.574
τ+0.559
Neg logit contributions
anka-0.905
plom-0.880
agen-0.864
 glitter-0.858
 interpol-0.830
TokenDoes
Token ID13921
Feature activation-9.66e-02

Pos logit contributions
arcity+0.700
 Cage+0.556
 Sisters+0.537
Hardware+0.532
 RI+0.518
Neg logit contributions
anka-0.736
plom-0.717
agen-0.704
 glitter-0.695
 interpol-0.672
Token One
Token ID1881
Feature activation+5.27e-02

Pos logit contributions
anka+0.405
plom+0.392
 glitter+0.385
agen+0.383
 interpol+0.366
Neg logit contributions
arcity-0.507
Hardware-0.420
 Cage-0.420
 Sisters-0.406
τ-0.404
Token-
Token ID12
Feature activation+2.37e-01

Pos logit contributions
arcity+0.252
Hardware+0.203
 Cage+0.201
 Sisters+0.195
τ+0.195
Neg logit contributions
anka-0.247
plom-0.239
agen-0.235
 glitter-0.234
 interpol-0.226
Tokenon
Token ID261
Feature activation+2.60e-02

Pos logit contributions
arcity+1.155
 Cage+0.923
Hardware+0.899
 Sisters+0.889
 RI+0.872
Neg logit contributions
anka-1.099
plom-1.073
agen-1.051
 glitter-1.040
 interpol-1.005
Token-
Token ID12
Feature activation+9.01e-01

Pos logit contributions
arcity+0.151
 Cage+0.126
Hardware+0.125
 Sisters+0.123
τ+0.122
Neg logit contributions
anka-0.095
plom-0.091
agen-0.090
 glitter-0.088
 interpol-0.084
TokenOne
Token ID3198
Feature activation-1.19e-01

Pos logit contributions
arcity+3.427
 Cage+2.649
Hardware+2.630
 Sisters+2.520
τ+2.461
Neg logit contributions
anka-5.052
plom-4.947
 glitter-4.846
agen-4.839
 interpol-4.705
Token Out
Token ID3806
Feature activation-3.99e-02

Pos logit contributions
anka+0.495
plom+0.477
 glitter+0.468
agen+0.457
 interpol+0.450
Neg logit contributions
arcity-0.630
Hardware-0.520
 Cage-0.508
τ-0.504
 Sisters-0.498
Tokenreach
Token ID16250
Feature activation-2.72e-02

Pos logit contributions
anka+0.183
plom+0.178
agen+0.173
 glitter+0.173
 interpol+0.166
Neg logit contributions
arcity-0.193
Hardware-0.157
 Cage-0.157
 Sisters-0.152
τ-0.151
Token Make
Token ID6889
Feature activation+1.06e-01

Pos logit contributions
anka+0.119
plom+0.116
 glitter+0.115
agen+0.113
 interpol+0.111
Neg logit contributions
arcity-0.137
Hardware-0.112
 Cage-0.110
τ-0.108
 Sisters-0.107
Token You
Token ID921
Feature activation+2.54e-02

Pos logit contributions
arcity+0.547
Hardware+0.450
 Cage+0.446
τ+0.431
 Sisters+0.431
Neg logit contributions
anka-0.455
plom-0.443
 glitter-0.430
agen-0.427
 interpol-0.413
Tokendraw
Token ID19334
Feature activation+4.02e-01

Pos logit contributions
arcity+0.872
 Cage+0.732
Hardware+0.722
 Sisters+0.713
τ+0.695
Neg logit contributions
anka-0.629
plom-0.610
agen-0.596
 glitter-0.587
 interpol-0.565
Tokening
Token ID278
Feature activation+1.74e-01

Pos logit contributions
arcity+2.137
 Cage+1.785
Hardware+1.772
 Sisters+1.726
τ+1.698
Neg logit contributions
anka-1.647
plom-1.601
 glitter-1.558
agen-1.549
 interpol-1.493
Token.
Token ID13
Feature activation+4.33e-01

Pos logit contributions
arcity+0.931
 Cage+0.770
Hardware+0.760
 Sisters+0.748
τ+0.733
Neg logit contributions
anka-0.715
plom-0.691
agen-0.677
 glitter-0.670
 interpol-0.646
TokenString
Token ID10100
Feature activation+2.80e-01

Pos logit contributions
arcity+1.663
 Cage+1.269
Hardware+1.236
 Sisters+1.210
τ+1.166
Neg logit contributions
anka-2.441
plom-2.386
agen-2.345
 glitter-2.332
 interpol-2.271
TokenAl
Token ID2348
Feature activation+4.79e-01

Pos logit contributions
arcity+0.992
 Cage+0.736
Hardware+0.717
 Sisters+0.700
τ+0.676
Neg logit contributions
anka-1.657
plom-1.619
agen-1.596
 glitter-1.583
 interpol-1.546
Tokenignment
Token ID16747
Feature activation+8.90e-01

Pos logit contributions
arcity+3.460
 Cage+3.013
Hardware+3.005
 Sisters+2.939
Drive+2.912
Neg logit contributions
anka-1.028
plom-0.985
 glitter-0.959
agen-0.910
 interpol-0.863
Token]
Token ID60
Feature activation+2.68e-01

Pos logit contributions
arcity+4.282
Hardware+3.587
 Cage+3.583
 Sisters+3.452
τ+3.418
Neg logit contributions
anka-4.001
plom-3.901
 glitter-3.789
agen-3.761
 interpol-3.635
Token::
Token ID3712
Feature activation+1.49e-01

Pos logit contributions
arcity+1.437
 Cage+1.179
Hardware+1.163
 Sisters+1.149
τ+1.115
Neg logit contributions
anka-1.108
plom-1.073
agen-1.054
 glitter-1.039
 interpol-1.005
TokenNear
Token ID40640
Feature activation+2.28e-01

Pos logit contributions
arcity+0.670
 Cage+0.520
Hardware+0.508
 Sisters+0.504
 RI+0.488
Neg logit contributions
anka-0.749
plom-0.731
agen-0.720
 glitter-0.710
 interpol-0.691
Token }
Token ID1782
Feature activation+4.82e-02

Pos logit contributions
arcity+1.105
 Cage+0.899
Hardware+0.887
 Sisters+0.867
τ+0.851
Neg logit contributions
anka-1.051
plom-1.024
agen-1.003
 glitter-1.000
 interpol-0.969
Token }
Token ID1782
Feature activation+1.86e-01

Pos logit contributions
arcity+0.237
Hardware+0.187
 Cage+0.186
 Sisters+0.182
τ+0.181
Neg logit contributions
anka-0.219
plom-0.213
 glitter-0.212
agen-0.211
 interpol-0.206
Tokenbe
Token ID1350
Feature activation+1.10e-01

Pos logit contributions
anka+0.178
plom+0.171
agen+0.169
 glitter+0.166
 interpol+0.161
Neg logit contributions
arcity-0.215
 Cage-0.178
Hardware-0.174
 Sisters-0.173
τ-0.168
Token66
Token ID2791
Feature activation+2.29e-01

Pos logit contributions
arcity+0.571
 Cage+0.474
Hardware+0.465
 Sisters+0.461
τ+0.449
Neg logit contributions
anka-0.471
plom-0.455
agen-0.447
 glitter-0.442
 interpol-0.427
Token IEEE
Token ID40552
Feature activation+3.26e-01

Pos logit contributions
arcity+1.149
 Cage+0.942
Hardware+0.928
 Sisters+0.914
τ+0.893
Neg logit contributions
anka-1.029
plom-0.993
agen-0.975
 glitter-0.968
 interpol-0.934
Token 802
Token ID33121
Feature activation+5.32e-01

Pos logit contributions
arcity+1.276
 Cage+0.958
Hardware+0.942
 Sisters+0.923
τ+0.898
Neg logit contributions
anka-1.823
plom-1.775
agen-1.747
 glitter-1.743
 interpol-1.712
Token.
Token ID13
Feature activation+6.22e-01

Pos logit contributions
arcity+2.773
 Cage+2.302
Hardware+2.279
 Sisters+2.231
τ+2.189
Neg logit contributions
anka-2.249
plom-2.181
agen-2.126
 glitter-2.116
 interpol-2.036
Token11
Token ID1157
Feature activation+8.87e-01

Pos logit contributions
arcity+2.790
Hardware+2.269
 Cage+2.261
 Sisters+2.170
τ+2.133
Neg logit contributions
anka-3.047
plom-2.972
 glitter-2.909
agen-2.872
 interpol-2.792
Tokenb
Token ID65
Feature activation+1.14e-01

Pos logit contributions
arcity+4.507
 Cage+3.744
Hardware+3.719
 Sisters+3.627
τ+3.546
Neg logit contributions
anka-3.820
plom-3.720
 glitter-3.610
agen-3.605
 interpol-3.459
Tokengn
Token ID4593
Feature activation+1.14e-01

Pos logit contributions
arcity+0.567
 Cage+0.459
Hardware+0.443
 Sisters+0.440
τ+0.433
Neg logit contributions
anka-0.516
plom-0.504
agen-0.494
 glitter-0.489
 interpol-0.480
Token E
Token ID412
Feature activation+1.27e-01

Pos logit contributions
arcity+0.557
 Cage+0.450
Hardware+0.439
 Sisters+0.434
τ+0.424
Neg logit contributions
anka-0.522
plom-0.506
agen-0.498
 glitter-0.492
 interpol-0.482
TokenSS
Token ID5432
Feature activation+1.01e-01

Pos logit contributions
arcity+0.621
 Cage+0.501
Hardware+0.493
 Sisters+0.486
τ+0.475
Neg logit contributions
anka-0.577
plom-0.564
agen-0.554
 glitter-0.545
 interpol-0.530
TokenID
Token ID2389
Feature activation-1.35e-02

Pos logit contributions
arcity+0.439
 Cage+0.337
Hardware+0.332
 Sisters+0.328
τ+0.317
Neg logit contributions
anka-0.522
plom-0.507
agen-0.503
 glitter-0.502
 interpol-0.487
Token original
Token ID2656
Feature activation+7.07e-02

Pos logit contributions
anka+0.886
plom+0.852
agen+0.824
 glitter+0.822
 interpol+0.778
Neg logit contributions
arcity-1.788
 Cage-1.529
Hardware-1.522
 Sisters-1.495
τ-1.474
Token image
Token ID2939
Feature activation-2.09e-01

Pos logit contributions
arcity+0.413
 Cage+0.350
Hardware+0.347
 Sisters+0.341
τ+0.336
Neg logit contributions
anka-0.255
plom-0.247
agen-0.238
 glitter-0.237
 interpol-0.226
Token Download
Token ID10472
Feature activation-2.45e-01

Pos logit contributions
anka+1.143
plom+1.114
agen+1.096
 glitter+1.090
 interpol+1.058
Neg logit contributions
arcity-0.831
 Cage-0.640
Hardware-0.633
 Sisters-0.610
τ-0.596
Token:
Token ID25
Feature activation+1.38e-01

Pos logit contributions
anka+1.221
plom+1.190
 glitter+1.179
agen+1.178
 interpol+1.133
Neg logit contributions
arcity-1.089
 Cage-0.859
Hardware-0.855
 Sisters-0.830
τ-0.805
Token Figure
Token ID11291
Feature activation-1.65e-01

Pos logit contributions
arcity+0.680
Hardware+0.544
 Cage+0.541
 Sisters+0.527
Drive+0.518
Neg logit contributions
anka-0.630
plom-0.610
 glitter-0.603
agen-0.603
 interpol-0.581
Token 1
Token ID352
Feature activation+8.80e-01

Pos logit contributions
anka+0.756
plom+0.717
agen+0.714
 glitter+0.712
 interpol+0.694
Neg logit contributions
arcity-0.815
Hardware-0.649
 Cage-0.647
 Sisters-0.625
τ-0.622
Token.
Token ID13
Feature activation+7.23e-01

Pos logit contributions
arcity+4.121
 Cage+3.572
Hardware+3.470
 Sisters+3.379
 RI+3.267
Neg logit contributions
anka-4.050
plom-3.975
agen-3.816
 glitter-3.796
 interpol-3.661
Token Maze
Token ID33412
Feature activation+4.68e-01

Pos logit contributions
arcity+3.343
 Cage+2.800
Hardware+2.729
 Sisters+2.664
τ+2.581
Neg logit contributions
anka-3.441
plom-3.373
agen-3.261
 glitter-3.248
 interpol-3.138
Token and
Token ID290
Feature activation-3.87e-03

Pos logit contributions
arcity+2.969
 Cage+2.543
Hardware+2.527
 Sisters+2.486
τ+2.449
Neg logit contributions
anka-1.457
plom-1.396
agen-1.352
 glitter-1.343
 interpol-1.274
Token task
Token ID4876
Feature activation+3.23e-02

Pos logit contributions
anka+0.015
plom+0.014
 glitter+0.014
agen+0.014
 interpol+0.013
Neg logit contributions
arcity-0.022
Hardware-0.018
 Cage-0.018
 Sisters-0.018
τ-0.018
Token description
Token ID6764
Feature activation-5.78e-02

Pos logit contributions
arcity+0.186
Hardware+0.155
 Cage+0.155
 Sisters+0.152
τ+0.150
Neg logit contributions
anka-0.120
plom-0.115
agen-0.113
 glitter-0.112
 interpol-0.108
Token on
Token ID319
Feature activation+4.57e-01

Pos logit contributions
arcity+1.034
 Cage+0.860
Hardware+0.849
 Sisters+0.829
τ+0.815
Neg logit contributions
anka-0.868
plom-0.845
agen-0.822
 glitter-0.818
 interpol-0.789
Token Twitter
Token ID3009
Feature activation+3.93e-01

Pos logit contributions
arcity+2.135
 Cage+1.749
Hardware+1.727
 Sisters+1.678
τ+1.653
Neg logit contributions
anka-2.163
plom-2.103
agen-2.059
 glitter-2.041
 interpol-1.972
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
arcity+2.013
 Cage+1.688
Hardware+1.664
 Sisters+1.623
τ+1.594
Neg logit contributions
anka-1.667
plom-1.630
agen-1.580
 glitter-1.578
 interpol-1.518
Token<|endoftext|>
Token ID50256
Feature activation+3.89e-02

Pos logit contributions
arcity+0.515
 Cage+0.415
Hardware+0.409
 Sisters+0.400
τ+0.391
Neg logit contributions
anka-0.547
plom-0.532
agen-0.521
 glitter-0.519
 interpol-0.502
TokenQ
Token ID48
Feature activation-1.81e-02

Pos logit contributions
arcity+0.182
 Cage+0.146
 Sisters+0.141
Hardware+0.139
 RI+0.135
Neg logit contributions
anka-0.189
plom-0.184
agen-0.181
 glitter-0.178
 interpol-0.172
Token:
Token ID25
Feature activation+8.78e-01

Pos logit contributions
anka+0.085
plom+0.082
agen+0.081
 glitter+0.079
 interpol+0.076
Neg logit contributions
arcity-0.087
 Cage-0.070
Hardware-0.070
 Sisters-0.068
τ-0.067
Token Sebastian
Token ID26190
Feature activation+1.45e-01

Pos logit contributions
arcity+4.307
 Cage+3.634
Hardware+3.561
 Sisters+3.529
 RI+3.410
Neg logit contributions
anka-3.846
plom-3.786
agen-3.675
 glitter-3.652
 interpol-3.534
Token,
Token ID11
Feature activation-6.40e-02

Pos logit contributions
arcity+0.723
 Cage+0.584
Hardware+0.584
 Sisters+0.567
τ+0.559
Neg logit contributions
anka-0.657
plom-0.634
agen-0.624
 glitter-0.620
 interpol-0.601
Token last
Token ID938
Feature activation-1.85e-01

Pos logit contributions
anka+0.262
plom+0.251
agen+0.246
 glitter+0.246
 interpol+0.237
Neg logit contributions
arcity-0.349
Hardware-0.285
 Cage-0.284
 Sisters-0.275
τ-0.275
Token year
Token ID614
Feature activation+1.93e-02

Pos logit contributions
anka+0.709
plom+0.678
 glitter+0.674
agen+0.665
 interpol+0.643
Neg logit contributions
arcity-1.054
 Cage-0.869
Hardware-0.866
 Sisters-0.845
τ-0.836
Token you
Token ID345
Feature activation-5.50e-02

Pos logit contributions
arcity+0.102
Hardware+0.083
 Cage+0.083
 Sisters+0.080
τ+0.080
Neg logit contributions
anka-0.082
plom-0.079
agen-0.077
 glitter-0.077
 interpol-0.074
Token.
Token ID13
Feature activation+1.78e-01

Pos logit contributions
arcity+0.740
 Cage+0.614
Hardware+0.609
 Sisters+0.594
τ+0.585
Neg logit contributions
anka-0.542
plom-0.520
agen-0.510
 glitter-0.507
 interpol-0.487
Token
Token ID198
Feature activation+2.83e-01

Pos logit contributions
arcity+0.757
 Cage+0.591
Hardware+0.587
 Sisters+0.567
τ+0.554
Neg logit contributions
anka-0.933
plom-0.907
agen-0.890
 glitter-0.887
 interpol-0.859
Token
Token ID198
Feature activation+2.21e-01

Pos logit contributions
arcity+1.209
 Cage+0.939
Hardware+0.925
 Sisters+0.901
τ+0.881
Neg logit contributions
anka-1.475
plom-1.436
agen-1.412
 glitter-1.403
 interpol-1.361
TokenUpdate
Token ID10260
Feature activation+2.70e-01

Pos logit contributions
arcity+1.041
 Cage+0.828
 Sisters+0.798
Hardware+0.796
 RI+0.771
Neg logit contributions
anka-1.071
plom-1.043
agen-1.027
 glitter-1.010
 interpol-0.974
Token,
Token ID11
Feature activation+2.87e-01

Pos logit contributions
arcity+1.298
 Cage+1.052
Hardware+1.044
 Sisters+1.015
τ+0.998
Neg logit contributions
anka-1.260
plom-1.224
agen-1.201
 glitter-1.192
 interpol-1.156
Token 3
Token ID513
Feature activation+8.77e-01

Pos logit contributions
arcity+1.369
Hardware+1.094
 Cage+1.090
 Sisters+1.050
τ+1.046
Neg logit contributions
anka-1.361
plom-1.316
 glitter-1.296
agen-1.294
 interpol-1.259
Token:
Token ID25
Feature activation+9.45e-01

Pos logit contributions
arcity+3.530
 Cage+2.765
Hardware+2.717
 Sisters+2.670
τ+2.579
Neg logit contributions
anka-4.716
plom-4.618
agen-4.502
 glitter-4.483
 interpol-4.361
Token01
Token ID486
Feature activation+6.03e-01

Pos logit contributions
arcity+4.305
 Cage+3.601
Hardware+3.532
 Sisters+3.472
τ+3.376
Neg logit contributions
anka-4.527
plom-4.428
agen-4.294
 glitter-4.288
 interpol-4.132
Token p
Token ID279
Feature activation+2.61e-01

Pos logit contributions
arcity+2.821
 Cage+2.284
Hardware+2.259
 Sisters+2.201
τ+2.156
Neg logit contributions
anka-2.879
plom-2.801
agen-2.743
 glitter-2.730
 interpol-2.640
Token.
Token ID13
Feature activation+3.54e-01

Pos logit contributions
arcity+1.414
 Cage+1.171
Hardware+1.159
 Sisters+1.136
τ+1.116
Neg logit contributions
anka-1.066
plom-1.024
agen-1.009
 glitter-0.992
 interpol-0.956
Tokenm
Token ID76
Feature activation+1.85e-01

Pos logit contributions
arcity+1.754
 Cage+1.439
Hardware+1.422
 Sisters+1.390
τ+1.362
Neg logit contributions
anka-1.592
plom-1.547
agen-1.512
 glitter-1.503
 interpol-1.451
Token G
Token ID402
Feature activation+2.40e-01

Pos logit contributions
arcity+0.460
Hardware+0.367
 Cage+0.364
 Sisters+0.354
τ+0.350
Neg logit contributions
anka-0.445
 glitter-0.425
plom-0.425
agen-0.418
 interpol-0.401
TokenAL
Token ID1847
Feature activation+5.77e-02

Pos logit contributions
arcity+1.016
 Cage+0.806
Hardware+0.794
 Sisters+0.774
τ+0.755
Neg logit contributions
anka-1.246
plom-1.217
agen-1.192
 glitter-1.187
 interpol-1.153
TokenAX
Token ID25922
Feature activation-1.12e-01

Pos logit contributions
arcity+0.243
 Cage+0.185
Hardware+0.184
 Sisters+0.177
τ+0.176
Neg logit contributions
anka-0.308
 glitter-0.293
agen-0.280
plom-0.277
 interpol-0.276
TokenY
Token ID56
Feature activation+8.52e-02

Pos logit contributions
anka+0.390
 glitter+0.375
plom+0.369
agen+0.363
 interpol+0.347
Neg logit contributions
arcity-0.683
 Cage-0.558
Hardware-0.550
 Sisters-0.530
Drive-0.528
Token VOL
Token ID38570
Feature activation+5.25e-01

Pos logit contributions
arcity+0.462
Hardware+0.376
 Cage+0.375
 Sisters+0.362
τ+0.361
Neg logit contributions
anka-0.350
plom-0.338
 glitter-0.335
agen-0.327
 interpol-0.319
Token.
Token ID13
Feature activation+8.77e-01

Pos logit contributions
arcity+2.673
 Cage+2.219
Hardware+2.196
 Sisters+2.151
τ+2.113
Neg logit contributions
anka-2.271
plom-2.220
agen-2.149
 glitter-2.142
 interpol-2.064
Token 2
Token ID362
Feature activation+6.77e-01

Pos logit contributions
arcity+3.730
 Cage+3.008
Hardware+2.961
 Sisters+2.905
τ+2.848
Neg logit contributions
anka-4.515
plom-4.413
agen-4.303
 glitter-4.270
 interpol-4.136
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
arcity+3.373
 Cage+2.806
Hardware+2.761
 Sisters+2.724
τ+2.658
Neg logit contributions
anka-2.984
plom-2.912
agen-2.839
 glitter-2.797
 interpol-2.709
Token However
Token ID2102
Feature activation-8.14e-02

Pos logit contributions
arcity+1.151
 Cage+0.924
Hardware+0.920
 Sisters+0.893
τ+0.881
Neg logit contributions
anka-1.047
plom-1.011
agen-0.992
 glitter-0.991
 interpol-0.956
Token,
Token ID11
Feature activation-5.03e-02

Pos logit contributions
anka+0.361
plom+0.350
agen+0.342
 glitter+0.341
 interpol+0.329
Neg logit contributions
arcity-0.408
 Cage-0.335
Hardware-0.332
 Sisters-0.325
τ-0.318
Token even
Token ID772
Feature activation-1.86e-01

Pos logit contributions
anka+0.203
 glitter+0.194
plom+0.192
agen+0.189
 interpol+0.185
Neg logit contributions
arcity-0.276
Hardware-0.227
 Cage-0.224
τ-0.219
 Sisters-0.218
Token
Token ID198
Feature activation-1.68e-03

Pos logit contributions
anka+0.344
plom+0.332
agen+0.326
 glitter+0.324
 interpol+0.314
Neg logit contributions
arcity-0.326
Hardware-0.254
 Cage-0.253
 Sisters-0.244
τ-0.243
Token
Token ID198
Feature activation+1.83e-02

Pos logit contributions
anka+0.008
plom+0.008
agen+0.008
 glitter+0.008
 interpol+0.008
Neg logit contributions
arcity-0.008
 Cage-0.006
Hardware-0.006
 Sisters-0.006
τ-0.006
TokenU
Token ID52
Feature activation+4.12e-03

Pos logit contributions
arcity+0.088
 Cage+0.069
 Sisters+0.067
Hardware+0.066
 RI+0.065
Neg logit contributions
anka-0.087
plom-0.085
agen-0.084
 glitter-0.082
 interpol-0.079
TokenPDATED
Token ID49316
Feature activation+2.33e-01

Pos logit contributions
arcity+0.022
 Cage+0.018
Hardware+0.018
 Sisters+0.018
τ+0.017
Neg logit contributions
anka-0.017
plom-0.017
agen-0.016
 glitter-0.016
 interpol-0.016
Token 2
Token ID362
Feature activation+5.00e-01

Pos logit contributions
arcity+1.096
 Cage+0.874
Hardware+0.872
 Sisters+0.842
τ+0.831
Neg logit contributions
anka-1.107
plom-1.074
agen-1.060
 glitter-1.052
 interpol-1.022
Token:
Token ID25
Feature activation+8.76e-01

Pos logit contributions
arcity+2.094
 Cage+1.646
Hardware+1.625
 Sisters+1.571
τ+1.538
Neg logit contributions
anka-2.639
plom-2.572
agen-2.526
 glitter-2.515
 interpol-2.440
Token35
Token ID2327
Feature activation+5.23e-01

Pos logit contributions
arcity+4.055
 Cage+3.379
Hardware+3.319
 Sisters+3.262
τ+3.176
Neg logit contributions
anka-4.152
plom-4.057
agen-3.937
 glitter-3.931
 interpol-3.789
Token p
Token ID279
Feature activation+2.81e-01

Pos logit contributions
arcity+2.412
 Cage+1.944
Hardware+1.927
 Sisters+1.872
τ+1.834
Neg logit contributions
anka-2.540
plom-2.470
agen-2.420
 glitter-2.409
 interpol-2.329
Token.
Token ID13
Feature activation+3.08e-01

Pos logit contributions
arcity+1.488
 Cage+1.234
Hardware+1.222
 Sisters+1.196
τ+1.174
Neg logit contributions
anka-1.173
plom-1.134
agen-1.110
 glitter-1.100
 interpol-1.059
Tokenm
Token ID76
Feature activation+1.59e-01

Pos logit contributions
arcity+1.528
 Cage+1.254
Hardware+1.239
 Sisters+1.211
τ+1.187
Neg logit contributions
anka-1.388
plom-1.348
agen-1.318
 glitter-1.310
 interpol-1.264
Token.:
Token ID11207
Feature activation+6.67e-01

Pos logit contributions
arcity+0.786
 Cage+0.651
Hardware+0.641
 Sisters+0.629
τ+0.615
Neg logit contributions
anka-0.714
plom-0.693
 glitter-0.680
agen-0.671
 interpol-0.653
TokenVolume
Token ID31715
Feature activation+5.81e-01

Pos logit contributions
arcity+1.696
 Cage+1.394
Hardware+1.368
 Sisters+1.342
τ+1.317
Neg logit contributions
anka-1.496
plom-1.447
agen-1.427
 glitter-1.412
 interpol-1.368
Token()
Token ID3419
Feature activation+9.74e-02

Pos logit contributions
arcity+2.875
 Cage+2.343
Hardware+2.299
 Sisters+2.257
τ+2.206
Neg logit contributions
anka-2.637
plom-2.549
agen-2.516
 glitter-2.496
 interpol-2.425
Token ;
Token ID2162
Feature activation+3.71e-01

Pos logit contributions
arcity+0.499
 Cage+0.412
Hardware+0.406
 Sisters+0.395
τ+0.389
Neg logit contributions
anka-0.422
plom-0.408
 glitter-0.403
agen-0.403
 interpol-0.392
Token return
Token ID1441
Feature activation+5.21e-02

Pos logit contributions
arcity+1.825
Hardware+1.462
 Cage+1.460
 Sisters+1.411
τ+1.395
Neg logit contributions
anka-1.699
plom-1.646
 glitter-1.629
agen-1.619
 interpol-1.579
Token f
Token ID277
Feature activation+4.19e-01

Pos logit contributions
arcity+0.264
Hardware+0.214
 Cage+0.212
 Sisters+0.207
τ+0.205
Neg logit contributions
anka-0.229
 glitter-0.222
plom-0.221
agen-0.219
 interpol-0.216
TokenMass
Token ID20273
Feature activation+8.72e-01

Pos logit contributions
arcity+2.077
 Cage+1.700
Hardware+1.693
 Sisters+1.654
τ+1.622
Neg logit contributions
anka-1.874
plom-1.826
agen-1.771
 glitter-1.767
 interpol-1.703
Token ;
Token ID2162
Feature activation+3.80e-01

Pos logit contributions
arcity+4.324
 Cage+3.576
Hardware+3.546
 Sisters+3.465
τ+3.420
Neg logit contributions
anka-3.845
plom-3.746
agen-3.624
 glitter-3.606
 interpol-3.454
Token }
Token ID1782
Feature activation+1.10e-01

Pos logit contributions
arcity+1.617
 Cage+1.291
Hardware+1.264
 Sisters+1.234
τ+1.206
Neg logit contributions
anka-1.978
plom-1.924
agen-1.875
 glitter-1.864
 interpol-1.800
Token
Token ID198
Feature activation+3.07e-01

Pos logit contributions
arcity+0.537
 Cage+0.426
Hardware+0.425
 Sisters+0.411
τ+0.411
Neg logit contributions
anka-0.513
plom-0.496
 glitter-0.495
agen-0.491
 interpol-0.480
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
arcity+1.310
 Cage+1.021
Hardware+1.003
 Sisters+0.980
τ+0.956
Neg logit contributions
anka-1.603
plom-1.561
agen-1.536
 glitter-1.526
 interpol-1.482
TokenAss
Token ID8021
Feature activation+3.27e-01

Pos logit contributions
arcity+0.658
 Cage+0.525
 Sisters+0.507
Hardware+0.496
 RI+0.486
Neg logit contributions
anka-0.707
plom-0.685
agen-0.678
 glitter-0.668
 interpol-0.652
Token performance
Token ID2854
Feature activation-1.37e-01

Pos logit contributions
arcity+1.173
Hardware+0.977
 Cage+0.976
 Sisters+0.949
τ+0.932
Neg logit contributions
anka-0.864
plom-0.833
 glitter-0.824
agen-0.818
 interpol-0.791
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
anka+0.545
plom+0.523
agen+0.517
 glitter+0.515
 interpol+0.496
Neg logit contributions
arcity-0.749
 Cage-0.627
Hardware-0.622
 Sisters-0.606
τ-0.596
Token would
Token ID561
Feature activation+1.17e-01

Pos logit contributions
arcity+1.034
Hardware+0.865
 Cage+0.862
 Sisters+0.843
τ+0.831
Neg logit contributions
anka-0.686
plom-0.663
 glitter-0.651
agen-0.645
 interpol-0.623
Token give
Token ID1577
Feature activation+2.75e-01

Pos logit contributions
arcity+0.629
 Cage+0.525
Hardware+0.525
 Sisters+0.511
τ+0.503
Neg logit contributions
anka-0.472
plom-0.462
 glitter-0.456
agen-0.452
 interpol-0.438
Token them
Token ID606
Feature activation+1.58e-01

Pos logit contributions
arcity+1.318
 Cage+1.065
Hardware+1.064
 Sisters+1.035
τ+1.015
Neg logit contributions
anka-1.278
plom-1.244
 glitter-1.220
agen-1.219
 interpol-1.177
Token enough
Token ID1576
Feature activation+8.71e-01

Pos logit contributions
arcity+0.845
Hardware+0.702
 Cage+0.698
 Sisters+0.681
τ+0.671
Neg logit contributions
anka-0.649
plom-0.629
 glitter-0.623
agen-0.616
 interpol-0.597
Token space
Token ID2272
Feature activation+2.28e-01

Pos logit contributions
arcity+4.807
 Cage+4.075
Hardware+3.995
 Sisters+3.924
τ+3.856
Neg logit contributions
anka-3.376
plom-3.278
agen-3.174
 glitter-3.105
 interpol-2.991
Token to
Token ID284
Feature activation+2.28e-01

Pos logit contributions
arcity+1.077
 Cage+0.876
Hardware+0.863
 Sisters+0.844
τ+0.827
Neg logit contributions
anka-1.075
plom-1.046
agen-1.021
 glitter-1.016
 interpol-0.983
Token sign
Token ID1051
Feature activation+8.42e-02

Pos logit contributions
arcity+1.203
 Cage+0.993
Hardware+0.990
 Sisters+0.967
τ+0.951
Neg logit contributions
anka-0.951
plom-0.926
 glitter-0.908
agen-0.903
 interpol-0.874
Token at
Token ID379
Feature activation-6.06e-06

Pos logit contributions
arcity+0.456
Hardware+0.377
 Cage+0.370
 Sisters+0.366
Drive+0.360
Neg logit contributions
anka-0.339
 glitter-0.330
plom-0.328
agen-0.323
 interpol-0.315
Token least
Token ID1551
Feature activation+5.03e-01

Feature not active on prev token;
no predictions were affected.
Token being
Token ID852
Feature activation+4.81e-02

Pos logit contributions
anka+0.531
 glitter+0.517
plom+0.517
agen+0.499
 interpol+0.490
Neg logit contributions
arcity-0.762
Hardware-0.636
 Cage-0.628
 Sisters-0.606
Drive-0.606
Token warned
Token ID7728
Feature activation-1.55e-01

Pos logit contributions
arcity+0.232
Hardware+0.187
 Cage+0.187
 Sisters+0.180
τ+0.179
Neg logit contributions
anka-0.226
plom-0.220
 glitter-0.217
agen-0.214
 interpol-0.209
Token to
Token ID284
Feature activation+2.75e-01

Pos logit contributions
anka+0.644
 glitter+0.619
plom+0.618
agen+0.617
 interpol+0.583
Neg logit contributions
arcity-0.818
Hardware-0.680
 Cage-0.665
 Sisters-0.649
τ-0.644
Token keep
Token ID1394
Feature activation+9.50e-02

Pos logit contributions
arcity+1.471
Hardware+1.219
 Cage+1.212
 Sisters+1.184
τ+1.164
Neg logit contributions
anka-1.120
plom-1.096
 glitter-1.086
agen-1.073
 interpol-1.038
Token an
Token ID281
Feature activation+2.06e-01

Pos logit contributions
arcity+0.505
Hardware+0.417
 Cage+0.406
 Sisters+0.396
τ+0.393
Neg logit contributions
anka-0.398
 glitter-0.393
plom-0.382
agen-0.375
 interpol-0.369
Token eye
Token ID4151
Feature activation+8.69e-01

Pos logit contributions
arcity+1.399
Hardware+1.215
 Cage+1.210
 Sisters+1.181
τ+1.178
Neg logit contributions
anka-0.550
plom-0.526
 glitter-0.512
agen-0.510
 interpol-0.479
Token out
Token ID503
Feature activation+1.29e-01

Pos logit contributions
arcity+4.244
 Cage+3.615
 Sisters+3.507
Hardware+3.468
τ+3.354
Neg logit contributions
anka-3.763
plom-3.673
agen-3.580
 glitter-3.438
 interpol-3.409
Token for
Token ID329
Feature activation+2.55e-01

Pos logit contributions
arcity+0.679
 Cage+0.564
Hardware+0.559
 Sisters+0.546
τ+0.537
Neg logit contributions
anka-0.538
plom-0.521
agen-0.508
 glitter-0.507
 interpol-0.486
Token two
Token ID734
Feature activation+6.16e-02

Pos logit contributions
arcity+1.369
Hardware+1.129
 Cage+1.124
 Sisters+1.088
τ+1.085
Neg logit contributions
anka-1.059
plom-1.016
 glitter-1.014
agen-1.000
 interpol-0.962
Token scams
Token ID41718
Feature activation+2.48e-01

Pos logit contributions
arcity+0.342
Hardware+0.284
 Cage+0.281
τ+0.274
Drive+0.269
Neg logit contributions
anka-0.243
 glitter-0.236
plom-0.231
agen-0.228
 interpol-0.222
Token working
Token ID1762
Feature activation-4.11e-02

Pos logit contributions
arcity+1.322
 Cage+1.092
Hardware+1.091
 Sisters+1.056
τ+1.044
Neg logit contributions
anka-1.030
plom-0.996
 glitter-0.975
agen-0.973
 interpol-0.935
Token-
Token ID12
Feature activation-6.60e-01

Pos logit contributions
anka+2.732
plom+2.570
agen+2.537
 glitter+2.535
 interpol+2.445
Neg logit contributions
arcity-5.279
Hardware-4.430
 Cage-4.424
τ-4.307
 Sisters-4.291
Tokenand
Token ID392
Feature activation-4.74e-01

Pos logit contributions
anka+2.595
plom+2.586
agen+2.488
 glitter+2.435
 interpol+2.332
Neg logit contributions
arcity-3.650
 Cage-3.071
Hardware-2.978
 Sisters-2.893
Drive-2.849
Token-
Token ID12
Feature activation-8.24e-02

Pos logit contributions
anka+1.645
plom+1.584
agen+1.548
 glitter+1.529
 interpol+1.468
Neg logit contributions
arcity-2.827
 Cage-2.390
Hardware-2.380
τ-2.305
 Sisters-2.304
Tokensoc
Token ID35634
Feature activation-2.03e-01

Pos logit contributions
anka+0.429
plom+0.420
agen+0.413
 glitter+0.407
 interpol+0.395
Neg logit contributions
arcity-0.351
 Cage-0.276
Hardware-0.274
 Sisters-0.264
τ-0.256
Tokeniety
Token ID1905
Feature activation-6.04e-01

Pos logit contributions
anka+0.538
plom+0.525
agen+0.479
 glitter+0.475
 interpol+0.432
Neg logit contributions
arcity-1.385
 Cage-1.204
Hardware-1.197
 Sisters-1.178
τ-1.176
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
anka+2.567
plom+2.510
agen+2.442
 glitter+2.425
 interpol+2.328
Neg logit contributions
arcity-3.130
 Cage-2.578
Hardware-2.544
 Sisters-2.499
τ-2.448
Token community
Token ID2055
Feature activation-8.52e-01

Pos logit contributions
anka+4.382
 glitter+4.286
 mer+4.105
plom+4.045
agen+4.034
Neg logit contributions
arcity-6.278
 Cage-5.242
Hardware-5.219
Drive-5.083
τ-4.999
Token-
Token ID12
Feature activation-5.51e-01

Pos logit contributions
anka+2.832
plom+2.696
agen+2.652
 glitter+2.633
 interpol+2.541
Neg logit contributions
arcity-5.248
 Cage-4.414
Hardware-4.394
τ-4.299
 Sisters-4.289
Tokenorgan
Token ID9971
Feature activation-3.89e-01

Pos logit contributions
anka+2.295
plom+2.260
agen+2.191
 glitter+2.163
 interpol+2.066
Neg logit contributions
arcity-2.921
 Cage-2.446
Hardware-2.363
 Sisters-2.343
Drive-2.281
Tokenisations
Token ID38189
Feature activation-2.72e-01

Pos logit contributions
anka+1.550
plom+1.484
agen+1.477
 glitter+1.475
 interpol+1.404
Neg logit contributions
arcity-2.128
 Cage-1.773
Hardware-1.759
 Sisters-1.715
τ-1.693
Token,
Token ID11
Feature activation-1.06e+00

Pos logit contributions
anka+1.143
plom+1.111
agen+1.086
 glitter+1.075
 interpol+1.034
Neg logit contributions
arcity-1.429
 Cage-1.184
Hardware-1.175
 Sisters-1.149
τ-1.128
Token marine
Token ID16050
Feature activation-6.42e-01

Pos logit contributions
 glitter+3.864
anka+3.805
plom+3.715
 interpol+3.689
agen+3.676
Neg logit contributions
arcity-4.742
Hardware-3.853
 Cage-3.814
τ-3.747
Drive-3.733
Token-
Token ID12
Feature activation-5.21e-01

Pos logit contributions
anka+2.340
plom+2.265
agen+2.248
 glitter+2.195
 interpol+2.091
Neg logit contributions
arcity-3.668
 Cage-3.143
Hardware-3.089
 Sisters-3.078
τ-3.014
Tokenbiology
Token ID43592
Feature activation-7.70e-01

Pos logit contributions
anka+1.942
plom+1.898
agen+1.894
 glitter+1.802
 interpol+1.709
Neg logit contributions
arcity-2.920
 Cage-2.486
 Sisters-2.461
Hardware-2.446
Drive-2.378
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
anka+2.888
agen+2.789
plom+2.789
 glitter+2.708
 interpol+2.613
Neg logit contributions
arcity-4.353
Hardware-3.599
 Cage-3.571
 Sisters-3.496
τ-3.470
Token conservation
Token ID14903
Feature activation-1.66e-01

Pos logit contributions
 glitter+4.317
anka+4.288
plom+4.200
 interpol+4.121
 mer+4.120
Neg logit contributions
arcity-5.623
Hardware-4.629
 Cage-4.521
Drive-4.481
τ-4.449
Token,
Token ID11
Feature activation-1.12e+00

Pos logit contributions
anka+0.717
plom+0.693
agen+0.682
 glitter+0.675
 interpol+0.652
Neg logit contributions
arcity-0.856
 Cage-0.708
Hardware-0.703
 Sisters-0.686
τ-0.676
Token environment
Token ID2858
Feature activation-5.20e-01

Pos logit contributions
 glitter+4.444
anka+4.384
plom+4.281
 mer+4.237
 interpol+4.223
Neg logit contributions
arcity-5.863
Hardware-4.847
 Cage-4.720
Drive-4.702
τ-4.654
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
anka+2.107
plom+2.027
agen+2.014
 glitter+1.982
 interpol+1.917
Neg logit contributions
arcity-2.807
 Cage-2.317
Hardware-2.314
 Sisters-2.242
τ-2.231
Token oceans
Token ID23744
Feature activation-5.41e-01

Pos logit contributions
 glitter+4.345
anka+4.316
plom+4.208
 mer+4.136
 interpol+4.125
Neg logit contributions
arcity-5.721
Hardware-4.745
Drive-4.601
 Cage-4.601
τ-4.539
Token-
Token ID12
Feature activation-5.27e-01

Pos logit contributions
anka+2.166
plom+2.096
agen+2.045
 glitter+2.032
 interpol+1.950
Neg logit contributions
arcity-2.939
 Cage-2.459
Hardware-2.435
 Sisters-2.388
τ-2.344
Tokenand
Token ID392
Feature activation-2.44e-01

Pos logit contributions
anka+2.233
plom+2.174
agen+2.120
 glitter+2.079
 interpol+1.994
Neg logit contributions
arcity-2.737
Hardware-2.291
 Cage-2.288
 Sisters-2.231
τ-2.157
Token-
Token ID12
Feature activation-4.24e-01

Pos logit contributions
anka+2.322
agen+2.254
plom+2.236
 glitter+2.147
 interpol+2.043
Neg logit contributions
arcity-4.134
 Cage-3.473
Hardware-3.452
 Sisters-3.355
τ-3.347
Tokenand
Token ID392
Feature activation-2.86e-01

Pos logit contributions
anka+1.871
plom+1.828
agen+1.784
 glitter+1.766
 interpol+1.700
Neg logit contributions
arcity-2.143
 Cage-1.763
Hardware-1.733
 Sisters-1.702
τ-1.659
Token-
Token ID12
Feature activation-1.69e-01

Pos logit contributions
anka+1.062
plom+1.023
agen+1.001
 glitter+0.987
 interpol+0.942
Neg logit contributions
arcity-1.647
 Cage-1.395
Hardware-1.374
 Sisters-1.349
τ-1.333
Tokenf
Token ID69
Feature activation-4.18e-02

Pos logit contributions
anka+0.951
plom+0.934
agen+0.920
 glitter+0.909
 interpol+0.880
Neg logit contributions
arcity-0.642
 Cage-0.493
Hardware-0.487
 Sisters-0.475
τ-0.451
Tokeninance
Token ID14149
Feature activation-5.10e-01

Pos logit contributions
anka+0.182
plom+0.177
agen+0.173
 glitter+0.171
 interpol+0.164
Neg logit contributions
arcity-0.213
 Cage-0.177
Hardware-0.175
 Sisters-0.171
τ-0.168
Token,
Token ID11
Feature activation-1.11e+00

Pos logit contributions
anka+2.046
plom+1.944
agen+1.921
 glitter+1.899
 interpol+1.827
Neg logit contributions
arcity-2.814
Hardware-2.297
 Cage-2.288
τ-2.217
 Sisters-2.214
Token aust
Token ID38132
Feature activation-3.48e-01

Pos logit contributions
anka+4.465
 glitter+4.376
plom+4.291
 mer+4.214
agen+4.184
Neg logit contributions
arcity-5.832
Hardware-4.708
 Cage-4.679
Drive-4.616
τ-4.601
Tokenral
Token ID1373
Feature activation+4.90e-02

Pos logit contributions
anka+1.214
plom+1.151
agen+1.113
 glitter+1.084
 interpol+1.027
Neg logit contributions
arcity-2.063
 Cage-1.796
Hardware-1.796
 Sisters-1.747
τ-1.736
Tokenia
Token ID544
Feature activation-1.78e-01

Pos logit contributions
arcity+0.177
 Cage+0.136
Hardware+0.133
 Sisters+0.129
τ+0.125
Neg logit contributions
anka-0.288
plom-0.282
agen-0.277
 glitter-0.272
 interpol-0.264
Token
Token ID198
Feature activation-6.51e-01

Pos logit contributions
anka+0.923
plom+0.898
agen+0.881
 glitter+0.878
 interpol+0.853
Neg logit contributions
arcity-0.764
 Cage-0.607
Hardware-0.599
 Sisters-0.583
τ-0.568
Token
Token ID198
Feature activation-4.45e-01

Pos logit contributions
anka+2.877
plom+2.769
agen+2.757
 glitter+2.711
 mer+2.658
Neg logit contributions
arcity-3.314
 conduc-2.654
 Cage-2.530
Hardware-2.473
 Instr-2.458
Token:
Token ID25
Feature activation-8.82e-01

Pos logit contributions
arcity+2.800
 Cage+2.200
Hardware+2.160
 Sisters+2.106
τ+2.021
Neg logit contributions
anka-3.956
plom-3.879
agen-3.787
 glitter-3.775
 interpol-3.679
Token beef
Token ID12023
Feature activation-7.63e-01

Pos logit contributions
anka+4.293
 glitter+4.230
plom+4.143
agen+4.125
 interpol+4.049
Neg logit contributions
arcity-3.935
Hardware-3.057
 Cage-3.041
τ-3.002
Drive-2.966
Token-
Token ID12
Feature activation-5.23e-01

Pos logit contributions
anka+3.030
plom+2.911
agen+2.896
 glitter+2.794
 interpol+2.689
Neg logit contributions
arcity-4.139
 Cage-3.480
Hardware-3.444
 Sisters-3.337
τ-3.306
Tokenc
Token ID66
Feature activation-2.40e-01

Pos logit contributions
anka+2.180
plom+2.135
agen+2.128
 glitter+2.048
 interpol+1.962
Neg logit contributions
arcity-2.724
 Cage-2.251
 Sisters-2.236
Hardware-2.212
τ-2.149
Tokenattle
Token ID1999
Feature activation-4.64e-01

Pos logit contributions
anka+0.962
plom+0.935
agen+0.932
 glitter+0.858
 interpol+0.834
Neg logit contributions
arcity-1.282
 Cage-1.108
Hardware-1.107
 Sisters-1.081
τ-1.068
Token,
Token ID11
Feature activation-1.11e+00

Pos logit contributions
anka+1.957
plom+1.898
agen+1.866
 glitter+1.804
 interpol+1.753
Neg logit contributions
arcity-2.422
 Cage-2.010
Hardware-1.996
 Sisters-1.964
τ-1.937
Token rural
Token ID10016
Feature activation-5.87e-01

Pos logit contributions
anka+4.936
 glitter+4.848
plom+4.743
agen+4.684
 mer+4.667
Neg logit contributions
arcity-5.365
Hardware-4.257
 Cage-4.205
τ-4.179
Drive-4.162
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
anka+2.337
plom+2.257
agen+2.209
 glitter+2.180
 interpol+2.094
Neg logit contributions
arcity-3.211
 Cage-2.678
Hardware-2.660
 Sisters-2.605
τ-2.566
Token business
Token ID1597
Feature activation-4.69e-01

Pos logit contributions
anka+4.108
 glitter+4.028
plom+3.925
agen+3.852
 diplomacy+3.839
Neg logit contributions
arcity-5.397
Hardware-4.398
 Cage-4.329
Drive-4.289
τ-4.283
Token-
Token ID12
Feature activation-5.64e-01

Pos logit contributions
anka+1.782
plom+1.701
agen+1.661
 glitter+1.634
 interpol+1.573
Neg logit contributions
arcity-2.692
 Cage-2.269
Hardware-2.243
 Sisters-2.192
τ-2.154
Tokeneconom
Token ID13926
Feature activation-5.45e-01

Pos logit contributions
plom+1.600
anka+1.586
agen+1.557
 glitter+1.468
 interpol+1.368
Neg logit contributions
arcity-3.758
 Cage-3.241
 Sisters-3.184
Hardware-3.139
Drive-3.059
Tokenbiology
Token ID43592
Feature activation-7.70e-01

Pos logit contributions
anka+1.942
plom+1.898
agen+1.894
 glitter+1.802
 interpol+1.709
Neg logit contributions
arcity-2.920
 Cage-2.486
 Sisters-2.461
Hardware-2.446
Drive-2.378
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
anka+2.888
agen+2.789
plom+2.789
 glitter+2.708
 interpol+2.613
Neg logit contributions
arcity-4.353
Hardware-3.599
 Cage-3.571
 Sisters-3.496
τ-3.470
Token conservation
Token ID14903
Feature activation-1.66e-01

Pos logit contributions
 glitter+4.317
anka+4.288
plom+4.200
 interpol+4.121
 mer+4.120
Neg logit contributions
arcity-5.623
Hardware-4.629
 Cage-4.521
Drive-4.481
τ-4.449
Token,
Token ID11
Feature activation-1.12e+00

Pos logit contributions
anka+0.717
plom+0.693
agen+0.682
 glitter+0.675
 interpol+0.652
Neg logit contributions
arcity-0.856
 Cage-0.708
Hardware-0.703
 Sisters-0.686
τ-0.676
Token environment
Token ID2858
Feature activation-5.20e-01

Pos logit contributions
 glitter+4.444
anka+4.384
plom+4.281
 mer+4.237
 interpol+4.223
Neg logit contributions
arcity-5.863
Hardware-4.847
 Cage-4.720
Drive-4.702
τ-4.654
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
anka+2.107
plom+2.027
agen+2.014
 glitter+1.982
 interpol+1.917
Neg logit contributions
arcity-2.807
 Cage-2.317
Hardware-2.314
 Sisters-2.242
τ-2.231
Token oceans
Token ID23744
Feature activation-5.41e-01

Pos logit contributions
 glitter+4.345
anka+4.316
plom+4.208
 mer+4.136
 interpol+4.125
Neg logit contributions
arcity-5.721
Hardware-4.745
Drive-4.601
 Cage-4.601
τ-4.539
Token-
Token ID12
Feature activation-5.27e-01

Pos logit contributions
anka+2.166
plom+2.096
agen+2.045
 glitter+2.032
 interpol+1.950
Neg logit contributions
arcity-2.939
 Cage-2.459
Hardware-2.435
 Sisters-2.388
τ-2.344
Tokenand
Token ID392
Feature activation-2.44e-01

Pos logit contributions
anka+2.233
plom+2.174
agen+2.120
 glitter+2.079
 interpol+1.994
Neg logit contributions
arcity-2.737
Hardware-2.291
 Cage-2.288
 Sisters-2.231
τ-2.157
Token-
Token ID12
Feature activation-6.27e-02

Pos logit contributions
anka+0.897
plom+0.864
agen+0.845
 glitter+0.833
 interpol+0.797
Neg logit contributions
arcity-1.405
 Cage-1.194
Hardware-1.187
 Sisters-1.157
τ-1.148
Tokenree
Token ID631
Feature activation-1.51e-01

Pos logit contributions
anka+0.191
plom+0.182
agen+0.175
 glitter+0.171
 interpol+0.160
Neg logit contributions
arcity-0.403
 Cage-0.350
Hardware-0.350
 Sisters-0.342
τ-0.335
TokenTopics
Token ID25902
Feature activation+6.68e-01

Pos logit contributions
arcity+0.737
 Cage+0.592
Hardware+0.577
 Sisters+0.571
τ+0.552
Neg logit contributions
anka-0.758
plom-0.737
agen-0.723
 glitter-0.716
 interpol-0.691
Token:
Token ID25
Feature activation-9.30e-01

Pos logit contributions
arcity+2.615
 Cage+2.055
Hardware+2.020
 Sisters+1.968
τ+1.895
Neg logit contributions
anka-3.651
plom-3.578
agen-3.498
 glitter-3.485
 interpol-3.395
Token marine
Token ID16050
Feature activation-6.42e-01

Pos logit contributions
 glitter+3.864
anka+3.805
plom+3.715
 interpol+3.689
agen+3.676
Neg logit contributions
arcity-4.742
Hardware-3.853
 Cage-3.814
τ-3.747
Drive-3.733
Token-
Token ID12
Feature activation-5.21e-01

Pos logit contributions
anka+2.340
plom+2.265
agen+2.248
 glitter+2.195
 interpol+2.091
Neg logit contributions
arcity-3.668
 Cage-3.143
Hardware-3.089
 Sisters-3.078
τ-3.014
Tokenbiology
Token ID43592
Feature activation-7.70e-01

Pos logit contributions
anka+1.942
plom+1.898
agen+1.894
 glitter+1.802
 interpol+1.709
Neg logit contributions
arcity-2.920
 Cage-2.486
 Sisters-2.461
Hardware-2.446
Drive-2.378
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
anka+2.888
agen+2.789
plom+2.789
 glitter+2.708
 interpol+2.613
Neg logit contributions
arcity-4.353
Hardware-3.599
 Cage-3.571
 Sisters-3.496
τ-3.470
Token conservation
Token ID14903
Feature activation-1.66e-01

Pos logit contributions
 glitter+4.317
anka+4.288
plom+4.200
 interpol+4.121
 mer+4.120
Neg logit contributions
arcity-5.623
Hardware-4.629
 Cage-4.521
Drive-4.481
τ-4.449
Token,
Token ID11
Feature activation-1.12e+00

Pos logit contributions
anka+0.717
plom+0.693
agen+0.682
 glitter+0.675
 interpol+0.652
Neg logit contributions
arcity-0.856
 Cage-0.708
Hardware-0.703
 Sisters-0.686
τ-0.676
Token environment
Token ID2858
Feature activation-5.20e-01

Pos logit contributions
 glitter+4.444
anka+4.384
plom+4.281
 mer+4.237
 interpol+4.223
Neg logit contributions
arcity-5.863
Hardware-4.847
 Cage-4.720
Drive-4.702
τ-4.654
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
anka+2.107
plom+2.027
agen+2.014
 glitter+1.982
 interpol+1.917
Neg logit contributions
arcity-2.807
 Cage-2.317
Hardware-2.314
 Sisters-2.242
τ-2.231
Token oceans
Token ID23744
Feature activation-5.41e-01

Pos logit contributions
 glitter+4.345
anka+4.316
plom+4.208
 mer+4.136
 interpol+4.125
Neg logit contributions
arcity-5.721
Hardware-4.745
Drive-4.601
 Cage-4.601
τ-4.539
Token-
Token ID12
Feature activation-5.27e-01

Pos logit contributions
anka+2.166
plom+2.096
agen+2.045
 glitter+2.032
 interpol+1.950
Neg logit contributions
arcity-2.939
 Cage-2.459
Hardware-2.435
 Sisters-2.388
τ-2.344
Tokenand
Token ID392
Feature activation-2.44e-01

Pos logit contributions
anka+2.233
plom+2.174
agen+2.120
 glitter+2.079
 interpol+1.994
Neg logit contributions
arcity-2.737
Hardware-2.291
 Cage-2.288
 Sisters-2.231
τ-2.157
Token-
Token ID12
Feature activation-6.27e-02

Pos logit contributions
anka+0.897
plom+0.864
agen+0.845
 glitter+0.833
 interpol+0.797
Neg logit contributions
arcity-1.405
 Cage-1.194
Hardware-1.187
 Sisters-1.157
τ-1.148
Tokenree
Token ID631
Feature activation-1.51e-01

Pos logit contributions
anka+0.191
plom+0.182
agen+0.175
 glitter+0.171
 interpol+0.160
Neg logit contributions
arcity-0.403
 Cage-0.350
Hardware-0.350
 Sisters-0.342
τ-0.335
Tokenfs
Token ID9501
Feature activation-1.10e-02

Pos logit contributions
anka+1.024
plom+1.011
agen+0.997
 glitter+0.975
 interpol+0.948
Neg logit contributions
arcity-0.412
 Cage-0.274
Hardware-0.267
 Sisters-0.267
τ-0.241
Token,
Token ID11
Feature activation-1.06e+00

Pos logit contributions
anka+0.050
plom+0.049
 glitter+0.048
agen+0.048
 interpol+0.046
Neg logit contributions
arcity-0.054
 Cage-0.044
Hardware-0.043
 Sisters-0.042
τ-0.042
Token water
Token ID1660
Feature activation-2.57e-01

Pos logit contributions
anka+3.965
 glitter+3.960
plom+3.894
 mer+3.776
 interpol+3.761
Neg logit contributions
arcity-5.844
Hardware-4.889
 Cage-4.749
Drive-4.735
τ-4.672
Token-
Token ID12
Feature activation-3.80e-01

Pos logit contributions
anka+1.051
plom+1.013
agen+1.004
 glitter+0.988
 interpol+0.955
Neg logit contributions
arcity-1.360
 Cage-1.158
Hardware-1.139
 Sisters-1.107
τ-1.093
Tokenpoll
Token ID30393
Feature activation-4.07e-01

Pos logit contributions
anka+1.452
agen+1.423
plom+1.419
 glitter+1.366
 interpol+1.316
Neg logit contributions
arcity-2.087
 Cage-1.768
Hardware-1.749
 Sisters-1.749
τ-1.681
Tokenution
Token ID1009
Feature activation-2.06e-01

Pos logit contributions
anka+0.966
agen+0.919
plom+0.859
 glitter+0.782
 interpol+0.739
Neg logit contributions
arcity-2.834
Hardware-2.589
 Cage-2.543
τ-2.521
 Sisters-2.519
Token,
Token ID11
Feature activation-9.98e-01

Pos logit contributions
anka+0.944
plom+0.918
agen+0.893
 glitter+0.893
 interpol+0.861
Neg logit contributions
arcity-1.005
 Cage-0.822
Hardware-0.808
 Sisters-0.791
τ-0.773
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
anka+2.567
plom+2.510
agen+2.442
 glitter+2.425
 interpol+2.328
Neg logit contributions
arcity-3.130
 Cage-2.578
Hardware-2.544
 Sisters-2.499
τ-2.448
Token community
Token ID2055
Feature activation-8.52e-01

Pos logit contributions
anka+4.382
 glitter+4.286
 mer+4.105
plom+4.045
agen+4.034
Neg logit contributions
arcity-6.278
 Cage-5.242
Hardware-5.219
Drive-5.083
τ-4.999
Token-
Token ID12
Feature activation-5.51e-01

Pos logit contributions
anka+2.832
plom+2.696
agen+2.652
 glitter+2.633
 interpol+2.541
Neg logit contributions
arcity-5.248
 Cage-4.414
Hardware-4.394
τ-4.299
 Sisters-4.289
Tokenorgan
Token ID9971
Feature activation-3.89e-01

Pos logit contributions
anka+2.295
plom+2.260
agen+2.191
 glitter+2.163
 interpol+2.066
Neg logit contributions
arcity-2.921
 Cage-2.446
Hardware-2.363
 Sisters-2.343
Drive-2.281
Tokenisations
Token ID38189
Feature activation-2.72e-01

Pos logit contributions
anka+1.550
plom+1.484
agen+1.477
 glitter+1.475
 interpol+1.404
Neg logit contributions
arcity-2.128
 Cage-1.773
Hardware-1.759
 Sisters-1.715
τ-1.693
Token,
Token ID11
Feature activation-1.06e+00

Pos logit contributions
anka+1.143
plom+1.111
agen+1.086
 glitter+1.075
 interpol+1.034
Neg logit contributions
arcity-1.429
 Cage-1.184
Hardware-1.175
 Sisters-1.149
τ-1.128
Token electricity
Token ID8744
Feature activation-2.91e-01

Pos logit contributions
anka+3.989
 glitter+3.921
 mer+3.747
plom+3.704
agen+3.667
Neg logit contributions
arcity-5.944
 Cage-4.950
Hardware-4.912
Drive-4.796
τ-4.734
Token-
Token ID12
Feature activation-1.58e-01

Pos logit contributions
anka+1.103
plom+1.057
agen+1.046
 glitter+1.027
 interpol+0.983
Neg logit contributions
arcity-1.645
 Cage-1.391
Hardware-1.375
 Sisters-1.352
τ-1.324
Tokenenergy
Token ID22554
Feature activation-3.14e-01

Pos logit contributions
anka+0.808
agen+0.787
plom+0.781
 glitter+0.770
 interpol+0.742
Neg logit contributions
arcity-0.674
 Cage-0.544
 Sisters-0.529
Hardware-0.526
τ-0.498
Token-
Token ID12
Feature activation-2.00e-02

Pos logit contributions
anka+1.178
plom+1.124
agen+1.121
 glitter+1.092
 interpol+1.060
Neg logit contributions
arcity-1.786
 Cage-1.521
Hardware-1.492
 Sisters-1.472
τ-1.456
Tokenand
Token ID392
Feature activation-1.56e-01

Pos logit contributions
anka+0.087
plom+0.084
agen+0.084
 glitter+0.082
 interpol+0.079
Neg logit contributions
arcity-0.101
 Cage-0.085
Hardware-0.083
 Sisters-0.082
τ-0.080
Token-
Token ID12
Feature activation-5.23e-01

Pos logit contributions
anka+3.030
plom+2.911
agen+2.896
 glitter+2.794
 interpol+2.689
Neg logit contributions
arcity-4.139
 Cage-3.480
Hardware-3.444
 Sisters-3.337
τ-3.306
Tokenc
Token ID66
Feature activation-2.40e-01

Pos logit contributions
anka+2.180
plom+2.135
agen+2.128
 glitter+2.048
 interpol+1.962
Neg logit contributions
arcity-2.724
 Cage-2.251
 Sisters-2.236
Hardware-2.212
τ-2.149
Tokenattle
Token ID1999
Feature activation-4.64e-01

Pos logit contributions
anka+0.962
plom+0.935
agen+0.932
 glitter+0.858
 interpol+0.834
Neg logit contributions
arcity-1.282
 Cage-1.108
Hardware-1.107
 Sisters-1.081
τ-1.068
Token,
Token ID11
Feature activation-1.11e+00

Pos logit contributions
anka+1.957
plom+1.898
agen+1.866
 glitter+1.804
 interpol+1.753
Neg logit contributions
arcity-2.422
 Cage-2.010
Hardware-1.996
 Sisters-1.964
τ-1.937
Token rural
Token ID10016
Feature activation-5.87e-01

Pos logit contributions
anka+4.936
 glitter+4.848
plom+4.743
agen+4.684
 mer+4.667
Neg logit contributions
arcity-5.365
Hardware-4.257
 Cage-4.205
τ-4.179
Drive-4.162
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
anka+2.337
plom+2.257
agen+2.209
 glitter+2.180
 interpol+2.094
Neg logit contributions
arcity-3.211
 Cage-2.678
Hardware-2.660
 Sisters-2.605
τ-2.566
Token business
Token ID1597
Feature activation-4.69e-01

Pos logit contributions
anka+4.108
 glitter+4.028
plom+3.925
agen+3.852
 diplomacy+3.839
Neg logit contributions
arcity-5.397
Hardware-4.398
 Cage-4.329
Drive-4.289
τ-4.283
Token-
Token ID12
Feature activation-5.64e-01

Pos logit contributions
anka+1.782
plom+1.701
agen+1.661
 glitter+1.634
 interpol+1.573
Neg logit contributions
arcity-2.692
 Cage-2.269
Hardware-2.243
 Sisters-2.192
τ-2.154
Tokeneconom
Token ID13926
Feature activation-5.45e-01

Pos logit contributions
plom+1.600
anka+1.586
agen+1.557
 glitter+1.468
 interpol+1.368
Neg logit contributions
arcity-3.758
 Cage-3.241
 Sisters-3.184
Hardware-3.139
Drive-3.059
Tokenics
Token ID873
Feature activation-6.84e-01

Pos logit contributions
anka+2.438
plom+2.375
agen+2.361
 glitter+2.284
 interpol+2.195
Neg logit contributions
arcity-2.730
Hardware-2.215
 Cage-2.211
 Sisters-2.159
τ-2.126
Token-
Token ID12
Feature activation-4.24e-01

Pos logit contributions
anka+2.322
agen+2.254
plom+2.236
 glitter+2.147
 interpol+2.043
Neg logit contributions
arcity-4.134
 Cage-3.473
Hardware-3.452
 Sisters-3.355
τ-3.347
Token,
Token ID11
Feature activation-1.06e+00

Pos logit contributions
anka+0.050
plom+0.049
 glitter+0.048
agen+0.048
 interpol+0.046
Neg logit contributions
arcity-0.054
 Cage-0.044
Hardware-0.043
 Sisters-0.042
τ-0.042
Token water
Token ID1660
Feature activation-2.57e-01

Pos logit contributions
anka+3.965
 glitter+3.960
plom+3.894
 mer+3.776
 interpol+3.761
Neg logit contributions
arcity-5.844
Hardware-4.889
 Cage-4.749
Drive-4.735
τ-4.672
Token-
Token ID12
Feature activation-3.80e-01

Pos logit contributions
anka+1.051
plom+1.013
agen+1.004
 glitter+0.988
 interpol+0.955
Neg logit contributions
arcity-1.360
 Cage-1.158
Hardware-1.139
 Sisters-1.107
τ-1.093
Tokenpoll
Token ID30393
Feature activation-4.07e-01

Pos logit contributions
anka+1.452
agen+1.423
plom+1.419
 glitter+1.366
 interpol+1.316
Neg logit contributions
arcity-2.087
 Cage-1.768
Hardware-1.749
 Sisters-1.749
τ-1.681
Tokenution
Token ID1009
Feature activation-2.06e-01

Pos logit contributions
anka+0.966
agen+0.919
plom+0.859
 glitter+0.782
 interpol+0.739
Neg logit contributions
arcity-2.834
Hardware-2.589
 Cage-2.543
τ-2.521
 Sisters-2.519
Token,
Token ID11
Feature activation-9.98e-01

Pos logit contributions
anka+0.944
plom+0.918
agen+0.893
 glitter+0.893
 interpol+0.861
Neg logit contributions
arcity-1.005
 Cage-0.822
Hardware-0.808
 Sisters-0.791
τ-0.773
Token environmental
Token ID6142
Feature activation-1.27e-01

Pos logit contributions
anka+3.781
 glitter+3.771
plom+3.692
 mer+3.581
 interpol+3.572
Neg logit contributions
arcity-5.452
Hardware-4.558
 Cage-4.438
Drive-4.392
τ-4.363
Token-
Token ID12
Feature activation-3.05e-01

Pos logit contributions
anka+0.512
plom+0.498
 glitter+0.482
agen+0.477
 interpol+0.461
Neg logit contributions
arcity-0.683
 Cage-0.567
Hardware-0.561
 Sisters-0.553
τ-0.540
Tokenimpact
Token ID48240
Feature activation-1.77e-01

Pos logit contributions
anka+1.279
plom+1.245
agen+1.219
 glitter+1.192
 interpol+1.155
Neg logit contributions
arcity-1.611
 Cage-1.348
Hardware-1.318
 Sisters-1.298
Drive-1.268
Token,
Token ID11
Feature activation-9.66e-01

Pos logit contributions
anka+0.821
plom+0.800
 glitter+0.781
agen+0.778
 interpol+0.753
Neg logit contributions
arcity-0.855
 Cage-0.699
Hardware-0.684
 Sisters-0.672
τ-0.658
Token environmental
Token ID6142
Feature activation-2.67e-01

Pos logit contributions
anka+3.653
 glitter+3.636
plom+3.565
 interpol+3.449
 mer+3.449
Neg logit contributions
arcity-5.300
Hardware-4.434
 Cage-4.329
Drive-4.266
τ-4.231
TokenS
Token ID50
Feature activation+2.67e-01

Pos logit contributions
anka+0.939
plom+0.912
agen+0.903
 glitter+0.893
 interpol+0.869
Neg logit contributions
arcity-0.864
 Cage-0.683
Hardware-0.672
 Sisters-0.654
τ-0.635
Token+
Token ID10
Feature activation+1.84e-01

Pos logit contributions
arcity+1.573
 Cage+1.338
Hardware+1.326
 Sisters+1.301
τ+1.282
Neg logit contributions
anka-0.950
plom-0.917
agen-0.887
 glitter-0.882
 interpol-0.842
Token\
Token ID59
Feature activation-3.31e-01

Pos logit contributions
arcity+0.848
 Cage+0.683
Hardware+0.673
 Sisters+0.658
τ+0.641
Neg logit contributions
anka-0.892
plom-0.868
agen-0.851
 glitter-0.846
 interpol-0.820
Tokens
Token ID82
Feature activation-9.28e-02

Pos logit contributions
anka+1.658
plom+1.609
agen+1.599
 glitter+1.580
 interpol+1.539
Neg logit contributions
arcity-1.478
 Cage-1.151
Hardware-1.141
 Sisters-1.103
τ-1.071
Token+
Token ID10
Feature activation+9.36e-02

Pos logit contributions
anka+0.321
plom+0.309
agen+0.302
 glitter+0.299
 interpol+0.285
Neg logit contributions
arcity-0.557
 Cage-0.472
Hardware-0.468
 Sisters-0.460
τ-0.452
Token"(
Token ID18109
Feature activation-9.98e-01

Pos logit contributions
arcity+0.473
 Cage+0.389
Hardware+0.384
 Sisters+0.376
τ+0.367
Neg logit contributions
anka-0.413
plom-0.400
agen-0.392
 glitter-0.390
 interpol-0.376
Token\
Token ID59
Feature activation-2.49e-01

Pos logit contributions
anka+4.673
agen+4.517
plom+4.491
 glitter+4.407
 interpol+4.283
Neg logit contributions
arcity-4.643
 Cage-3.661
Hardware-3.565
 Sisters-3.548
 RI-3.391
TokenS
Token ID50
Feature activation+1.93e-01

Pos logit contributions
anka+1.264
plom+1.228
agen+1.219
 glitter+1.206
 interpol+1.173
Neg logit contributions
arcity-1.097
 Cage-0.845
Hardware-0.830
 Sisters-0.810
τ-0.785
Token+)
Token ID28988
Feature activation-1.72e-01

Pos logit contributions
arcity+1.125
 Cage+0.957
Hardware+0.948
 Sisters+0.929
τ+0.915
Neg logit contributions
anka-0.697
plom-0.674
agen-0.651
 glitter-0.649
 interpol-0.621
Token"]
Token ID8973
Feature activation-5.86e-01

Pos logit contributions
anka+0.764
plom+0.737
agen+0.727
 glitter+0.721
 interpol+0.699
Neg logit contributions
arcity-0.868
 Cage-0.707
Hardware-0.699
 Sisters-0.682
τ-0.666
Token'
Token ID6
Feature activation-4.43e-01

Pos logit contributions
anka+2.361
plom+2.275
agen+2.226
 glitter+2.214
 interpol+2.141
Neg logit contributions
arcity-3.181
 Cage-2.629
Hardware-2.595
 Sisters-2.561
τ-2.493
Tokenimpact
Token ID48240
Feature activation-1.77e-01

Pos logit contributions
anka+1.279
plom+1.245
agen+1.219
 glitter+1.192
 interpol+1.155
Neg logit contributions
arcity-1.611
 Cage-1.348
Hardware-1.318
 Sisters-1.298
Drive-1.268
Token,
Token ID11
Feature activation-9.66e-01

Pos logit contributions
anka+0.821
plom+0.800
 glitter+0.781
agen+0.778
 interpol+0.753
Neg logit contributions
arcity-0.855
 Cage-0.699
Hardware-0.684
 Sisters-0.672
τ-0.658
Token environmental
Token ID6142
Feature activation-2.67e-01

Pos logit contributions
anka+3.653
 glitter+3.636
plom+3.565
 interpol+3.449
 mer+3.449
Neg logit contributions
arcity-5.300
Hardware-4.434
 Cage-4.329
Drive-4.266
τ-4.231
Token-
Token ID12
Feature activation-2.23e-01

Pos logit contributions
anka+1.039
plom+1.007
agen+0.977
 glitter+0.974
 interpol+0.934
Neg logit contributions
arcity-1.479
 Cage-1.240
Hardware-1.228
 Sisters-1.205
τ-1.183
Tokenmanagement
Token ID27604
Feature activation-1.46e-01

Pos logit contributions
anka+0.963
plom+0.934
agen+0.912
 glitter+0.898
 interpol+0.868
Neg logit contributions
arcity-1.159
 Cage-0.959
Hardware-0.945
 Sisters-0.925
τ-0.903
Token,
Token ID11
Feature activation-9.85e-01

Pos logit contributions
anka+0.626
plom+0.607
agen+0.595
 glitter+0.586
 interpol+0.566
Neg logit contributions
arcity-0.754
 Cage-0.624
Hardware-0.617
 Sisters-0.603
τ-0.592
Token environmental
Token ID6142
Feature activation-2.19e-01

Pos logit contributions
anka+3.679
 glitter+3.654
plom+3.584
 mer+3.467
 interpol+3.463
Neg logit contributions
arcity-5.438
Hardware-4.564
 Cage-4.451
Drive-4.401
τ-4.364
Token-
Token ID12
Feature activation-1.62e-01

Pos logit contributions
anka+0.867
plom+0.843
 glitter+0.816
agen+0.813
 interpol+0.782
Neg logit contributions
arcity-1.201
 Cage-1.001
Hardware-0.991
 Sisters-0.975
τ-0.955
Tokentechnology
Token ID45503
Feature activation-4.99e-01

Pos logit contributions
anka+0.700
plom+0.681
agen+0.665
 glitter+0.654
 interpol+0.633
Neg logit contributions
arcity-0.841
 Cage-0.695
Hardware-0.685
 Sisters-0.670
τ-0.655
Token,
Token ID11
Feature activation-9.38e-01

Pos logit contributions
anka+2.152
plom+2.088
agen+2.045
 glitter+2.025
 interpol+1.952
Neg logit contributions
arcity-2.566
 Cage-2.109
Hardware-2.087
 Sisters-2.037
τ-2.001
Token q
Token ID10662
Feature activation-6.88e-01

Pos logit contributions
anka+3.481
 glitter+3.449
plom+3.394
 mer+3.268
 interpol+3.267
Neg logit contributions
arcity-5.233
Hardware-4.375
 Cage-4.286
Drive-4.225
τ-4.195
Tokenution
Token ID1009
Feature activation-2.06e-01

Pos logit contributions
anka+0.966
agen+0.919
plom+0.859
 glitter+0.782
 interpol+0.739
Neg logit contributions
arcity-2.834
Hardware-2.589
 Cage-2.543
τ-2.521
 Sisters-2.519
Token,
Token ID11
Feature activation-9.98e-01

Pos logit contributions
anka+0.944
plom+0.918
agen+0.893
 glitter+0.893
 interpol+0.861
Neg logit contributions
arcity-1.005
 Cage-0.822
Hardware-0.808
 Sisters-0.791
τ-0.773
Token environmental
Token ID6142
Feature activation-1.27e-01

Pos logit contributions
anka+3.781
 glitter+3.771
plom+3.692
 mer+3.581
 interpol+3.572
Neg logit contributions
arcity-5.452
Hardware-4.558
 Cage-4.438
Drive-4.392
τ-4.363
Token-
Token ID12
Feature activation-3.05e-01

Pos logit contributions
anka+0.512
plom+0.498
 glitter+0.482
agen+0.477
 interpol+0.461
Neg logit contributions
arcity-0.683
 Cage-0.567
Hardware-0.561
 Sisters-0.553
τ-0.540
Tokenimpact
Token ID48240
Feature activation-1.77e-01

Pos logit contributions
anka+1.279
plom+1.245
agen+1.219
 glitter+1.192
 interpol+1.155
Neg logit contributions
arcity-1.611
 Cage-1.348
Hardware-1.318
 Sisters-1.298
Drive-1.268
Token,
Token ID11
Feature activation-9.66e-01

Pos logit contributions
anka+0.821
plom+0.800
 glitter+0.781
agen+0.778
 interpol+0.753
Neg logit contributions
arcity-0.855
 Cage-0.699
Hardware-0.684
 Sisters-0.672
τ-0.658
Token environmental
Token ID6142
Feature activation-2.67e-01

Pos logit contributions
anka+3.653
 glitter+3.636
plom+3.565
 interpol+3.449
 mer+3.449
Neg logit contributions
arcity-5.300
Hardware-4.434
 Cage-4.329
Drive-4.266
τ-4.231
Token-
Token ID12
Feature activation-2.23e-01

Pos logit contributions
anka+1.039
plom+1.007
agen+0.977
 glitter+0.974
 interpol+0.934
Neg logit contributions
arcity-1.479
 Cage-1.240
Hardware-1.228
 Sisters-1.205
τ-1.183
Tokenmanagement
Token ID27604
Feature activation-1.46e-01

Pos logit contributions
anka+0.963
plom+0.934
agen+0.912
 glitter+0.898
 interpol+0.868
Neg logit contributions
arcity-1.159
 Cage-0.959
Hardware-0.945
 Sisters-0.925
τ-0.903
Token,
Token ID11
Feature activation-9.85e-01

Pos logit contributions
anka+0.626
plom+0.607
agen+0.595
 glitter+0.586
 interpol+0.566
Neg logit contributions
arcity-0.754
 Cage-0.624
Hardware-0.617
 Sisters-0.603
τ-0.592
Token environmental
Token ID6142
Feature activation-2.19e-01

Pos logit contributions
anka+3.679
 glitter+3.654
plom+3.584
 mer+3.467
 interpol+3.463
Neg logit contributions
arcity-5.438
Hardware-4.564
 Cage-4.451
Drive-4.401
τ-4.364
Tokenale
Token ID1000
Feature activation-1.34e-01

Pos logit contributions
anka+0.201
plom+0.190
agen+0.187
 glitter+0.180
 interpol+0.169
Neg logit contributions
arcity-0.462
 Cage-0.403
Hardware-0.401
 Sisters-0.395
τ-0.390
Token wil
Token ID39716
Feature activation+1.22e-01

Pos logit contributions
anka+0.515
plom+0.502
 glitter+0.490
agen+0.488
 interpol+0.466
Neg logit contributions
arcity-0.756
 Cage-0.631
Hardware-0.629
 Sisters-0.612
Drive-0.605
Tokenkins
Token ID5331
Feature activation+1.05e-01

Pos logit contributions
arcity+0.588
 Cage+0.482
Hardware+0.477
 Sisters+0.461
τ+0.453
Neg logit contributions
anka-0.574
plom-0.556
agen-0.546
 glitter-0.539
 interpol-0.520
Tokeni
Token ID72
Feature activation-8.73e-02

Pos logit contributions
arcity+0.494
 Cage+0.399
Hardware+0.397
 Sisters+0.383
Drive+0.375
Neg logit contributions
anka-0.503
plom-0.487
agen-0.478
 glitter-0.474
 interpol-0.458
Token),
Token ID828
Feature activation-2.82e-01

Pos logit contributions
anka+0.451
plom+0.441
agen+0.434
 glitter+0.426
 interpol+0.411
Neg logit contributions
arcity-0.379
Hardware-0.300
 Cage-0.299
 Sisters-0.287
Drive-0.281
Token after
Token ID706
Feature activation-9.65e-01

Pos logit contributions
anka+1.041
plom+0.995
agen+0.981
 glitter+0.975
 interpol+0.936
Neg logit contributions
arcity-1.632
Hardware-1.367
 Cage-1.367
 Sisters-1.325
Drive-1.309
Token Australian
Token ID6638
Feature activation+1.40e-01

Pos logit contributions
anka+3.962
 glitter+3.868
agen+3.816
plom+3.774
 mer+3.663
Neg logit contributions
arcity-4.922
Hardware-4.129
 Cage-3.912
Drive-3.857
τ-3.850
Token explorer
Token ID39349
Feature activation+5.54e-02

Pos logit contributions
arcity+0.814
 Cage+0.681
Hardware+0.679
 Sisters+0.662
τ+0.656
Neg logit contributions
anka-0.518
plom-0.499
 glitter-0.490
agen-0.490
 interpol-0.468
Token,
Token ID11
Feature activation+6.72e-02

Pos logit contributions
arcity+0.265
Hardware+0.212
 Cage+0.210
 Sisters+0.202
τ+0.202
Neg logit contributions
anka-0.261
plom-0.253
agen-0.250
 glitter-0.248
 interpol-0.240
Token natural
Token ID3288
Feature activation+6.68e-02

Pos logit contributions
arcity+0.350
Hardware+0.287
 Cage+0.285
 Sisters+0.276
τ+0.273
Neg logit contributions
anka-0.286
plom-0.278
 glitter-0.273
agen-0.272
 interpol-0.262
Tokenist
Token ID396
Feature activation+1.12e-01

Pos logit contributions
arcity+0.334
 Cage+0.274
Hardware+0.272
 Sisters+0.265
τ+0.260
Neg logit contributions
anka-0.297
plom-0.288
agen-0.285
 glitter-0.282
 interpol-0.273
Token 366
Token ID44856
Feature activation+3.84e-01

Pos logit contributions
anka+0.024
plom+0.023
agen+0.023
 glitter+0.023
 interpol+0.022
Neg logit contributions
arcity-0.025
 Cage-0.020
Hardware-0.020
 Sisters-0.019
τ-0.019
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
arcity+1.958
 Cage+1.630
Hardware+1.607
 Sisters+1.576
τ+1.549
Neg logit contributions
anka-1.660
plom-1.610
agen-1.572
 glitter-1.560
 interpol-1.503
Token
Token ID198
Feature activation+9.90e-02

Pos logit contributions
arcity+0.547
 Cage+0.436
Hardware+0.430
 Sisters+0.419
τ+0.409
Neg logit contributions
anka-0.637
plom-0.621
agen-0.608
 glitter-0.606
 interpol-0.587
Token
Token ID198
Feature activation+1.09e-01

Pos logit contributions
arcity+0.435
 Cage+0.338
Hardware+0.333
 Sisters+0.324
τ+0.318
Neg logit contributions
anka-0.507
plom-0.492
agen-0.486
 glitter-0.482
 interpol-0.468
TokenTopics
Token ID25902
Feature activation+6.90e-01

Pos logit contributions
arcity+0.346
 Cage+0.248
Hardware+0.236
 Sisters+0.231
 RI+0.221
Neg logit contributions
anka-0.687
plom-0.671
agen-0.662
 glitter-0.654
 interpol-0.637
Token:
Token ID25
Feature activation-9.57e-01

Pos logit contributions
arcity+2.675
 Cage+2.103
Hardware+2.063
 Sisters+2.014
τ+1.933
Neg logit contributions
anka-3.783
plom-3.715
agen-3.627
 glitter-3.615
 interpol-3.523
Token community
Token ID2055
Feature activation-8.43e-01

Pos logit contributions
anka+3.693
 glitter+3.657
agen+3.460
plom+3.455
 mer+3.446
Neg logit contributions
arcity-5.211
 Cage-4.367
Hardware-4.308
Drive-4.164
τ-4.151
Token-
Token ID12
Feature activation-6.60e-01

Pos logit contributions
anka+2.732
plom+2.570
agen+2.537
 glitter+2.535
 interpol+2.445
Neg logit contributions
arcity-5.279
Hardware-4.430
 Cage-4.424
τ-4.307
 Sisters-4.291
Tokenand
Token ID392
Feature activation-4.74e-01

Pos logit contributions
anka+2.595
plom+2.586
agen+2.488
 glitter+2.435
 interpol+2.332
Neg logit contributions
arcity-3.650
 Cage-3.071
Hardware-2.978
 Sisters-2.893
Drive-2.849
Token-
Token ID12
Feature activation-8.24e-02

Pos logit contributions
anka+1.645
plom+1.584
agen+1.548
 glitter+1.529
 interpol+1.468
Neg logit contributions
arcity-2.827
 Cage-2.390
Hardware-2.380
τ-2.305
 Sisters-2.304
Tokensoc
Token ID35634
Feature activation-2.03e-01

Pos logit contributions
anka+0.429
plom+0.420
agen+0.413
 glitter+0.407
 interpol+0.395
Neg logit contributions
arcity-0.351
 Cage-0.276
Hardware-0.274
 Sisters-0.264
τ-0.256
Token-
Token ID12
Feature activation-2.00e-02

Pos logit contributions
anka+1.178
plom+1.124
agen+1.121
 glitter+1.092
 interpol+1.060
Neg logit contributions
arcity-1.786
 Cage-1.521
Hardware-1.492
 Sisters-1.472
τ-1.456
Tokenand
Token ID392
Feature activation-1.56e-01

Pos logit contributions
anka+0.087
plom+0.084
agen+0.084
 glitter+0.082
 interpol+0.079
Neg logit contributions
arcity-0.101
 Cage-0.085
Hardware-0.083
 Sisters-0.082
τ-0.080
Token-
Token ID12
Feature activation+2.31e-01

Pos logit contributions
anka+0.573
plom+0.550
agen+0.542
 glitter+0.534
 interpol+0.512
Neg logit contributions
arcity-0.898
 Cage-0.763
Hardware-0.753
 Sisters-0.744
τ-0.732
Tokenut
Token ID315
Feature activation+1.69e-01

Pos logit contributions
arcity+0.800
 Cage+0.600
Hardware+0.589
 Sisters+0.576
τ+0.548
Neg logit contributions
anka-1.387
plom-1.352
agen-1.336
 glitter-1.325
 interpol-1.288
Tokenilities
Token ID2410
Feature activation-4.14e-01

Pos logit contributions
arcity+0.831
 Cage+0.680
Hardware+0.672
 Sisters+0.656
τ+0.643
Neg logit contributions
anka-0.763
plom-0.742
agen-0.723
 glitter-0.722
 interpol-0.696
Token,
Token ID11
Feature activation-9.39e-01

Pos logit contributions
anka+1.692
plom+1.624
agen+1.609
 glitter+1.569
 interpol+1.511
Neg logit contributions
arcity-2.244
 Cage-1.842
Hardware-1.824
 Sisters-1.778
τ-1.763
Token family
Token ID1641
Feature activation-3.10e-01

Pos logit contributions
anka+3.443
 glitter+3.368
plom+3.217
 mer+3.196
agen+3.168
Neg logit contributions
arcity-5.354
 Cage-4.478
Hardware-4.447
Drive-4.340
τ-4.299
Token-
Token ID12
Feature activation-1.19e-01

Pos logit contributions
anka+1.185
plom+1.131
agen+1.117
 glitter+1.096
 interpol+1.054
Neg logit contributions
arcity-1.757
 Cage-1.480
Hardware-1.469
 Sisters-1.436
τ-1.408
Tokenand
Token ID392
Feature activation-2.29e-01

Pos logit contributions
anka+0.498
plom+0.482
agen+0.477
 glitter+0.469
 interpol+0.448
Neg logit contributions
arcity-0.636
 Cage-0.531
Hardware-0.521
 Sisters-0.510
Drive-0.492
Token-
Token ID12
Feature activation+3.48e-01

Pos logit contributions
anka+0.826
plom+0.795
agen+0.777
 glitter+0.769
 interpol+0.736
Neg logit contributions
arcity-1.338
 Cage-1.132
Hardware-1.127
τ-1.091
 Sisters-1.087
Tokenchildren
Token ID17197
Feature activation-2.06e-02

Pos logit contributions
arcity+1.350
 Cage+1.047
Hardware+1.034
 Sisters+1.007
τ+0.984
Neg logit contributions
anka-1.928
plom-1.887
agen-1.839
 glitter-1.837
 interpol-1.801
Tokenmanagement
Token ID27604
Feature activation-1.46e-01

Pos logit contributions
anka+0.963
plom+0.934
agen+0.912
 glitter+0.898
 interpol+0.868
Neg logit contributions
arcity-1.159
 Cage-0.959
Hardware-0.945
 Sisters-0.925
τ-0.903
Token,
Token ID11
Feature activation-9.85e-01

Pos logit contributions
anka+0.626
plom+0.607
agen+0.595
 glitter+0.586
 interpol+0.566
Neg logit contributions
arcity-0.754
 Cage-0.624
Hardware-0.617
 Sisters-0.603
τ-0.592
Token environmental
Token ID6142
Feature activation-2.19e-01

Pos logit contributions
anka+3.679
 glitter+3.654
plom+3.584
 mer+3.467
 interpol+3.463
Neg logit contributions
arcity-5.438
Hardware-4.564
 Cage-4.451
Drive-4.401
τ-4.364
Token-
Token ID12
Feature activation-1.62e-01

Pos logit contributions
anka+0.867
plom+0.843
 glitter+0.816
agen+0.813
 interpol+0.782
Neg logit contributions
arcity-1.201
 Cage-1.001
Hardware-0.991
 Sisters-0.975
τ-0.955
Tokentechnology
Token ID45503
Feature activation-4.99e-01

Pos logit contributions
anka+0.700
plom+0.681
agen+0.665
 glitter+0.654
 interpol+0.633
Neg logit contributions
arcity-0.841
 Cage-0.695
Hardware-0.685
 Sisters-0.670
τ-0.655
Token,
Token ID11
Feature activation-9.38e-01

Pos logit contributions
anka+2.152
plom+2.088
agen+2.045
 glitter+2.025
 interpol+1.952
Neg logit contributions
arcity-2.566
 Cage-2.109
Hardware-2.087
 Sisters-2.037
τ-2.001
Token q
Token ID10662
Feature activation-6.88e-01

Pos logit contributions
anka+3.481
 glitter+3.449
plom+3.394
 mer+3.268
 interpol+3.267
Neg logit contributions
arcity-5.233
Hardware-4.375
 Cage-4.286
Drive-4.225
τ-4.195
Tokenld
Token ID335
Feature activation-4.98e-01

Pos logit contributions
anka+2.221
agen+2.124
plom+2.106
 glitter+1.911
 interpol+1.831
Neg logit contributions
arcity-4.202
Hardware-3.776
 Cage-3.725
FACE-3.716
 Sisters-3.680
Token
Token ID198
Feature activation-4.74e-01

Pos logit contributions
anka+2.390
plom+2.328
agen+2.281
 glitter+2.260
 interpol+2.189
Neg logit contributions
arcity-2.302
 Cage-1.863
Hardware-1.839
 Sisters-1.792
τ-1.754
Token
Token ID198
Feature activation-1.44e-01

Pos logit contributions
anka+2.196
plom+2.112
agen+2.097
 glitter+2.072
 interpol+2.014
Neg logit contributions
arcity-2.329
 Cage-1.785
 conduc-1.770
Hardware-1.745
 Sisters-1.722
TokenFirst
Token ID5962
Feature activation+2.10e-01

Pos logit contributions
anka+0.664
plom+0.647
agen+0.631
 glitter+0.622
 interpol+0.599
Neg logit contributions
arcity-0.700
 Cage-0.566
Hardware-0.553
 Sisters-0.546
 RI-0.533
Token them
Token ID606
Feature activation+1.42e-01

Pos logit contributions
arcity+1.296
Hardware+1.076
 Cage+1.064
 Sisters+1.037
τ+1.030
Neg logit contributions
anka-0.953
plom-0.915
 glitter-0.913
agen-0.897
 interpol-0.870
Token".
Token ID1911
Feature activation+1.26e-01

Pos logit contributions
arcity+0.750
 Cage+0.621
Hardware+0.618
 Sisters+0.603
τ+0.593
Neg logit contributions
anka-0.595
plom-0.577
agen-0.563
 glitter-0.561
 interpol-0.540
Token
Token ID198
Feature activation+2.04e-01

Pos logit contributions
arcity+0.535
 Cage+0.419
Hardware+0.415
 Sisters+0.403
τ+0.394
Neg logit contributions
anka-0.655
plom-0.637
agen-0.625
 glitter-0.621
 interpol-0.602
Token
Token ID198
Feature activation+1.57e-01

Pos logit contributions
arcity+0.879
 Cage+0.684
Hardware+0.675
 Sisters+0.657
τ+0.643
Neg logit contributions
anka-1.061
plom-1.031
agen-1.015
 glitter-1.009
 interpol-0.979
TokenTopics
Token ID25902
Feature activation+6.68e-01

Pos logit contributions
arcity+0.737
 Cage+0.592
Hardware+0.577
 Sisters+0.571
τ+0.552
Neg logit contributions
anka-0.758
plom-0.737
agen-0.723
 glitter-0.716
 interpol-0.691
Token:
Token ID25
Feature activation-9.30e-01

Pos logit contributions
arcity+2.615
 Cage+2.055
Hardware+2.020
 Sisters+1.968
τ+1.895
Neg logit contributions
anka-3.651
plom-3.578
agen-3.498
 glitter-3.485
 interpol-3.395
Token marine
Token ID16050
Feature activation-6.42e-01

Pos logit contributions
 glitter+3.864
anka+3.805
plom+3.715
 interpol+3.689
agen+3.676
Neg logit contributions
arcity-4.742
Hardware-3.853
 Cage-3.814
τ-3.747
Drive-3.733
Token-
Token ID12
Feature activation-5.21e-01

Pos logit contributions
anka+2.340
plom+2.265
agen+2.248
 glitter+2.195
 interpol+2.091
Neg logit contributions
arcity-3.668
 Cage-3.143
Hardware-3.089
 Sisters-3.078
τ-3.014
Tokenbiology
Token ID43592
Feature activation-7.70e-01

Pos logit contributions
anka+1.942
plom+1.898
agen+1.894
 glitter+1.802
 interpol+1.709
Neg logit contributions
arcity-2.920
 Cage-2.486
 Sisters-2.461
Hardware-2.446
Drive-2.378
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
anka+2.888
agen+2.789
plom+2.789
 glitter+2.708
 interpol+2.613
Neg logit contributions
arcity-4.353
Hardware-3.599
 Cage-3.571
 Sisters-3.496
τ-3.470
Token conservation
Token ID14903
Feature activation-1.66e-01

Pos logit contributions
 glitter+4.317
anka+4.288
plom+4.200
 interpol+4.121
 mer+4.120
Neg logit contributions
arcity-5.623
Hardware-4.629
 Cage-4.521
Drive-4.481
τ-4.449
Token with
Token ID351
Feature activation+2.70e-01

Pos logit contributions
arcity+0.978
 Cage+0.804
Hardware+0.798
 Sisters+0.777
τ+0.766
Neg logit contributions
anka-0.814
plom-0.789
agen-0.770
 glitter-0.769
 interpol-0.743
Token all
Token ID477
Feature activation+5.85e-02

Pos logit contributions
arcity+1.400
Hardware+1.145
 Cage+1.139
 Sisters+1.105
τ+1.087
Neg logit contributions
anka-1.165
plom-1.118
 glitter-1.108
agen-1.098
 interpol-1.066
Token this
Token ID428
Feature activation-1.67e-01

Pos logit contributions
arcity+0.307
Hardware+0.250
 Cage+0.248
 Sisters+0.241
τ+0.237
Neg logit contributions
anka-0.251
 glitter-0.240
plom-0.239
agen-0.238
 interpol-0.229
Token Al
Token ID978
Feature activation-3.90e-02

Pos logit contributions
anka+0.652
 glitter+0.625
plom+0.617
agen+0.611
 interpol+0.595
Neg logit contributions
arcity-0.939
Hardware-0.772
 Cage-0.766
 Sisters-0.752
τ-0.742
Token J
Token ID449
Feature activation+1.68e-01

Pos logit contributions
anka+0.169
plom+0.161
agen+0.159
 glitter+0.157
 interpol+0.151
Neg logit contributions
arcity-0.203
Hardware-0.166
 Cage-0.165
 Sisters-0.162
τ-0.159
Tokenour
Token ID454
Feature activation-9.07e-01

Pos logit contributions
arcity+0.857
 Cage+0.703
Hardware+0.703
 Sisters+0.684
τ+0.673
Neg logit contributions
anka-0.740
plom-0.711
agen-0.700
 glitter-0.690
 interpol-0.664
Tokeng
Token ID70
Feature activation-4.91e-01

Pos logit contributions
anka+3.990
plom+3.709
agen+3.675
 glitter+3.634
 interpol+3.548
Neg logit contributions
arcity-4.676
 Cage-3.739
Hardware-3.674
 Sisters-3.559
Drive-3.540
Tokenensen
Token ID18756
Feature activation+1.69e-01

Pos logit contributions
anka+2.571
agen+2.502
plom+2.491
 glitter+2.406
 mer+2.313
Neg logit contributions
arcity-2.096
Hardware-1.616
 Cage-1.601
 Sisters-1.514
τ-1.502
Token and
Token ID290
Feature activation-3.43e-03

Pos logit contributions
arcity+0.925
 Cage+0.765
Hardware+0.760
 Sisters+0.744
τ+0.731
Neg logit contributions
anka-0.678
plom-0.653
agen-0.639
 glitter-0.639
 interpol-0.614
Token Ge
Token ID2269
Feature activation+5.55e-02

Pos logit contributions
anka+0.015
 glitter+0.015
plom+0.015
agen+0.015
 interpol+0.014
Neg logit contributions
arcity-0.017
Hardware-0.014
 Cage-0.013
 Sisters-0.013
τ-0.013
Tokenza
Token ID4496
Feature activation+1.34e-02

Pos logit contributions
arcity+0.290
Hardware+0.241
 Cage+0.240
 Sisters+0.234
τ+0.229
Neg logit contributions
anka-0.236
plom-0.228
agen-0.225
 glitter-0.217
 interpol-0.209
Token groups
Token ID2628
Feature activation+9.96e-02

Pos logit contributions
arcity+0.754
 Cage+0.628
Hardware+0.625
 Sisters+0.607
τ+0.601
Neg logit contributions
anka-0.556
plom-0.541
 glitter-0.526
agen-0.525
 interpol-0.505
Token@
Token ID31
Feature activation-4.72e-01

Pos logit contributions
arcity+0.509
 Cage+0.423
Hardware+0.416
 Sisters+0.408
τ+0.399
Neg logit contributions
anka-0.433
plom-0.424
agen-0.415
 glitter-0.406
 interpol-0.389
Tokenpeace
Token ID22988
Feature activation-3.15e-01

Pos logit contributions
anka+1.625
plom+1.589
agen+1.528
 glitter+1.494
 interpol+1.401
Neg logit contributions
arcity-2.796
 Cage-2.420
Hardware-2.391
 Sisters-2.348
Drive-2.307
Tokencor
Token ID10215
Feature activation-5.57e-01

Pos logit contributions
anka+0.699
plom+0.669
agen+0.633
 glitter+0.599
 interpol+0.553
Neg logit contributions
arcity-2.262
Hardware-2.011
 Cage-2.005
 Sisters-1.975
τ-1.951
Tokenps
Token ID862
Feature activation-3.10e-01

Pos logit contributions
anka+2.240
plom+2.223
agen+2.147
 glitter+2.036
 interpol+1.980
Neg logit contributions
arcity-2.962
 Cage-2.527
Hardware-2.494
 RI-2.426
 Sisters-2.422
Tokenconnect
Token ID8443
Feature activation-8.98e-01

Pos logit contributions
anka+1.006
plom+0.973
agen+0.941
 glitter+0.913
 interpol+0.864
Neg logit contributions
arcity-1.923
 Cage-1.658
Hardware-1.641
 Sisters-1.622
 RI-1.596
Token.
Token ID13
Feature activation-4.01e-01

Pos logit contributions
anka+3.149
agen+2.966
plom+2.950
 glitter+2.770
 interpol+2.660
Neg logit contributions
arcity-5.330
 conduc-4.521
 Cage-4.465
 Sisters-4.380
Hardware-4.361
Tokenorg
Token ID2398
Feature activation-3.54e-01

Pos logit contributions
anka+1.523
agen+1.477
plom+1.469
 glitter+1.385
 interpol+1.320
Neg logit contributions
arcity-2.251
 Cage-1.884
Hardware-1.861
 Sisters-1.841
τ-1.804
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
anka+1.478
plom+1.435
agen+1.397
 glitter+1.391
 interpol+1.336
Neg logit contributions
arcity-1.867
 Cage-1.552
Hardware-1.536
 Sisters-1.505
τ-1.478
Token The
Token ID383
Feature activation+3.38e-02

Pos logit contributions
arcity+0.860
 Cage+0.729
Hardware+0.724
 Sisters+0.709
τ+0.701
Neg logit contributions
anka-0.512
plom-0.494
agen-0.479
 glitter-0.475
 interpol-0.453
Token deadline
Token ID12508
Feature activation+3.07e-01

Pos logit contributions
arcity+0.178
Hardware+0.146
 Cage+0.145
τ+0.142
 Sisters+0.139
Neg logit contributions
anka-0.141
plom-0.139
 glitter-0.137
agen-0.135
 interpol-0.130
Token safety
Token ID3747
Feature activation+2.46e-01

Pos logit contributions
anka+0.302
 glitter+0.293
plom+0.290
agen+0.285
 interpol+0.272
Neg logit contributions
arcity-0.442
 Cage-0.365
Hardware-0.363
 Sisters-0.353
τ-0.353
Token.
Token ID13
Feature activation+1.63e-01

Pos logit contributions
arcity+1.219
 Cage+1.011
Hardware+1.000
 Sisters+0.976
τ+0.956
Neg logit contributions
anka-1.092
plom-1.060
agen-1.033
 glitter-1.022
 interpol-0.991
Token It
Token ID632
Feature activation+2.24e-01

Pos logit contributions
arcity+0.823
Hardware+0.661
 Cage+0.658
 Sisters+0.637
τ+0.634
Neg logit contributions
anka-0.723
plom-0.697
agen-0.687
 glitter-0.684
 interpol-0.656
Token's
Token ID338
Feature activation-7.58e-02

Pos logit contributions
arcity+1.030
Hardware+0.826
 Cage+0.823
 Sisters+0.799
τ+0.783
Neg logit contributions
anka-1.092
plom-1.062
agen-1.044
 glitter-1.043
 interpol-1.008
Token right
Token ID826
Feature activation+1.96e-02

Pos logit contributions
anka+0.299
 glitter+0.287
plom+0.285
agen+0.281
 interpol+0.271
Neg logit contributions
arcity-0.422
Hardware-0.349
 Cage-0.346
 Sisters-0.336
τ-0.335
Token up
Token ID510
Feature activation+6.32e-01

Pos logit contributions
arcity+0.108
 Cage+0.090
Hardware+0.089
 Sisters+0.088
τ+0.086
Neg logit contributions
anka-0.078
plom-0.074
agen-0.073
 glitter-0.073
 interpol-0.070
Token there
Token ID612
Feature activation+6.85e-01

Pos logit contributions
arcity+2.942
 Cage+2.391
Hardware+2.349
 Sisters+2.305
τ+2.241
Neg logit contributions
anka-3.014
plom-2.940
agen-2.870
 glitter-2.853
 interpol-2.771
Token with
Token ID351
Feature activation+3.24e-01

Pos logit contributions
arcity+3.350
 Cage+2.810
Hardware+2.747
 Sisters+2.669
 RI+2.617
Neg logit contributions
anka-3.015
plom-2.934
agen-2.859
 glitter-2.811
 interpol-2.757
Token be
Token ID307
Feature activation+3.00e-01

Pos logit contributions
arcity+1.746
Hardware+1.440
 Cage+1.437
 Sisters+1.401
τ+1.385
Neg logit contributions
anka-1.324
plom-1.280
 glitter-1.262
agen-1.250
 interpol-1.201
Tokenavers
Token ID30400
Feature activation+2.61e-01

Pos logit contributions
arcity+1.617
 Cage+1.353
Hardware+1.337
 Sisters+1.311
τ+1.287
Neg logit contributions
anka-1.217
plom-1.180
agen-1.148
 glitter-1.142
 interpol-1.099
Token and
Token ID290
Feature activation+2.05e-01

Pos logit contributions
arcity+1.341
 Cage+1.113
Hardware+1.098
 Sisters+1.076
τ+1.055
Neg logit contributions
anka-1.126
plom-1.093
agen-1.064
 glitter-1.056
 interpol-1.021
Token was
Token ID373
Feature activation+3.02e-03

Pos logit contributions
anka+0.525
plom+0.511
agen+0.506
 glitter+0.502
 interpol+0.499
Neg logit contributions
arcity-0.644
Hardware-0.520
 Cage-0.517
 Sisters-0.505
τ-0.504
Token available
Token ID1695
Feature activation+4.25e-04

Pos logit contributions
arcity+0.016
 Cage+0.013
Hardware+0.013
 Sisters+0.013
τ+0.013
Neg logit contributions
anka-0.012
plom-0.012
agen-0.012
 glitter-0.012
 interpol-0.012
Token for
Token ID329
Feature activation+7.40e-02

Pos logit contributions
arcity+0.002
 Cage+0.002
Hardware+0.002
 Sisters+0.002
τ+0.002
Neg logit contributions
anka-0.002
plom-0.002
agen-0.002
 glitter-0.002
 interpol-0.002
Token 802
Token ID33121
Feature activation+3.11e-01

Pos logit contributions
arcity+0.382
 Cage+0.309
Hardware+0.304
τ+0.298
 Sisters+0.297
Neg logit contributions
anka-0.321
plom-0.309
agen-0.307
 glitter-0.306
 interpol-0.299
Token.
Token ID13
Feature activation+1.56e-02

Pos logit contributions
arcity+1.518
Hardware+1.259
 Cage+1.254
 Sisters+1.222
τ+1.189
Neg logit contributions
anka-1.393
plom-1.361
 glitter-1.318
agen-1.309
 interpol-1.264
Token11
Token ID1157
Feature activation+5.52e-01

Pos logit contributions
arcity+0.075
 Cage+0.061
Hardware+0.061
 Sisters+0.059
τ+0.058
Neg logit contributions
anka-0.072
plom-0.070
agen-0.069
 glitter-0.069
 interpol-0.066
Tokeng
Token ID70
Feature activation+1.58e-01

Pos logit contributions
arcity+2.959
 Cage+2.471
Hardware+2.452
 Sisters+2.403
τ+2.352
Neg logit contributions
anka-2.247
plom-2.182
agen-2.116
 glitter-2.111
 interpol-2.026
Token devices
Token ID4410
Feature activation+2.06e-01

Pos logit contributions
arcity+0.785
 Cage+0.640
Hardware+0.630
 Sisters+0.617
τ+0.604
Neg logit contributions
anka-0.716
plom-0.694
agen-0.682
 glitter-0.675
 interpol-0.656
Token.
Token ID13
Feature activation+6.13e-02

Pos logit contributions
arcity+1.133
 Cage+0.941
Hardware+0.932
 Sisters+0.914
τ+0.899
Neg logit contributions
anka-0.826
plom-0.795
agen-0.779
 glitter-0.777
 interpol-0.750
Token However
Token ID2102
Feature activation+1.32e-01

Pos logit contributions
arcity+0.297
 Cage+0.234
Hardware+0.230
 Sisters+0.225
τ+0.223
Neg logit contributions
anka-0.284
plom-0.274
agen-0.272
 glitter-0.268
 interpol-0.263
Token,
Token ID11
Feature activation+1.43e-01

Pos logit contributions
arcity+0.652
 Cage+0.535
Hardware+0.529
 Sisters+0.518
τ+0.507
Neg logit contributions
anka-0.592
plom-0.575
agen-0.562
 glitter-0.559
 interpol-0.539
Token Division
Token ID7458
Feature activation+3.89e-02

Pos logit contributions
arcity+0.548
 Cage+0.452
Hardware+0.451
 Sisters+0.438
τ+0.432
Neg logit contributions
anka-0.438
plom-0.421
agen-0.413
 glitter-0.413
 interpol-0.397
Token National
Token ID2351
Feature activation-3.84e-02

Pos logit contributions
arcity+0.184
 Cage+0.147
Hardware+0.147
 Sisters+0.141
τ+0.139
Neg logit contributions
anka-0.186
plom-0.179
 glitter-0.176
agen-0.175
 interpol-0.170
Token Forest
Token ID9115
Feature activation+3.33e-01

Pos logit contributions
anka+0.168
plom+0.159
 glitter+0.158
agen+0.158
 interpol+0.151
Neg logit contributions
arcity-0.199
Hardware-0.160
 Cage-0.159
 Sisters-0.154
τ-0.154
Token
Token ID851
Feature activation-5.16e-02

Pos logit contributions
arcity+1.725
 Cage+1.424
Hardware+1.411
 Sisters+1.379
τ+1.359
Neg logit contributions
anka-1.433
plom-1.378
agen-1.353
 glitter-1.350
 interpol-1.297
Token swap
Token ID16075
Feature activation+6.45e-01

Pos logit contributions
anka+0.217
plom+0.207
 glitter+0.206
agen+0.204
 interpol+0.197
Neg logit contributions
arcity-0.272
 Cage-0.223
Hardware-0.223
 Sisters-0.216
τ-0.214
Token the
Token ID262
Feature activation+5.74e-01

Pos logit contributions
arcity+3.330
 Cage+2.759
Hardware+2.729
 Sisters+2.672
τ+2.620
Neg logit contributions
anka-2.759
plom-2.678
agen-2.612
 glitter-2.598
 interpol-2.503
Token concrete
Token ID10017
Feature activation+1.06e-02

Pos logit contributions
arcity+3.148
 Cage+2.636
Hardware+2.611
 Sisters+2.557
τ+2.516
Neg logit contributions
anka-2.283
plom-2.208
agen-2.150
 glitter-2.141
 interpol-2.055
Token for
Token ID329
Feature activation+2.95e-01

Pos logit contributions
arcity+0.058
Hardware+0.047
 Cage+0.047
τ+0.045
 Sisters+0.045
Neg logit contributions
anka-0.044
 glitter-0.042
plom-0.042
agen-0.041
 interpol-0.040
Token trees
Token ID7150
Feature activation+1.59e-02

Pos logit contributions
arcity+1.612
Hardware+1.331
 Cage+1.325
 Sisters+1.293
τ+1.283
Neg logit contributions
anka-1.191
 glitter-1.145
plom-1.144
agen-1.117
 interpol-1.081
Token,
Token ID11
Feature activation+8.13e-02

Pos logit contributions
arcity+0.085
 Cage+0.070
Hardware+0.070
 Sisters+0.068
τ+0.067
Neg logit contributions
anka-0.066
plom-0.063
 glitter-0.062
agen-0.062
 interpol-0.059
Token and
Token ID290
Feature activation+8.91e-02

Pos logit contributions
arcity+0.439
Hardware+0.357
 Cage+0.356
 Sisters+0.345
τ+0.344
Neg logit contributions
anka-0.337
 glitter-0.323
plom-0.321
agen-0.312
 interpol-0.307
Token from
Token ID422
Feature activation+1.49e-02

Pos logit contributions
arcity+1.941
 Cage+1.585
Hardware+1.564
 Sisters+1.530
τ+1.498
Neg logit contributions
anka-1.862
plom-1.810
agen-1.770
 glitter-1.760
 interpol-1.702
Token antagon
Token ID23775
Feature activation-1.55e-01

Pos logit contributions
arcity+0.082
Hardware+0.069
 Cage+0.068
 Sisters+0.066
τ+0.066
Neg logit contributions
anka-0.059
plom-0.057
 glitter-0.057
agen-0.055
 interpol-0.053
Tokenistic
Token ID2569
Feature activation+4.42e-02

Pos logit contributions
anka+0.556
plom+0.535
agen+0.526
 glitter+0.517
 interpol+0.492
Neg logit contributions
arcity-0.913
 Cage-0.773
Hardware-0.766
 Sisters-0.746
τ-0.736
Token states
Token ID2585
Feature activation-1.52e-01

Pos logit contributions
arcity+0.248
Hardware+0.206
 Cage+0.205
 Sisters+0.198
Drive+0.197
Neg logit contributions
anka-0.172
plom-0.167
 glitter-0.165
agen-0.161
 interpol-0.155
Token,
Token ID11
Feature activation+3.45e-01

Pos logit contributions
anka+0.539
plom+0.525
 glitter+0.508
agen+0.506
 interpol+0.478
Neg logit contributions
arcity-0.899
 Cage-0.761
Hardware-0.759
 Sisters-0.739
Drive-0.726
Token but
Token ID475
Feature activation+5.90e-01

Pos logit contributions
arcity+2.070
 Cage+1.760
Hardware+1.747
 Sisters+1.712
τ+1.686
Neg logit contributions
anka-1.195
plom-1.152
agen-1.114
 glitter-1.112
 interpol-1.059
Token from
Token ID422
Feature activation+4.40e-02

Pos logit contributions
arcity+3.079
 Cage+2.561
Hardware+2.526
 Sisters+2.487
τ+2.436
Neg logit contributions
anka-2.483
plom-2.401
agen-2.351
 glitter-2.329
 interpol-2.248
Token our
Token ID674
Feature activation+2.71e-02

Pos logit contributions
arcity+0.245
Hardware+0.203
 Cage+0.203
 Sisters+0.196
τ+0.194
Neg logit contributions
anka-0.174
plom-0.169
 glitter-0.165
agen-0.162
 interpol-0.157
Token own
Token ID898
Feature activation+3.81e-01

Pos logit contributions
arcity+0.149
 Cage+0.124
Hardware+0.123
 Sisters+0.119
τ+0.118
Neg logit contributions
anka-0.108
plom-0.105
 glitter-0.103
agen-0.101
 interpol-0.097
Token foreign
Token ID3215
Feature activation+1.61e-01

Pos logit contributions
arcity+2.025
 Cage+1.690
Hardware+1.671
 Sisters+1.641
τ+1.609
Neg logit contributions
anka-1.570
plom-1.522
agen-1.485
 glitter-1.473
 interpol-1.419
Token service
Token ID2139
Feature activation+1.40e-01

Pos logit contributions
arcity+0.854
 Cage+0.708
Hardware+0.701
 Sisters+0.683
τ+0.673
Neg logit contributions
anka-0.675
plom-0.655
agen-0.639
 glitter-0.638
 interpol-0.611
Token support
Token ID1104
Feature activation-7.30e-02

Pos logit contributions
arcity+0.006
Hardware+0.005
 Cage+0.005
 Sisters+0.005
τ+0.005
Neg logit contributions
anka-0.004
plom-0.004
 glitter-0.004
agen-0.004
 interpol-0.004
Token their
Token ID511
Feature activation-2.44e-01

Pos logit contributions
anka+0.296
plom+0.282
 glitter+0.279
agen+0.276
 interpol+0.268
Neg logit contributions
arcity-0.403
Hardware-0.330
 Cage-0.326
 Sisters-0.319
τ-0.317
Token already
Token ID1541
Feature activation+4.53e-02

Pos logit contributions
anka+0.832
 glitter+0.797
plom+0.790
agen+0.772
 interpol+0.745
Neg logit contributions
arcity-1.482
Hardware-1.251
 Cage-1.247
τ-1.214
 Sisters-1.208
Token-
Token ID12
Feature activation+1.32e-03

Pos logit contributions
arcity+0.255
 Cage+0.214
Hardware+0.213
 Sisters+0.208
τ+0.205
Neg logit contributions
anka-0.174
plom-0.168
 glitter-0.164
agen-0.164
 interpol-0.156
Tokente
Token ID660
Feature activation+1.00e-01

Pos logit contributions
arcity+0.007
 Cage+0.006
Hardware+0.006
 Sisters+0.005
τ+0.005
Neg logit contributions
anka-0.006
plom-0.006
agen-0.005
 glitter-0.005
 interpol-0.005
Tokenet
Token ID316
Feature activation+5.93e-01

Pos logit contributions
arcity+0.523
 Cage+0.438
Hardware+0.433
 Sisters+0.429
τ+0.418
Neg logit contributions
anka-0.422
plom-0.412
agen-0.401
 glitter-0.397
 interpol-0.379
Tokenering
Token ID1586
Feature activation+1.21e-01

Pos logit contributions
arcity+3.675
 Cage+3.150
Hardware+3.112
 Sisters+3.056
τ+3.012
Neg logit contributions
anka-1.910
plom-1.847
 glitter-1.775
agen-1.762
 interpol-1.694
Token legislative
Token ID10828
Feature activation-2.98e-01

Pos logit contributions
arcity+0.759
Hardware+0.643
 Cage+0.642
 Sisters+0.628
τ+0.623
Neg logit contributions
anka-0.395
plom-0.377
 glitter-0.371
agen-0.368
 interpol-0.351
Token agenda
Token ID8666
Feature activation-4.92e-02

Pos logit contributions
anka+0.954
 glitter+0.910
plom+0.901
agen+0.881
 interpol+0.853
Neg logit contributions
arcity-1.896
Hardware-1.585
 Cage-1.569
τ-1.553
 Sisters-1.527
Token if
Token ID611
Feature activation-2.52e-03

Pos logit contributions
anka+0.192
plom+0.186
agen+0.181
 glitter+0.180
 interpol+0.172
Neg logit contributions
arcity-0.274
 Cage-0.229
Hardware-0.228
 Sisters-0.222
τ-0.219
Token there
Token ID612
Feature activation-8.81e-02

Pos logit contributions
anka+0.011
plom+0.010
agen+0.010
 glitter+0.010
 interpol+0.010
Neg logit contributions
arcity-0.013
Hardware-0.011
 Cage-0.011
 Sisters-0.011
τ-0.011
Token category
Token ID6536
Feature activation+5.10e-02

Pos logit contributions
arcity+1.390
 Cage+1.130
Hardware+1.129
 Sisters+1.103
τ+1.092
Neg logit contributions
anka-1.119
plom-1.084
 glitter-1.076
agen-1.065
 interpol-1.043
Token which
Token ID543
Feature activation+3.05e-01

Pos logit contributions
arcity+0.273
 Cage+0.227
Hardware+0.225
 Sisters+0.221
τ+0.216
Neg logit contributions
anka-0.210
plom-0.205
agen-0.200
 glitter-0.198
 interpol-0.192
Token could
Token ID714
Feature activation-3.15e-02

Pos logit contributions
arcity+1.553
Hardware+1.266
 Cage+1.250
 Sisters+1.217
τ+1.210
Neg logit contributions
anka-1.348
plom-1.310
 glitter-1.293
agen-1.278
 interpol-1.259
Token capture
Token ID8006
Feature activation-1.22e-02

Pos logit contributions
anka+0.130
plom+0.128
 glitter+0.127
agen+0.126
 interpol+0.124
Neg logit contributions
arcity-0.166
Hardware-0.138
 Cage-0.137
 Sisters-0.133
τ-0.131
Token the
Token ID262
Feature activation-1.81e-02

Pos logit contributions
anka+0.051
 glitter+0.049
plom+0.049
agen+0.048
 interpol+0.047
Neg logit contributions
arcity-0.065
Hardware-0.053
 Cage-0.053
 Sisters-0.051
τ-0.051
Token economic
Token ID3034
Feature activation-8.18e-03

Pos logit contributions
anka+0.071
 glitter+0.069
plom+0.068
agen+0.067
 interpol+0.065
Neg logit contributions
arcity-0.100
Hardware-0.083
 Cage-0.083
 Sisters-0.080
τ-0.080
Token middle
Token ID3504
Feature activation-5.12e-02

Pos logit contributions
anka+0.034
 glitter+0.033
plom+0.033
agen+0.032
 interpol+0.032
Neg logit contributions
arcity-0.043
Hardware-0.036
 Cage-0.036
 Sisters-0.035
τ-0.034
Token in
Token ID287
Feature activation-1.17e-01

Pos logit contributions
anka+0.199
plom+0.190
 glitter+0.187
agen+0.187
 interpol+0.179
Neg logit contributions
arcity-0.285
 Cage-0.239
Hardware-0.238
 Sisters-0.232
τ-0.229
Token India
Token ID3794
Feature activation-1.81e-01

Pos logit contributions
anka+0.482
plom+0.461
 glitter+0.461
agen+0.452
 interpol+0.438
Neg logit contributions
arcity-0.626
Hardware-0.522
 Cage-0.519
 Sisters-0.502
τ-0.498
Token.
Token ID13
Feature activation-4.31e-02

Pos logit contributions
anka+0.738
plom+0.714
agen+0.697
 glitter+0.694
 interpol+0.667
Neg logit contributions
arcity-0.979
 Cage-0.812
Hardware-0.807
 Sisters-0.791
Drive-0.772
Token While
Token ID2893
Feature activation-2.59e-01

Pos logit contributions
anka+0.199
plom+0.190
 glitter+0.187
agen+0.187
 interpol+0.181
Neg logit contributions
arcity-0.210
Hardware-0.166
 Cage-0.165
 Sisters-0.158
τ-0.158
Token to
Token ID284
Feature activation+2.45e-01

Pos logit contributions
arcity+0.294
 Cage+0.235
Hardware+0.231
 Sisters+0.226
Drive+0.220
Neg logit contributions
anka-0.333
plom-0.321
agen-0.316
 glitter-0.312
 interpol-0.302
Token sort
Token ID3297
Feature activation+2.82e-01

Pos logit contributions
arcity+1.330
 Cage+1.106
Hardware+1.103
 Sisters+1.076
τ+1.062
Neg logit contributions
anka-0.982
plom-0.959
 glitter-0.936
agen-0.934
 interpol-0.901
Token its
Token ID663
Feature activation-9.77e-02

Pos logit contributions
arcity+1.583
 Cage+1.331
Hardware+1.318
 Sisters+1.291
τ+1.271
Neg logit contributions
anka-1.081
plom-1.042
agen-1.016
 glitter-1.013
 interpol-0.970
Token financial
Token ID3176
Feature activation+1.21e-01

Pos logit contributions
anka+0.396
 glitter+0.379
plom+0.378
agen+0.370
 interpol+0.359
Neg logit contributions
arcity-0.535
 Cage-0.443
Hardware-0.439
 Sisters-0.424
τ-0.424
Token position
Token ID2292
Feature activation-1.32e-01

Pos logit contributions
arcity+0.614
 Cage+0.498
Hardware+0.495
 Sisters+0.480
τ+0.475
Neg logit contributions
anka-0.540
plom-0.520
 glitter-0.514
agen-0.511
 interpol-0.493
Token.
Token ID13
Feature activation+6.14e-02

Pos logit contributions
anka+0.519
plom+0.504
agen+0.493
 glitter+0.489
 interpol+0.469
Neg logit contributions
arcity-0.728
 Cage-0.607
Hardware-0.603
 Sisters-0.588
τ-0.580
Token The
Token ID383
Feature activation+4.42e-02

Pos logit contributions
arcity+0.296
 Cage+0.239
Hardware+0.238
 Sisters+0.230
τ+0.227
Neg logit contributions
anka-0.286
plom-0.276
agen-0.270
 glitter-0.269
 interpol-0.260
Token company
Token ID1664
Feature activation+2.84e-01

Pos logit contributions
arcity+0.243
 Cage+0.203
Hardware+0.201
τ+0.194
 Sisters+0.194
Neg logit contributions
anka-0.176
plom-0.169
 glitter-0.167
agen-0.166
 interpol-0.160
Token has
Token ID468
Feature activation+9.01e-02

Pos logit contributions
arcity+1.432
 Cage+1.171
Hardware+1.164
 Sisters+1.132
τ+1.116
Neg logit contributions
anka-1.263
plom-1.227
agen-1.201
 glitter-1.197
 interpol-1.157
Token warned
Token ID7728
Feature activation+1.51e-01

Pos logit contributions
arcity+0.490
Hardware+0.404
 Cage+0.404
 Sisters+0.391
τ+0.388
Neg logit contributions
anka-0.364
plom-0.355
 glitter-0.350
agen-0.343
 interpol-0.337
Token it
Token ID340
Feature activation+1.78e-01

Pos logit contributions
arcity+0.785
Hardware+0.646
 Cage+0.642
 Sisters+0.621
τ+0.615
Neg logit contributions
anka-0.645
plom-0.623
 glitter-0.618
agen-0.612
 interpol-0.591
Token
Token ID198
Feature activation+1.09e-01

Pos logit contributions
arcity+0.926
 Cage+0.720
Hardware+0.708
 Sisters+0.692
τ+0.676
Neg logit contributions
anka-1.102
plom-1.071
agen-1.056
 glitter-1.049
 interpol-1.018
TokenS
Token ID50
Feature activation+1.15e-01

Pos logit contributions
arcity+0.393
 Cage+0.290
Hardware+0.274
 Sisters+0.272
 RI+0.258
Neg logit contributions
anka-0.640
plom-0.624
agen-0.618
 glitter-0.612
 interpol-0.597
Token EC
Token ID13182
Feature activation+5.77e-02

Pos logit contributions
arcity+0.499
Hardware+0.398
 Cage+0.396
 Sisters+0.380
Drive+0.374
Neg logit contributions
anka-0.586
plom-0.572
agen-0.562
 glitter-0.557
 interpol-0.541
TokenUN
Token ID4944
Feature activation+1.57e-01

Pos logit contributions
arcity+0.300
 Cage+0.250
Hardware+0.247
 Sisters+0.241
τ+0.236
Neg logit contributions
anka-0.245
plom-0.237
agen-0.231
 glitter-0.230
 interpol-0.222
TokenDA
Token ID5631
Feature activation+1.03e-01

Pos logit contributions
arcity+0.519
 Cage+0.381
Hardware+0.374
 Sisters+0.360
τ+0.348
Neg logit contributions
anka-0.966
plom-0.946
agen-0.929
 glitter-0.925
 interpol-0.903
Token S
Token ID311
Feature activation+2.27e-01

Pos logit contributions
arcity+0.475
 Cage+0.378
Hardware+0.377
 Sisters+0.364
Drive+0.357
Neg logit contributions
anka-0.498
plom-0.485
agen-0.476
 glitter-0.473
 interpol-0.460
Token EC
Token ID13182
Feature activation+1.71e-01

Pos logit contributions
arcity+1.046
Hardware+0.832
 Cage+0.830
 Sisters+0.802
Drive+0.783
Neg logit contributions
anka-1.101
plom-1.071
agen-1.055
 glitter-1.050
 interpol-1.019
TokenUN
Token ID4944
Feature activation+2.45e-02

Pos logit contributions
arcity+0.864
 Cage+0.709
Hardware+0.701
 Sisters+0.682
τ+0.666
Neg logit contributions
anka-0.756
plom-0.731
agen-0.717
 glitter-0.710
 interpol-0.687
TokenD
Token ID35
Feature activation-1.52e-01

Pos logit contributions
arcity+0.096
 Cage+0.072
Hardware+0.071
 Sisters+0.068
τ+0.066
Neg logit contributions
anka-0.137
plom-0.133
agen-0.132
 glitter-0.131
 interpol-0.127
Token
Token ID127
Feature activation+1.09e-01

Pos logit contributions
anka+0.631
plom+0.607
agen+0.602
 glitter+0.588
 interpol+0.569
Neg logit contributions
arcity-0.810
 Cage-0.668
Hardware-0.663
 Sisters-0.642
Drive-0.632
Token
Token ID228
Feature activation-4.14e-03

Pos logit contributions
arcity+0.759
 Cage+0.658
Hardware+0.656
 Sisters+0.645
Drive+0.633
Neg logit contributions
anka-0.272
plom-0.259
agen-0.249
 glitter-0.247
 interpol-0.230
Token Charlie
Token ID11526
Feature activation+1.23e-01

Pos logit contributions
anka+0.138
 glitter+0.135
plom+0.133
agen+0.131
 interpol+0.129
Neg logit contributions
arcity-0.175
Hardware-0.146
 Cage-0.140
Drive-0.139
τ-0.139
Token and
Token ID290
Feature activation+7.02e-02

Pos logit contributions
arcity+0.640
 Cage+0.527
Hardware+0.526
 Sisters+0.512
τ+0.504
Neg logit contributions
anka-0.521
plom-0.505
agen-0.494
 glitter-0.492
 interpol-0.473
Token the
Token ID262
Feature activation-4.63e-02

Pos logit contributions
arcity+0.350
Hardware+0.282
 Cage+0.279
τ+0.272
 Sisters+0.270
Neg logit contributions
anka-0.317
plom-0.305
 glitter-0.303
agen-0.302
 interpol-0.291
Token Chocolate
Token ID24777
Feature activation+1.16e-02

Pos logit contributions
anka+0.091
plom+0.083
 glitter+0.082
agen+0.081
 interpol+0.072
Neg logit contributions
arcity-0.348
Hardware-0.304
 Cage-0.300
τ-0.299
Drive-0.295
Token Factory
Token ID19239
Feature activation-5.01e-02

Pos logit contributions
arcity+0.052
Hardware+0.041
 Cage+0.040
τ+0.039
Drive+0.038
Neg logit contributions
anka-0.058
plom-0.056
agen-0.056
 glitter-0.056
 interpol-0.054
Token,
Token ID11
Feature activation+1.81e-01

Pos logit contributions
anka+0.210
plom+0.203
 glitter+0.200
agen+0.200
 interpol+0.193
Neg logit contributions
arcity-0.264
Hardware-0.218
 Cage-0.216
 Sisters-0.209
τ-0.207
Token from
Token ID422
Feature activation-4.21e-02

Pos logit contributions
arcity+0.994
Hardware+0.825
 Cage+0.818
 Sisters+0.793
τ+0.791
Neg logit contributions
anka-0.716
plom-0.692
 glitter-0.686
agen-0.674
 interpol-0.657
Token the
Token ID262
Feature activation+1.13e-02

Pos logit contributions
anka+0.184
 glitter+0.177
plom+0.177
agen+0.173
 interpol+0.169
Neg logit contributions
arcity-0.214
Hardware-0.177
 Cage-0.173
 Sisters-0.168
τ-0.168
Token poverty
Token ID8098
Feature activation-6.27e-02

Pos logit contributions
arcity+0.063
Hardware+0.053
 Cage+0.052
τ+0.051
 Sisters+0.050
Neg logit contributions
anka-0.044
 glitter-0.043
plom-0.042
agen-0.042
 interpol-0.041
Token-
Token ID12
Feature activation+1.83e-01

Pos logit contributions
anka+0.266
 glitter+0.256
plom+0.253
agen+0.251
 interpol+0.246
Neg logit contributions
arcity-0.327
Hardware-0.272
 Cage-0.267
 Sisters-0.258
τ-0.258
Tokenstr
Token ID2536
Feature activation+1.86e-01

Pos logit contributions
arcity+0.807
 Cage+0.642
Hardware+0.636
 Sisters+0.619
τ+0.602
Neg logit contributions
anka-0.929
plom-0.904
agen-0.890
 glitter-0.884
 interpol-0.853
Token that
Token ID326
Feature activation+1.71e-02

Pos logit contributions
arcity+0.919
 Cage+0.755
Hardware+0.755
τ+0.721
 Sisters+0.716
Neg logit contributions
anka-0.715
 glitter-0.684
plom-0.683
agen-0.668
 interpol-0.655
Token you
Token ID345
Feature activation+1.30e-01

Pos logit contributions
arcity+0.095
Hardware+0.079
 Cage+0.078
τ+0.075
Drive+0.074
Neg logit contributions
anka-0.068
plom-0.065
 glitter-0.065
agen-0.064
 interpol-0.063
Token still
Token ID991
Feature activation+2.32e-01

Pos logit contributions
arcity+0.713
Hardware+0.593
 Cage+0.591
τ+0.573
 Sisters+0.572
Neg logit contributions
anka-0.512
plom-0.494
 glitter-0.493
agen-0.490
 interpol-0.470
Token get
Token ID651
Feature activation-1.81e-01

Pos logit contributions
arcity+1.253
 Cage+1.042
Hardware+1.038
 Sisters+1.010
τ+0.999
Neg logit contributions
anka-0.943
plom-0.909
 glitter-0.897
agen-0.895
 interpol-0.859
Token awesome
Token ID7427
Feature activation-7.84e-03

Pos logit contributions
anka+0.755
 glitter+0.738
plom+0.717
 interpol+0.699
agen+0.697
Neg logit contributions
arcity-0.963
Hardware-0.794
 Cage-0.786
τ-0.761
xtap-0.740
Token stuff
Token ID3404
Feature activation+1.48e-01

Pos logit contributions
anka+0.033
 glitter+0.032
plom+0.031
agen+0.031
 interpol+0.030
Neg logit contributions
arcity-0.042
 Cage-0.034
Hardware-0.034
τ-0.033
 Sisters-0.033
Token and
Token ID290
Feature activation-4.09e-02

Pos logit contributions
arcity+0.804
 Cage+0.664
Hardware+0.664
 Sisters+0.642
τ+0.636
Neg logit contributions
anka-0.606
plom-0.583
 glitter-0.573
agen-0.567
 interpol-0.549
Token cool
Token ID3608
Feature activation+2.96e-02

Pos logit contributions
anka+0.166
 glitter+0.161
plom+0.157
agen+0.154
 interpol+0.152
Neg logit contributions
arcity-0.222
 Cage-0.184
Hardware-0.183
τ-0.178
 Sisters-0.175
Token experiences
Token ID6461
Feature activation-1.47e-01

Pos logit contributions
arcity+0.148
 Cage+0.121
Hardware+0.119
τ+0.115
 Sisters+0.115
Neg logit contributions
anka-0.134
 glitter-0.129
plom-0.129
agen-0.126
 interpol-0.123
Token.
Token ID13
Feature activation-8.30e-02

Pos logit contributions
anka+0.582
plom+0.557
 glitter+0.552
agen+0.543
 interpol+0.527
Neg logit contributions
arcity-0.817
Hardware-0.675
 Cage-0.674
 Sisters-0.651
τ-0.650
Token
Token ID198
Feature activation-1.51e-01

Pos logit contributions
anka+0.387
plom+0.369
 glitter+0.367
agen+0.366
 interpol+0.354
Neg logit contributions
arcity-0.402
Hardware-0.315
 Cage-0.315
τ-0.302
 Sisters-0.299
Tokenв
Token ID38857
Feature activation+7.70e-03

Pos logit contributions
arcity+0.738
 Cage+0.603
Hardware+0.597
 Sisters+0.583
Drive+0.570
Neg logit contributions
anka-0.644
plom-0.624
agen-0.611
 glitter-0.611
 interpol-0.589
Tokenа
Token ID16142
Feature activation+3.34e-03

Pos logit contributions
arcity+0.043
 Cage+0.036
Hardware+0.035
 Sisters+0.034
Drive+0.034
Neg logit contributions
anka-0.031
plom-0.029
agen-0.029
 glitter-0.029
 interpol-0.027
Tokenт
Token ID20375
Feature activation-9.67e-02

Pos logit contributions
arcity+0.017
 Cage+0.014
Hardware+0.014
 Sisters+0.014
Drive+0.013
Neg logit contributions
anka-0.014
plom-0.014
agen-0.014
 glitter-0.014
 interpol-0.013
Tokenь
Token ID45367
Feature activation+7.02e-02

Pos logit contributions
anka+0.406
plom+0.392
agen+0.387
 glitter+0.383
 interpol+0.369
Neg logit contributions
arcity-0.509
 Cage-0.421
Hardware-0.418
 Sisters-0.410
Drive-0.399
Token
Token ID12466
Feature activation-8.56e-02

Pos logit contributions
arcity+0.326
 Cage+0.262
Hardware+0.259
 Sisters+0.253
Drive+0.246
Neg logit contributions
anka-0.339
plom-0.329
agen-0.324
 glitter-0.323
 interpol-0.313
Token
Token ID116
Feature activation-3.92e-01

Pos logit contributions
anka+0.302
plom+0.288
 glitter+0.282
agen+0.281
 interpol+0.266
Neg logit contributions
arcity-0.508
 Cage-0.431
Hardware-0.427
 Sisters-0.420
Drive-0.411
Token
Token ID141
Feature activation+4.51e-02

Pos logit contributions
anka+1.969
plom+1.906
agen+1.901
 glitter+1.879
 interpol+1.823
Neg logit contributions
arcity-1.740
 Cage-1.357
Hardware-1.342
 Sisters-1.307
Drive-1.269
Token
Token ID227
Feature activation-3.19e-01

Pos logit contributions
arcity+0.323
 Cage+0.282
Hardware+0.280
 Sisters+0.276
Drive+0.272
Neg logit contributions
anka-0.105
plom-0.097
agen-0.095
 glitter-0.093
 interpol-0.085
Token.
Token ID13
Feature activation-9.85e-02

Pos logit contributions
anka+1.592
plom+1.529
agen+1.512
 glitter+1.512
 interpol+1.451
Neg logit contributions
arcity-1.446
 Cage-1.140
Hardware-1.122
 Sisters-1.099
Drive-1.068
Token
Token ID12466
Feature activation+2.11e-01

Pos logit contributions
anka+0.508
plom+0.491
agen+0.484
 glitter+0.482
 interpol+0.468
Neg logit contributions
arcity-0.427
 Cage-0.330
Hardware-0.328
 Sisters-0.317
Drive-0.309
Token
Token ID248
Feature activation-3.58e-01

Pos logit contributions
arcity+1.221
 Cage+1.031
Hardware+1.023
 Sisters+1.005
Drive+0.982
Neg logit contributions
anka-0.773
plom-0.744
 glitter-0.724
agen-0.722
 interpol-0.687
Token.
Token ID13
Feature activation+2.29e-01

Pos logit contributions
arcity+1.303
 Cage+1.081
Hardware+1.067
 Sisters+1.048
τ+1.026
Neg logit contributions
anka-1.116
plom-1.089
agen-1.062
 glitter-1.056
 interpol-1.023
Token Gordon
Token ID11646
Feature activation+3.26e-01

Pos logit contributions
arcity+0.991
 Cage+0.769
Hardware+0.766
 Sisters+0.749
τ+0.725
Neg logit contributions
anka-1.185
plom-1.146
agen-1.133
 glitter-1.128
 interpol-1.094
Token Reid
Token ID16095
Feature activation-2.02e-01

Pos logit contributions
arcity+0.958
Hardware+0.647
 Cage+0.636
 Sisters+0.592
τ+0.586
Neg logit contributions
anka-2.139
plom-2.091
agen-2.067
 glitter-2.059
 interpol-2.012
Token (
Token ID357
Feature activation+1.48e-01

Pos logit contributions
anka+0.895
plom+0.869
agen+0.848
 glitter+0.844
 interpol+0.814
Neg logit contributions
arcity-1.014
 Cage-0.834
Hardware-0.826
 Sisters-0.807
τ-0.791
Token108
Token ID15711
Feature activation+8.15e-02

Pos logit contributions
arcity+0.767
 Cage+0.620
 Sisters+0.605
Hardware+0.603
 RI+0.584
Neg logit contributions
anka-0.651
plom-0.625
agen-0.623
 glitter-0.605
 interpol-0.584
Token)
Token ID8
Feature activation-1.90e-01

Pos logit contributions
arcity+0.370
 Cage+0.292
Hardware+0.288
 Sisters+0.280
τ+0.273
Neg logit contributions
anka-0.408
plom-0.393
agen-0.388
 glitter-0.384
 interpol-0.372
Token (
Token ID357
Feature activation-3.33e-02

Pos logit contributions
anka+0.777
plom+0.737
agen+0.731
 glitter+0.723
 interpol+0.700
Neg logit contributions
arcity-1.039
Hardware-0.844
 Cage-0.841
 Sisters-0.815
τ-0.807
Token20
Token ID1238
Feature activation+5.87e-02

Pos logit contributions
anka+0.145
agen+0.140
plom+0.140
 glitter+0.134
 interpol+0.131
Neg logit contributions
arcity-0.173
 Cage-0.138
 Sisters-0.135
Hardware-0.134
 RI-0.130
Token)
Token ID8
Feature activation+4.42e-01

Pos logit contributions
arcity+0.269
 Cage+0.211
Hardware+0.208
 Sisters+0.203
τ+0.198
Neg logit contributions
anka-0.292
plom-0.281
agen-0.278
 glitter-0.274
 interpol-0.266
Token
Token ID198
Feature activation+1.85e-01

Pos logit contributions
arcity+1.744
 Cage+1.372
Hardware+1.331
 Sisters+1.299
τ+1.266
Neg logit contributions
anka-2.398
plom-2.363
agen-2.316
 glitter-2.299
 interpol-2.232
Token
Token ID198
Feature activation+1.21e-01

Pos logit contributions
arcity+0.812
 Cage+0.630
Hardware+0.621
 Sisters+0.606
τ+0.593
Neg logit contributions
anka-0.948
plom-0.919
agen-0.908
 glitter-0.900
 interpol-0.873
Token near
Token ID1474
Feature activation-6.72e-02

Pos logit contributions
arcity+0.458
Hardware+0.380
 Cage+0.379
 Sisters+0.369
τ+0.365
Neg logit contributions
anka-0.352
plom-0.337
 glitter-0.333
agen-0.333
 interpol-0.316
Token the
Token ID262
Feature activation+7.10e-02

Pos logit contributions
anka+0.306
plom+0.296
 glitter+0.292
agen+0.289
 interpol+0.279
Neg logit contributions
arcity-0.329
Hardware-0.270
 Cage-0.264
 Sisters-0.257
τ-0.255
Token portal
Token ID17898
Feature activation+3.12e-01

Pos logit contributions
arcity+0.415
 Cage+0.349
Hardware+0.348
 Sisters+0.339
τ+0.336
Neg logit contributions
anka-0.258
plom-0.249
 glitter-0.243
agen-0.241
 interpol-0.231
Token to
Token ID284
Feature activation+5.58e-02

Pos logit contributions
arcity+1.602
 Cage+1.317
Hardware+1.310
 Sisters+1.275
τ+1.257
Neg logit contributions
anka-1.357
plom-1.315
agen-1.287
 glitter-1.286
 interpol-1.234
Token R
Token ID371
Feature activation-1.25e-01

Pos logit contributions
arcity+0.299
Hardware+0.251
 Cage+0.246
τ+0.239
 Sisters+0.238
Neg logit contributions
anka-0.226
plom-0.222
 glitter-0.218
agen-0.214
 interpol-0.209
Tokenal
Token ID282
Feature activation-4.20e-01

Pos logit contributions
anka+0.610
plom+0.591
agen+0.584
 glitter+0.566
 interpol+0.551
Neg logit contributions
arcity-0.565
 Cage-0.464
Hardware-0.458
 Sisters-0.448
τ-0.434
Tokenn
Token ID77
Feature activation-2.20e-01

Pos logit contributions
anka+1.551
plom+1.449
agen+1.447
 glitter+1.373
 interpol+1.313
Neg logit contributions
arcity-2.448
 Cage-2.097
Hardware-2.077
 Sisters-2.013
τ-1.996
Tokenoth
Token ID849
Feature activation-2.19e-01

Pos logit contributions
anka+1.041
plom+0.994
agen+0.985
 glitter+0.950
 interpol+0.909
Neg logit contributions
arcity-1.051
Hardware-0.867
 Cage-0.859
 Sisters-0.846
τ-0.818
Token
Token ID198
Feature activation-9.69e-02

Pos logit contributions
anka+0.977
plom+0.946
agen+0.933
 glitter+0.931
 interpol+0.888
Neg logit contributions
arcity-1.095
Hardware-0.900
 Cage-0.885
 Sisters-0.857
τ-0.851
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
anka+0.481
plom+0.465
agen+0.460
 glitter+0.456
 interpol+0.442
Neg logit contributions
arcity-0.444
 Cage-0.344
Hardware-0.339
 Sisters-0.332
τ-0.325
Tokenonly
Token ID8807
Feature activation-7.96e-02

Pos logit contributions
anka+0.559
plom+0.542
agen+0.536
 glitter+0.522
 interpol+0.503
Neg logit contributions
arcity-0.566
 Cage-0.454
 Sisters-0.441
Hardware-0.441
 RI-0.426
Token low
Token ID1877
Feature activation+1.90e-01

Pos logit contributions
arcity+0.431
Hardware+0.356
 Cage+0.355
τ+0.343
 Sisters+0.342
Neg logit contributions
anka-0.326
plom-0.312
 glitter-0.311
agen-0.305
 interpol-0.296
Token-
Token ID12
Feature activation-9.72e-03

Pos logit contributions
arcity+1.058
 Cage+0.890
Hardware+0.884
 Sisters+0.863
τ+0.852
Neg logit contributions
anka-0.733
plom-0.707
agen-0.691
 glitter-0.690
 interpol-0.659
Tokenlying
Token ID3157
Feature activation+1.81e-01

Pos logit contributions
anka+0.042
plom+0.041
agen+0.040
 glitter+0.040
 interpol+0.038
Neg logit contributions
arcity-0.049
 Cage-0.041
Hardware-0.040
 Sisters-0.040
τ-0.039
Token areas
Token ID3006
Feature activation-1.98e-02

Pos logit contributions
arcity+0.955
Hardware+0.783
 Cage+0.781
τ+0.755
 Sisters+0.751
Neg logit contributions
anka-0.766
plom-0.733
 glitter-0.729
agen-0.718
 interpol-0.698
Token started
Token ID2067
Feature activation-6.67e-02

Pos logit contributions
anka+0.081
 glitter+0.078
plom+0.078
agen+0.077
 interpol+0.074
Neg logit contributions
arcity-0.105
 Cage-0.088
Hardware-0.087
 Sisters-0.085
Drive-0.084
Token flooding
Token ID17448
Feature activation-1.10e-01

Pos logit contributions
anka+0.278
 glitter+0.271
plom+0.268
agen+0.262
 interpol+0.257
Neg logit contributions
arcity-0.351
 Cage-0.290
Hardware-0.290
 Sisters-0.280
Drive-0.277
Token over
Token ID625
Feature activation-6.58e-02

Pos logit contributions
anka+0.439
plom+0.416
agen+0.415
 glitter+0.413
 interpol+0.393
Neg logit contributions
arcity-0.603
 Cage-0.504
Hardware-0.501
 Sisters-0.488
τ-0.483
Token the
Token ID262
Feature activation+2.68e-01

Pos logit contributions
anka+0.287
 glitter+0.273
plom+0.272
agen+0.268
 interpol+0.259
Neg logit contributions
arcity-0.336
 Cage-0.279
Hardware-0.275
 Sisters-0.268
τ-0.265
Token last
Token ID938
Feature activation-2.14e-01

Pos logit contributions
arcity+1.390
 Cage+1.141
Hardware+1.136
 Sisters+1.100
τ+1.095
Neg logit contributions
anka-1.155
plom-1.116
 glitter-1.105
agen-1.091
 interpol-1.057
Token few
Token ID1178
Feature activation+1.75e-01

Pos logit contributions
anka+0.924
 glitter+0.893
plom+0.871
agen+0.865
 interpol+0.846
Neg logit contributions
arcity-1.117
Hardware-0.904
 Cage-0.896
τ-0.874
 Sisters-0.866
Token weeks
Token ID2745
Feature activation+3.21e-01

Pos logit contributions
arcity+0.777
 Cage+0.615
Hardware+0.609
 Sisters+0.584
τ+0.580
Neg logit contributions
anka-0.890
plom-0.861
 glitter-0.854
agen-0.844
 interpol-0.823
Token,
Token ID11
Feature activation+1.57e-02

Pos logit contributions
arcity+1.809
 Cage+1.494
Hardware+1.457
 Sisters+1.441
τ+1.400
Neg logit contributions
anka-1.730
plom-1.688
agen-1.641
 glitter-1.627
 interpol-1.587
Token has
Token ID468
Feature activation-7.11e-02

Pos logit contributions
arcity+0.083
Hardware+0.069
 Cage+0.068
 Sisters+0.066
τ+0.065
Neg logit contributions
anka-0.066
plom-0.064
 glitter-0.063
agen-0.062
 interpol-0.060
Token not
Token ID407
Feature activation+6.17e-02

Pos logit contributions
anka+0.285
plom+0.274
 glitter+0.273
agen+0.266
 interpol+0.259
Neg logit contributions
arcity-0.393
Hardware-0.326
 Cage-0.324
 Sisters-0.314
τ-0.311
Token addressed
Token ID9469
Feature activation+4.28e-02

Pos logit contributions
arcity+0.333
Hardware+0.277
 Cage+0.276
 Sisters+0.268
τ+0.265
Neg logit contributions
anka-0.253
plom-0.244
 glitter-0.240
agen-0.239
 interpol-0.229
Token the
Token ID262
Feature activation-2.04e-01

Pos logit contributions
arcity+0.223
Hardware+0.183
 Cage+0.182
 Sisters+0.177
τ+0.176
Neg logit contributions
anka-0.185
plom-0.177
 glitter-0.174
agen-0.173
 interpol-0.166
Token rumors
Token ID14923
Feature activation-3.32e-01

Pos logit contributions
anka+0.785
plom+0.744
 glitter+0.743
agen+0.733
 interpol+0.699
Neg logit contributions
arcity-1.164
Hardware-0.970
 Cage-0.963
τ-0.937
 Sisters-0.932
Token,
Token ID11
Feature activation+1.24e-01

Pos logit contributions
anka+1.342
plom+1.282
 glitter+1.266
agen+1.264
 interpol+1.201
Neg logit contributions
arcity-1.817
Hardware-1.510
 Cage-1.489
 Sisters-1.444
τ-1.442
Token but
Token ID475
Feature activation+5.79e-02

Pos logit contributions
arcity+0.699
Hardware+0.582
 Cage+0.582
 Sisters+0.566
τ+0.560
Neg logit contributions
anka-0.477
plom-0.458
 glitter-0.450
agen-0.446
 interpol-0.430
Token brother
Token ID3956
Feature activation-3.39e-02

Pos logit contributions
arcity+0.317
Hardware+0.263
 Cage+0.259
τ+0.251
 Sisters+0.250
Neg logit contributions
anka-0.239
plom-0.228
 glitter-0.224
agen-0.221
 interpol-0.213
Token Eric
Token ID7651
Feature activation+4.68e-01

Pos logit contributions
anka+0.147
plom+0.140
agen+0.139
 glitter+0.138
 interpol+0.133
Neg logit contributions
arcity-0.176
Hardware-0.144
 Cage-0.143
 Sisters-0.138
τ-0.138
Token backed
Token ID9763
Feature activation+1.81e-01

Pos logit contributions
arcity+2.446
 Cage+2.027
Hardware+2.008
 Sisters+1.964
τ+1.928
Neg logit contributions
anka-1.982
plom-1.920
agen-1.873
 glitter-1.864
 interpol-1.794
Token were
Token ID547
Feature activation-2.69e-01

Pos logit contributions
anka+1.143
 glitter+1.103
plom+1.101
agen+1.081
 interpol+1.078
Neg logit contributions
arcity-1.623
Hardware-1.342
 Cage-1.335
τ-1.308
 Sisters-1.307
Token play
Token ID711
Feature activation+1.39e-01

Pos logit contributions
anka+1.047
plom+1.018
 glitter+1.017
agen+0.984
 interpol+0.978
Neg logit contributions
arcity-1.508
Hardware-1.242
 Cage-1.238
 Sisters-1.199
τ-1.196
Token-
Token ID12
Feature activation-2.79e-02

Pos logit contributions
arcity+0.893
 Cage+0.769
Hardware+0.764
 Sisters+0.751
τ+0.740
Neg logit contributions
anka-0.417
plom-0.399
agen-0.386
 glitter-0.383
 interpol-0.362
Tokentesting
Token ID33407
Feature activation-6.14e-01

Pos logit contributions
anka+0.081
plom+0.077
agen+0.075
 glitter+0.074
 interpol+0.070
Neg logit contributions
arcity-0.183
 Cage-0.158
Hardware-0.157
 Sisters-0.154
τ-0.152
Token.
Token ID13
Feature activation-3.38e-01

Pos logit contributions
anka+2.283
 glitter+2.206
plom+2.180
agen+2.176
 interpol+2.128
Neg logit contributions
arcity-3.498
 Cage-2.858
Hardware-2.855
 Sisters-2.793
τ-2.790
Token One
Token ID1881
Feature activation-6.41e-01

Pos logit contributions
anka+1.486
plom+1.419
 glitter+1.415
agen+1.408
 interpol+1.370
Neg logit contributions
arcity-1.713
Hardware-1.352
 Cage-1.330
τ-1.301
 Sisters-1.283
Token was
Token ID373
Feature activation+7.41e-03

Pos logit contributions
anka+2.581
 glitter+2.491
plom+2.477
agen+2.434
 interpol+2.378
Neg logit contributions
arcity-3.479
Hardware-2.846
 Cage-2.795
 Sisters-2.739
τ-2.733
Token a
Token ID257
Feature activation+8.50e-03

Pos logit contributions
arcity+0.039
Hardware+0.032
 Cage+0.031
 Sisters+0.030
τ+0.030
Neg logit contributions
anka-0.032
plom-0.031
 glitter-0.030
agen-0.030
 interpol-0.029
Token Thought
Token ID27522
Feature activation+1.62e-01

Pos logit contributions
arcity+0.048
Hardware+0.040
 Cage+0.040
 Sisters+0.039
τ+0.039
Neg logit contributions
anka-0.032
plom-0.031
 glitter-0.031
agen-0.030
 interpol-0.029
Tokenst
Token ID301
Feature activation-2.31e-01

Pos logit contributions
arcity+0.782
Hardware+0.634
 Cage+0.618
τ+0.607
FACE+0.600
Neg logit contributions
anka-0.746
plom-0.731
agen-0.729
 glitter-0.714
 interpol-0.686
Tokeneal
Token ID2287
Feature activation-4.12e-01

Pos logit contributions
anka+1.266
agen+1.244
plom+1.237
 glitter+1.194
 interpol+1.177
Neg logit contributions
arcity-0.903
Hardware-0.719
 Cage-0.702
 Sisters-0.689
τ-0.672
Token cell
Token ID2685
Feature activation-1.45e-01

Pos logit contributions
anka+0.932
plom+0.889
 glitter+0.887
agen+0.883
 interpol+0.871
Neg logit contributions
arcity-1.127
Hardware-0.926
 Cage-0.919
 Sisters-0.886
τ-0.885
Token,
Token ID11
Feature activation+1.45e-01

Pos logit contributions
anka+0.618
plom+0.589
agen+0.588
 glitter+0.587
 interpol+0.576
Neg logit contributions
arcity-0.749
Hardware-0.622
 Cage-0.619
 Sisters-0.596
Drive-0.590
Token as
Token ID355
Feature activation-1.57e-01

Pos logit contributions
arcity+0.804
Hardware+0.664
 Cage+0.662
 Sisters+0.643
τ+0.634
Neg logit contributions
anka-0.577
plom-0.551
 glitter-0.545
agen-0.544
 interpol-0.537
Token shown
Token ID3402
Feature activation+1.71e-02

Pos logit contributions
anka+0.660
 glitter+0.625
plom+0.619
agen+0.618
 interpol+0.618
Neg logit contributions
arcity-0.835
Hardware-0.675
 Cage-0.668
 Sisters-0.646
Drive-0.644
Token in
Token ID287
Feature activation+5.11e-02

Pos logit contributions
arcity+0.097
 Cage+0.080
Hardware+0.080
 Sisters+0.078
Drive+0.077
Neg logit contributions
anka-0.066
plom-0.063
agen-0.062
 glitter-0.062
 interpol-0.060
Token Figure
Token ID11291
Feature activation-6.06e-01

Pos logit contributions
arcity+0.246
 Cage+0.198
Hardware+0.197
 Sisters+0.191
τ+0.187
Neg logit contributions
anka-0.238
plom-0.231
 glitter-0.227
agen-0.227
 interpol-0.221
Token 3
Token ID513
Feature activation+2.49e-01

Pos logit contributions
anka+2.657
 glitter+2.555
plom+2.543
agen+2.540
 interpol+2.495
Neg logit contributions
arcity-3.012
Hardware-2.424
 Cage-2.385
τ-2.322
 Sisters-2.313
Token.
Token ID13
Feature activation+1.93e-01

Pos logit contributions
arcity+1.297
 Cage+1.077
Hardware+1.065
 Sisters+1.043
τ+1.023
Neg logit contributions
anka-1.053
plom-1.022
agen-0.996
 glitter-0.991
 interpol-0.954
Token
Token ID198
Feature activation+2.18e-01

Pos logit contributions
arcity+0.889
 Cage+0.707
Hardware+0.700
 Sisters+0.680
τ+0.667
Neg logit contributions
anka-0.941
plom-0.912
agen-0.898
 glitter-0.893
 interpol-0.870
Token
Token ID198
Feature activation+2.04e-01

Pos logit contributions
arcity+0.937
 Cage+0.729
Hardware+0.717
 Sisters+0.700
τ+0.683
Neg logit contributions
anka-1.137
plom-1.107
agen-1.090
 glitter-1.083
 interpol-1.051
TokenFigure
Token ID11337
Feature activation-5.16e-01

Pos logit contributions
arcity+0.936
 Cage+0.744
 Sisters+0.720
Hardware+0.715
 RI+0.695
Neg logit contributions
anka-1.005
plom-0.976
agen-0.963
 glitter-0.953
 interpol-0.926
Token a
Token ID257
Feature activation-1.69e-02

Pos logit contributions
anka+0.656
plom+0.634
 glitter+0.628
agen+0.624
 interpol+0.596
Neg logit contributions
arcity-0.747
Hardware-0.609
 Cage-0.606
Drive-0.582
τ-0.581
Token crater
Token ID32593
Feature activation-3.83e-01

Pos logit contributions
anka+0.058
 glitter+0.057
plom+0.057
agen+0.055
 interpol+0.053
Neg logit contributions
arcity-0.101
Hardware-0.085
 Cage-0.085
τ-0.082
 Sisters-0.082
Token on
Token ID319
Feature activation-3.30e-01

Pos logit contributions
anka+1.468
 glitter+1.435
agen+1.424
plom+1.394
 interpol+1.337
Neg logit contributions
arcity-2.128
Hardware-1.800
 Cage-1.787
τ-1.713
 Sisters-1.708
Token planet
Token ID5440
Feature activation-5.63e-02

Pos logit contributions
anka+1.467
 glitter+1.429
plom+1.419
agen+1.408
 interpol+1.343
Neg logit contributions
arcity-1.636
Hardware-1.337
 Cage-1.317
τ-1.261
Drive-1.257
Token Venus
Token ID21094
Feature activation+4.77e-02

Pos logit contributions
anka+0.245
plom+0.236
 glitter+0.235
agen+0.235
 interpol+0.222
Neg logit contributions
arcity-0.287
Hardware-0.236
 Cage-0.234
 Sisters-0.226
τ-0.224
Token in
Token ID287
Feature activation-6.15e-01

Pos logit contributions
arcity+0.253
Hardware+0.210
 Cage+0.208
 Sisters+0.200
τ+0.199
Neg logit contributions
anka-0.199
 glitter-0.191
plom-0.191
agen-0.189
 interpol-0.180
Token her
Token ID607
Feature activation-2.35e-01

Pos logit contributions
anka+2.182
 glitter+2.175
plom+2.109
agen+2.061
 interpol+1.985
Neg logit contributions
arcity-3.530
Hardware-3.010
 Cage-2.933
τ-2.876
Drive-2.868
Token honor
Token ID7522
Feature activation-3.12e-01

Pos logit contributions
anka+0.476
 glitter+0.446
plom+0.444
agen+0.426
 interpol+0.398
Neg logit contributions
arcity-1.744
Hardware-1.520
 Cage-1.513
τ-1.488
 Sisters-1.481
Token.[
Token ID3693
Feature activation-1.58e-02

Pos logit contributions
anka+1.260
plom+1.215
agen+1.186
 glitter+1.182
 interpol+1.134
Neg logit contributions
arcity-1.689
 Cage-1.405
Hardware-1.401
 Sisters-1.360
τ-1.343
Token55
Token ID2816
Feature activation-1.72e-01

Pos logit contributions
anka+0.065
plom+0.063
agen+0.061
 glitter+0.061
 interpol+0.059
Neg logit contributions
arcity-0.084
 Cage-0.070
Hardware-0.069
 Sisters-0.068
τ-0.067
Token]
Token ID60
Feature activation+9.97e-02

Pos logit contributions
anka+0.731
plom+0.710
agen+0.692
 glitter+0.689
 interpol+0.663
Neg logit contributions
arcity-0.894
 Cage-0.742
Hardware-0.734
 Sisters-0.719
τ-0.706
Token of
Token ID286
Feature activation-3.55e-02

Pos logit contributions
arcity+1.166
 Cage+0.946
Hardware+0.929
 Sisters+0.911
τ+0.890
Neg logit contributions
anka-1.211
plom-1.176
agen-1.149
 glitter-1.141
 interpol-1.105
Token which
Token ID543
Feature activation-3.32e-01

Pos logit contributions
anka+0.154
plom+0.150
agen+0.146
 glitter+0.146
 interpol+0.140
Neg logit contributions
arcity-0.181
 Cage-0.150
Hardware-0.148
 Sisters-0.145
τ-0.142
Token way
Token ID835
Feature activation-7.49e-02

Pos logit contributions
anka+1.384
plom+1.340
 glitter+1.329
agen+1.304
 interpol+1.276
Neg logit contributions
arcity-1.749
Hardware-1.436
 Cage-1.408
τ-1.378
 Sisters-1.376
Token they
Token ID484
Feature activation-3.76e-01

Pos logit contributions
anka+0.319
plom+0.307
 glitter+0.301
agen+0.301
 interpol+0.289
Neg logit contributions
arcity-0.391
 Cage-0.321
Hardware-0.320
 Sisters-0.310
τ-0.308
Token were
Token ID547
Feature activation-3.31e-01

Pos logit contributions
anka+1.457
 glitter+1.445
plom+1.420
 interpol+1.403
agen+1.392
Neg logit contributions
arcity-2.073
Hardware-1.739
 Cage-1.690
τ-1.677
 Sisters-1.650
Token going
Token ID1016
Feature activation-6.97e-01

Pos logit contributions
anka+1.376
plom+1.348
 glitter+1.341
agen+1.308
 interpol+1.306
Neg logit contributions
arcity-1.762
Hardware-1.438
 Cage-1.417
τ-1.371
 Sisters-1.370
Token.
Token ID13
Feature activation-2.71e-01

Pos logit contributions
anka+2.883
plom+2.761
 glitter+2.717
agen+2.706
 interpol+2.628
Neg logit contributions
arcity-3.684
Hardware-3.027
 Cage-2.998
τ-2.924
 Sisters-2.913
Token As
Token ID1081
Feature activation-4.22e-02

Pos logit contributions
anka+1.200
plom+1.154
agen+1.143
 glitter+1.137
 interpol+1.099
Neg logit contributions
arcity-1.361
Hardware-1.069
 Cage-1.057
τ-1.024
 Sisters-1.020
Token part
Token ID636
Feature activation+8.69e-02

Pos logit contributions
anka+0.180
plom+0.173
 glitter+0.170
agen+0.169
 interpol+0.162
Neg logit contributions
arcity-0.222
Hardware-0.182
 Cage-0.181
 Sisters-0.176
τ-0.174
Token of
Token ID286
Feature activation-3.79e-01

Pos logit contributions
arcity+0.432
 Cage+0.352
Hardware+0.347
 Sisters+0.340
τ+0.335
Neg logit contributions
anka-0.394
plom-0.380
agen-0.373
 glitter-0.372
 interpol-0.360
Token the
Token ID262
Feature activation-2.49e-01

Pos logit contributions
anka+1.568
plom+1.520
 glitter+1.507
agen+1.474
 interpol+1.454
Neg logit contributions
arcity-1.994
Hardware-1.638
 Cage-1.605
τ-1.575
 Sisters-1.561
Token do
Token ID466
Feature activation-4.34e-02

Pos logit contributions
anka+0.722
plom+0.716
 glitter+0.714
agen+0.704
 interpol+0.693
Neg logit contributions
arcity-0.971
Hardware-0.805
 Cage-0.798
τ-0.772
 Sisters-0.770
Token two
Token ID734
Feature activation-1.06e-01

Pos logit contributions
anka+0.174
plom+0.169
 glitter+0.167
agen+0.166
 interpol+0.161
Neg logit contributions
arcity-0.235
Hardware-0.195
 Cage-0.194
 Sisters-0.188
τ-0.188
Token main
Token ID1388
Feature activation+3.84e-02

Pos logit contributions
anka+0.546
 glitter+0.531
plom+0.530
agen+0.522
 interpol+0.517
Neg logit contributions
arcity-0.464
Hardware-0.360
 Cage-0.358
τ-0.343
 Sisters-0.335
Token things
Token ID1243
Feature activation-3.14e-01

Pos logit contributions
arcity+0.153
 Cage+0.115
Hardware+0.114
τ+0.109
 Sisters+0.107
Neg logit contributions
anka-0.213
plom-0.208
 glitter-0.206
agen-0.203
 interpol-0.202
Token.
Token ID13
Feature activation-5.04e-01

Pos logit contributions
anka+1.486
plom+1.447
agen+1.424
 glitter+1.414
 interpol+1.369
Neg logit contributions
arcity-1.477
Hardware-1.184
 Cage-1.183
τ-1.134
 Sisters-1.131
Token One
Token ID1881
Feature activation-7.01e-01

Pos logit contributions
anka+2.212
plom+2.149
agen+2.137
 glitter+2.119
 interpol+2.042
Neg logit contributions
arcity-2.509
Hardware-2.014
 Cage-1.950
τ-1.939
 Sisters-1.883
Token is
Token ID318
Feature activation-1.32e-01

Pos logit contributions
anka+2.510
 glitter+2.450
plom+2.448
agen+2.414
 interpol+2.347
Neg logit contributions
arcity-4.115
Hardware-3.390
 Cage-3.330
τ-3.266
 Sisters-3.258
Token to
Token ID284
Feature activation-1.80e-02

Pos logit contributions
anka+0.566
plom+0.556
 glitter+0.550
agen+0.540
 interpol+0.530
Neg logit contributions
arcity-0.677
Hardware-0.552
 Cage-0.546
τ-0.530
 Sisters-0.529
Token create
Token ID2251
Feature activation+4.88e-03

Pos logit contributions
anka+0.071
plom+0.070
 glitter+0.069
agen+0.068
 interpol+0.067
Neg logit contributions
arcity-0.099
Hardware-0.082
 Cage-0.081
τ-0.079
 Sisters-0.079
Token a
Token ID257
Feature activation-7.81e-02

Pos logit contributions
arcity+0.026
Hardware+0.022
 Cage+0.021
τ+0.021
 Sisters+0.021
Neg logit contributions
anka-0.020
plom-0.019
 glitter-0.019
agen-0.019
 interpol-0.019
Token shared
Token ID4888
Feature activation+1.38e-01

Pos logit contributions
anka+0.298
plom+0.291
 glitter+0.289
agen+0.282
 interpol+0.275
Neg logit contributions
arcity-0.439
Hardware-0.366
 Cage-0.362
τ-0.353
 Sisters-0.351