TOP ACTIVATIONS
MAX = 21.952

are the Anti - Author itarian Movement ( AK ) and
just water , the carcin ogenic heavy metals are also entering
may be fue lling xen ophobic sentiment , as
the phrase femin ist TV with some
sm earing of a wholly benevolent foundation , due only to
same market forces . Ne oliberal analysts similarly blame the 2001
U . S . Immigration and Customs Enforcement forb ade his
as the cab ler s most watched series launch
the petty - bour ge ois intellig ents ia resisted en
may hear that GHC s garbage collector is well
T oxic or harmful al gal blo
the Russian government , misogyn istic and hateful rhetoric and general
.[ 107 ] Soc io economic factors also have a direct
practice of incentiv izing businesses to build here .
" AIR s Health and Social Development
Our nation s capital is rep lete
. The Center for Respons ive Politics has the full list
, the way " hom osexual s " are described in
new hardware , Assassin s Creed ® Liberation HD
; thus , Israel s ongoing Juda isation and

MIN ACTIVATIONS
MIN = -26.712

for shorter tours throughout the day ). All tickets
. m . ET on Sunday . With Josh
. m . ET on Sunday . I touched
vs . Seattle Seahawks on Thursday . Of corner
shooting incidents earlier in the day . According to
as prime minister later that day .[ 195 ]
broke out in France on Monday . ATT ENTION
for shorter tours throughout the day ). W right
travel agent earlier in the week to a different flight (
the Week recognition the following day .[ 113 ] He was
my research back in the spring of 2000 . He ignored
greatly improved in the last year or so . I believe
porn to share throughout the week , so I
exchange from earlier in the day on Nov . 12 between
. m . ET on Sunday . N orman
in a phone interview on Friday . Currently ,
areas in the last six months and now makes appointments by
when it arrives at the end of this month .
happened to me at some point ). The flash process fails
: at Arizona Cardinals on Thursday . When other

INTERVAL 9.786 - 21.952
CONTAINS 2.792%

ambition to establish a Great Zionist Empire
but it won t if leaders don
a shotgun , you ve got a gun in
Trans gender identity may be a relatively
think one side is superior ; usually it s

INTERVAL -2.380 - 9.786
CONTAINS 65.129%

One of the best ways to achieve effort less and long
their screens . L apt ops must already be pulled out
them from complaining to Congress about IRS targeting and
a sense , is this idea of the global community ,
that time ( start of the exercise ), " Eastern "

INTERVAL -14.546 - -2.380
CONTAINS 31.179%

where it got interesting . All four people I brought this
's ) fantasy mate . But the correct one
itude 34 00 m ; 19 ° 30 N )
, honestly . We did many things right . But that
La Feb re says five months after Price s

INTERVAL -26.712 - -14.546
CONTAINS 0.901%

which begins in the final week of July .
list management system ( May 2013 ), S out ron Global
cases of firearm shootings in 2010 , according to the most
were introduced in Milwaukee in 1990 . " Fund
ranking within the last 12 months ), a 3 - 0
Token are
Token ID389
Feature activation+5.58e+00

Pos logit contributions
 lifestyles+2.087
 personalities+2.011
 behaviour+1.922
 techn+1.915
 voices+1.914
Neg logit contributions
 semester-2.206
Feb-1.958
EMBER-1.810
 weeks-1.804
imeo-1.766
Token the
Token ID262
Feature activation+7.13e+00

Pos logit contributions
 lifestyles+3.472
 personalities+3.341
 techn+3.131
 behaviour+3.129
 voices+3.128
Neg logit contributions
 semester-5.795
Feb-5.311
EMBER-4.945
 weeks-4.898
imeo-4.876
Token Anti
Token ID12297
Feature activation+8.82e+00

Pos logit contributions
 lifestyles+4.953
 personalities+4.840
 voices+4.576
 behaviour+4.522
 techn+4.521
Neg logit contributions
 semester-6.821
Feb-6.258
EMBER-5.771
imeo-5.697
 hrs-5.670
Token-
Token ID12
Feature activation+1.44e+01

Pos logit contributions
 lifestyles+8.207
 personalities+8.131
 Resistance+7.924
 behaviour+7.795
 voices+7.784
Neg logit contributions
 semester-5.853
Feb-5.062
EMBER-4.650
imeo-4.520
 hrs-4.466
TokenAuthor
Token ID13838
Feature activation+1.19e+01

Pos logit contributions
 personalities+9.111
 lifestyles+9.074
 Resistance+8.612
 behaviour+8.588
 techn+8.431
Neg logit contributions
 semester-12.829
Feb-10.975
 weeks-10.628
EMBER-10.592
 hrs-10.527
Tokenitarian
Token ID8353
Feature activation+2.20e+01

Pos logit contributions
 lifestyles+2.542
 personalities+2.501
 behaviour+2.140
 voices+2.061
 techn+1.922
Neg logit contributions
 semester-16.301
Feb-14.897
EMBER-14.265
 conclud-14.206
 hrs-14.093
Token Movement
Token ID15477
Feature activation+6.97e+00

Pos logit contributions
 personalities+15.112
 lifestyles+14.806
 Resistance+14.669
 voices+14.448
 organisations+14.280
Neg logit contributions
 semester-15.629
Feb-14.382
imeo-13.186
 apiece-12.972
imester-12.959
Token (
Token ID357
Feature activation+3.99e+00

Pos logit contributions
 lifestyles+6.297
 personalities+6.197
 voices+5.936
 behaviour+5.913
 techn+5.911
Neg logit contributions
 semester-5.153
Feb-4.530
EMBER-4.079
imeo-4.022
 weeks-4.022
TokenAK
Token ID10206
Feature activation+3.25e+00

Pos logit contributions
 lifestyles+3.725
 personalities+3.637
 behaviour+3.499
 voices+3.492
 techn+3.483
Neg logit contributions
 semester-2.880
Feb-2.448
 weeks-2.250
EMBER-2.232
 hrs-2.201
Token)
Token ID8
Feature activation+5.94e+00

Pos logit contributions
 lifestyles+3.339
 personalities+3.241
 behaviour+3.129
 techn+3.122
 voices+3.116
Neg logit contributions
 semester-2.101
Feb-1.785
EMBER-1.597
 weeks-1.593
imeo-1.541
Token and
Token ID290
Feature activation+7.92e+00

Pos logit contributions
 lifestyles+4.691
 personalities+4.569
 voices+4.346
 behaviour+4.340
 techn+4.335
Neg logit contributions
 semester-5.176
Feb-4.609
EMBER-4.252
 weeks-4.215
imeo-4.180
Token just
Token ID655
Feature activation+2.25e+00

Pos logit contributions
 semester+0.686
Feb+0.602
 weeks+0.562
EMBER+0.552
 hrs+0.539
Neg logit contributions
 lifestyles-0.702
 personalities-0.676
 behaviour-0.644
 voices-0.642
 techn-0.641
Token water
Token ID1660
Feature activation+2.87e+00

Pos logit contributions
 lifestyles+1.524
 personalities+1.458
 behaviour+1.380
 techn+1.373
 voices+1.370
Neg logit contributions
 semester-2.230
Feb-2.011
 weeks-1.883
EMBER-1.880
imeo-1.841
Token,
Token ID11
Feature activation+7.88e+00

Pos logit contributions
 lifestyles+2.175
 personalities+2.083
 techn+1.999
 behaviour+1.995
 voices+1.988
Neg logit contributions
 semester-2.625
Feb-2.336
EMBER-2.185
imeo-2.145
 weeks-2.143
Token the
Token ID262
Feature activation+3.83e+00

Pos logit contributions
 lifestyles+6.674
 personalities+6.379
 techn+6.219
 voices+6.155
 behaviour+6.152
Neg logit contributions
 semester-6.279
Feb-5.501
EMBER-5.151
imeo-5.004
 hrs-4.970
Token carcin
Token ID28164
Feature activation+1.22e+01

Pos logit contributions
 lifestyles+2.533
 personalities+2.405
 behaviour+2.283
 voices+2.277
 techn+2.273
Neg logit contributions
 semester-3.867
Feb-3.505
EMBER-3.294
 weeks-3.258
imeo-3.230
Tokenogenic
Token ID15147
Feature activation+2.09e+01

Pos logit contributions
 lifestyles+7.231
 personalities+7.009
 behaviour+6.663
 voices+6.610
 techn+6.478
Neg logit contributions
 semester-11.877
Feb-10.564
EMBER-10.132
imeo-10.100
 hrs-10.099
Token heavy
Token ID4334
Feature activation+6.72e+00

Pos logit contributions
 lifestyles+16.455
 behaviour+16.040
 elements+16.032
 personalities+15.693
 voices+15.377
Neg logit contributions
 semester-12.891
Feb-12.245
imeo-11.636
EMBER-11.593
imester-11.355
Token metals
Token ID21782
Feature activation+1.27e+01

Pos logit contributions
 lifestyles+2.582
 personalities+2.368
 techn+2.191
 behaviour+2.184
 voices+2.157
Neg logit contributions
 semester-8.412
Feb-7.902
EMBER-7.559
imeo-7.443
 hrs-7.380
Token are
Token ID389
Feature activation+2.16e+00

Pos logit contributions
 lifestyles+11.946
 personalities+11.399
 techn+11.274
 voices+11.122
 behaviour+11.102
Neg logit contributions
 semester-7.853
Feb-6.932
EMBER-6.427
imeo-6.161
 hrs-6.015
Token also
Token ID635
Feature activation-5.46e-01

Pos logit contributions
 lifestyles+1.725
 personalities+1.660
 behaviour+1.586
 techn+1.581
 voices+1.577
Neg logit contributions
 semester-1.892
Feb-1.683
EMBER-1.561
 weeks-1.552
imeo-1.522
Token entering
Token ID8218
Feature activation+4.51e+00

Pos logit contributions
 semester+0.461
Feb+0.405
 weeks+0.379
EMBER+0.371
imeo+0.364
Neg logit contributions
 lifestyles-0.450
 personalities-0.435
 behaviour-0.414
 techn-0.414
 voices-0.412
Tokenmay
Token ID11261
Feature activation+5.10e-01

Pos logit contributions
 lifestyles+8.917
 personalities+8.603
 behaviour+8.358
 voices+8.228
 Resistance+8.192
Neg logit contributions
 semester-8.297
Feb-6.873
EMBER-6.660
imeo-6.523
 weeks-6.455
Token be
Token ID307
Feature activation-3.16e-01

Pos logit contributions
 lifestyles+0.427
 personalities+0.411
 behaviour+0.392
 techn+0.392
 voices+0.390
Neg logit contributions
 semester-0.428
Feb-0.378
 weeks-0.350
EMBER-0.348
 hrs-0.340
Token fue
Token ID37911
Feature activation+6.47e+00

Pos logit contributions
 semester+0.278
Feb+0.247
 weeks+0.230
EMBER+0.229
 hrs+0.223
Neg logit contributions
 lifestyles-0.251
 personalities-0.241
 techn-0.230
 behaviour-0.230
 voices-0.228
Tokenlling
Token ID2680
Feature activation+1.21e+01

Pos logit contributions
 lifestyles+5.039
 personalities+4.837
 behaviour+4.768
 voices+4.756
 techn+4.665
Neg logit contributions
 semester-5.463
Feb-4.788
EMBER-4.491
 weeks-4.344
 apiece-4.319
Token xen
Token ID27132
Feature activation+9.67e+00

Pos logit contributions
 lifestyles+8.442
 personalities+8.188
 voices+8.093
 behaviour+8.091
 opinions+7.896
Neg logit contributions
 semester-10.737
Feb-9.674
EMBER-8.924
imeo-8.882
 hrs-8.751
Tokenophobic
Token ID23468
Feature activation+2.01e+01

Pos logit contributions
 lifestyles+4.683
 personalities+4.328
 voices+4.265
 behaviour+4.247
 nationalism+4.203
Neg logit contributions
 semester-11.009
Feb-9.968
EMBER-9.435
 hrs-9.412
 weeks-9.371
Token sentiment
Token ID15598
Feature activation+5.59e+00

Pos logit contributions
 lifestyles+15.894
 behaviour+15.883
 voices+15.578
 nationalism+15.354
 personalities+15.315
Neg logit contributions
 semester-13.522
Feb-12.339
imester-11.651
��-11.628
imeo-11.530
Token
Token ID447
Feature activation-2.82e+00

Pos logit contributions
 lifestyles+5.902
 personalities+5.763
 behaviour+5.664
 voices+5.651
 techn+5.590
Neg logit contributions
 semester-3.270
Feb-2.728
EMBER-2.401
imeo-2.337
 hrs-2.312
Token
Token ID251
Feature activation+1.11e+01

Pos logit contributions
 semester+2.630
Feb+2.354
 weeks+2.200
EMBER+2.194
 hrs+2.150
Neg logit contributions
 lifestyles-2.086
 personalities-1.995
 behaviour-1.899
 techn-1.894
 voices-1.875
Token,
Token ID11
Feature activation+8.96e+00

Pos logit contributions
 lifestyles+11.864
 personalities+11.630
 voices+11.422
 behaviour+11.390
 techn+11.241
Neg logit contributions
 semester-5.729
Feb-4.601
EMBER-4.112
imeo-4.002
iatus-3.931
Token as
Token ID355
Feature activation+2.19e+00

Pos logit contributions
 lifestyles+7.191
 personalities+6.928
 behaviour+6.720
 voices+6.701
 techn+6.660
Neg logit contributions
 semester-7.438
Feb-6.549
EMBER-6.141
imeo-5.987
 weeks-5.919
Token the
Token ID262
Feature activation+6.95e+00

Pos logit contributions
 lifestyles+9.004
 personalities+8.747
 techn+8.514
 voices+8.399
 behaviour+8.287
Neg logit contributions
 semester-10.489
Feb-9.498
EMBER-8.809
imeo-8.698
 hrs-8.520
Token phrase
Token ID9546
Feature activation+5.83e+00

Pos logit contributions
 lifestyles+5.479
 personalities+5.325
 voices+5.091
 techn+5.091
 behaviour+5.083
Neg logit contributions
 semester-5.958
Feb-5.361
EMBER-4.957
imeo-4.856
 weeks-4.825
Token
Token ID564
Feature activation+6.96e-01

Pos logit contributions
 lifestyles+3.912
 personalities+3.734
 techn+3.605
 behaviour+3.552
 voices+3.542
Neg logit contributions
 semester-5.736
Feb-5.208
EMBER-4.893
 weeks-4.817
imeo-4.791
Token
Token ID250
Feature activation+1.59e+01

Pos logit contributions
 lifestyles+0.621
 personalities+0.603
 voices+0.579
 behaviour+0.578
 techn+0.577
Neg logit contributions
 semester-0.538
Feb-0.470
EMBER-0.429
 weeks-0.428
imeo-0.419
Tokenfemin
Token ID33594
Feature activation+1.42e+01

Pos logit contributions
 lifestyles+13.244
 personalities+12.919
 techn+12.776
 behaviour+12.593
 Resistance+12.577
Neg logit contributions
 semester-10.620
Feb-8.873
EMBER-8.227
 weeks-8.169
 hrs-8.069
Tokenist
Token ID396
Feature activation+2.00e+01

Pos logit contributions
 lifestyles+8.586
 personalities+8.098
 techn+8.060
 voices+8.011
 behaviour+7.825
Neg logit contributions
 semester-13.297
Feb-12.079
EMBER-11.273
imeo-11.035
 weeks-10.983
Token TV
Token ID3195
Feature activation+5.93e+00

Pos logit contributions
 lifestyles+17.308
 techn+16.651
 voices+16.514
 personalities+16.483
 masculinity+16.286
Neg logit contributions
 semester-11.459
Feb-10.720
imeo-9.289
EMBER-9.168
imester-8.716
Token
Token ID447
Feature activation-2.26e+00

Pos logit contributions
 lifestyles+5.273
 personalities+5.104
 behaviour+4.915
 techn+4.909
 voices+4.892
Neg logit contributions
 semester-4.538
Feb-4.032
EMBER-3.628
imeo-3.590
 weeks-3.580
Token
Token ID251
Feature activation+1.70e+01

Pos logit contributions
 semester+1.854
Feb+1.634
EMBER+1.504
 weeks+1.501
imeo+1.465
Neg logit contributions
 lifestyles-1.925
 personalities-1.858
 behaviour-1.780
 techn-1.774
 voices-1.771
Token with
Token ID351
Feature activation+8.25e+00

Pos logit contributions
 lifestyles+14.037
 personalities+13.704
 behaviour+13.406
 techn+13.360
 voices+13.359
Neg logit contributions
 semester-11.010
Feb-9.688
EMBER-8.971
 hrs-8.858
imeo-8.705
Token some
Token ID617
Feature activation-2.95e-01

Pos logit contributions
 lifestyles+5.754
 personalities+5.558
 techn+5.331
 voices+5.291
 behaviour+5.271
Neg logit contributions
 semester-7.743
Feb-7.043
EMBER-6.558
imeo-6.440
 weeks-6.416
Token sm
Token ID895
Feature activation+6.85e+00

Pos logit contributions
 lifestyles+0.634
 personalities+0.609
 behaviour+0.580
 techn+0.579
 voices+0.577
Neg logit contributions
 semester-0.746
Feb-0.666
EMBER-0.618
 weeks-0.617
imeo-0.604
Tokenearing
Token ID6648
Feature activation+1.28e+01

Pos logit contributions
 lifestyles+5.629
 personalities+5.420
 behaviour+5.237
 voices+5.223
 techn+5.200
Neg logit contributions
 semester-5.683
Feb-4.968
EMBER-4.652
 weeks-4.541
 hrs-4.462
Token of
Token ID286
Feature activation+1.25e+01

Pos logit contributions
 lifestyles+13.721
 personalities+13.563
 behaviour+13.326
 voices+13.197
 techn+13.102
Neg logit contributions
 semester-5.928
Feb-5.165
EMBER-4.749
imeo-4.685
imester-4.432
Token a
Token ID257
Feature activation+3.76e+00

Pos logit contributions
 lifestyles+8.527
 personalities+8.414
 voices+8.001
 behaviour+7.872
 techn+7.831
Neg logit contributions
 semester-11.265
Feb-10.368
EMBER-9.682
imeo-9.652
imester-9.439
Token wholly
Token ID18174
Feature activation+8.80e-01

Pos logit contributions
 lifestyles+2.593
 personalities+2.484
 behaviour+2.361
 techn+2.355
 voices+2.343
Neg logit contributions
 semester-3.672
Feb-3.323
EMBER-3.103
 weeks-3.085
imeo-3.054
Token benevolent
Token ID45599
Feature activation+1.96e+01

Pos logit contributions
 lifestyles+0.638
 personalities+0.609
 behaviour+0.581
 techn+0.576
 voices+0.576
Neg logit contributions
 semester-0.834
Feb-0.747
 weeks-0.698
EMBER-0.695
 hrs-0.679
Token foundation
Token ID8489
Feature activation+4.22e+00

Pos logit contributions
 lifestyles+15.892
 techn+15.680
 personalities+15.678
 personality+15.591
 behaviour+15.398
Neg logit contributions
 semester-12.437
Feb-11.575
imester-10.841
imeo-10.673
 hrs-10.320
Token,
Token ID11
Feature activation+8.81e+00

Pos logit contributions
 lifestyles+4.769
 personalities+4.664
 techn+4.525
 behaviour+4.521
 voices+4.499
Neg logit contributions
 semester-2.221
Feb-1.848
EMBER-1.605
imeo-1.581
 weeks-1.541
Token due
Token ID2233
Feature activation+2.69e+00

Pos logit contributions
 lifestyles+7.007
 personalities+6.780
 techn+6.516
 behaviour+6.489
 voices+6.471
Neg logit contributions
 semester-7.393
Feb-6.618
EMBER-6.177
imeo-6.052
 hrs-5.998
Token only
Token ID691
Feature activation+3.75e-01

Pos logit contributions
 lifestyles+2.536
 personalities+2.463
 behaviour+2.371
 techn+2.364
 voices+2.360
Neg logit contributions
 semester-1.947
Feb-1.690
EMBER-1.537
 weeks-1.522
imeo-1.489
Token to
Token ID284
Feature activation+5.52e+00

Pos logit contributions
 lifestyles+0.367
 personalities+0.356
 behaviour+0.343
 techn+0.343
 voices+0.342
Neg logit contributions
 semester-0.259
Feb-0.223
EMBER-0.201
 weeks-0.200
imeo-0.195
Token same
Token ID976
Feature activation-4.36e+00

Pos logit contributions
 semester+3.056
Feb+2.754
 weeks+2.657
EMBER+2.590
 hrs+2.549
Neg logit contributions
 lifestyles-1.610
 personalities-1.538
 behaviour-1.441
 Responsibility-1.439
 Resistance-1.438
Token market
Token ID1910
Feature activation+2.59e-01

Pos logit contributions
 semester+4.566
Feb+4.066
 weeks+3.974
EMBER+3.820
 hrs+3.776
Neg logit contributions
 lifestyles-2.526
 personalities-2.391
 Responsibility-2.293
 Flavoring-2.254
 Resistance-2.236
Token forces
Token ID3386
Feature activation-3.78e+00

Pos logit contributions
 lifestyles+0.122
 personalities+0.114
 behaviour+0.105
 techn+0.105
 voices+0.104
Neg logit contributions
 semester-0.309
Feb-0.283
 weeks-0.270
EMBER-0.269
 hrs-0.264
Token.
Token ID13
Feature activation+4.71e+00

Pos logit contributions
 semester+1.902
Feb+1.529
 weeks+1.340
EMBER+1.306
 hrs+1.241
Neg logit contributions
 lifestyles-4.390
 personalities-4.266
 behaviour-4.135
 voices-4.118
 techn-4.115
Token Ne
Token ID3169
Feature activation+6.06e+00

Pos logit contributions
 lifestyles+3.120
 personalities+2.966
 behaviour+2.819
 techn+2.819
 voices+2.815
Neg logit contributions
 semester-4.719
Feb-4.238
EMBER-3.979
 weeks-3.960
imeo-3.928
Tokenoliberal
Token ID28525
Feature activation+1.96e+01

Pos logit contributions
 lifestyles+4.344
 personalities+4.119
 techn+4.012
 behaviour+4.002
 voices+3.974
Neg logit contributions
 semester-5.636
Feb-4.999
EMBER-4.738
 weeks-4.645
 hrs-4.626
Token analysts
Token ID13440
Feature activation+7.02e+00

Pos logit contributions
 lifestyles+14.765
 personalities+14.417
 techn+14.164
 behaviour+14.035
 voices+13.878
Neg logit contributions
 semester-14.070
Feb-12.740
imeo-12.023
EMBER-11.749
imester-11.693
Token similarly
Token ID12470
Feature activation-8.12e-01

Pos logit contributions
 lifestyles+5.889
 personalities+5.727
 techn+5.522
 voices+5.519
 behaviour+5.501
Neg logit contributions
 semester-5.525
Feb-4.942
EMBER-4.589
imeo-4.545
 hrs-4.416
Token blame
Token ID8138
Feature activation+1.06e+01

Pos logit contributions
 semester+0.708
Feb+0.626
 weeks+0.582
EMBER+0.576
 hrs+0.566
Neg logit contributions
 lifestyles-0.652
 personalities-0.626
 behaviour-0.597
 techn-0.594
 voices-0.592
Token the
Token ID262
Feature activation+6.18e+00

Pos logit contributions
 lifestyles+7.818
 personalities+7.562
 techn+7.268
 behaviour+7.195
 voices+7.150
Neg logit contributions
 semester-9.240
Feb-8.538
EMBER-7.925
imeo-7.849
 hrs-7.664
Token 2001
Token ID5878
Feature activation-4.33e+00

Pos logit contributions
 lifestyles+4.500
 personalities+4.320
 techn+4.136
 behaviour+4.132
 voices+4.092
Neg logit contributions
 semester-5.734
Feb-5.193
EMBER-4.819
imeo-4.757
 weeks-4.744
TokenU
Token ID52
Feature activation-3.20e+00

Pos logit contributions
 semester+1.885
Feb+1.680
EMBER+1.511
 weeks+1.495
imeo+1.446
Neg logit contributions
 lifestyles-2.443
 personalities-2.355
 behaviour-2.263
 techn-2.261
 voices-2.249
Token.
Token ID13
Feature activation+3.60e+00

Pos logit contributions
 semester+0.808
Feb+0.492
EMBER+0.301
 weeks+0.299
 hrs+0.252
Neg logit contributions
 lifestyles-4.535
 personalities-4.446
 behaviour-4.338
 techn-4.334
 voices-4.324
TokenS
Token ID50
Feature activation+5.62e-01

Pos logit contributions
 lifestyles+2.582
 personalities+2.503
 voices+2.448
 Behavior+2.419
 behaviour+2.417
Neg logit contributions
 semester-3.300
Feb-2.796
imeo-2.699
 challeng-2.673
 weeks-2.666
Token.
Token ID13
Feature activation+8.01e+00

Pos logit contributions
 lifestyles+0.781
 personalities+0.766
 behaviour+0.749
 techn+0.747
 voices+0.747
Neg logit contributions
 semester-0.155
Feb-0.097
EMBER-0.063
 weeks-0.063
imeo-0.059
Token Immigration
Token ID18204
Feature activation+1.08e+01

Pos logit contributions
 lifestyles+3.743
 personalities+3.603
 techn+3.345
 behaviour+3.297
 voices+3.288
Neg logit contributions
 semester-9.325
Feb-8.577
EMBER-8.092
imeo-8.057
 weeks-7.997
Token and
Token ID290
Feature activation+1.94e+01

Pos logit contributions
 lifestyles+5.264
 personalities+5.211
 techn+4.981
 behaviour+4.843
 voices+4.790
Neg logit contributions
 semester-12.007
Feb-10.972
EMBER-10.468
iatus-10.281
imeo-10.278
Token Customs
Token ID23888
Feature activation+1.40e+01

Pos logit contributions
 Resistance+8.420
 Policies+8.358
 Responsibility+8.318
 Controls+8.186
 personalities+7.923
Neg logit contributions
 semester-19.553
Feb-17.604
iatus-16.891
imeo-16.823
EMBER-16.583
Token Enforcement
Token ID19198
Feature activation+1.30e+01

Pos logit contributions
 personalities+6.367
 Resistance+6.276
 Responsibility+6.245
 lifestyles+6.228
 voices+6.133
Neg logit contributions
 semester-15.196
Feb-13.598
iatus-13.320
EMBER-12.921
imeo-12.832
Token forb
Token ID11747
Feature activation+1.09e+01

Pos logit contributions
 lifestyles+10.724
 personalities+10.563
 techn+10.340
 voices+10.196
 behaviour+10.135
Neg logit contributions
 semester-9.232
Feb-8.276
imester-7.840
imeo-7.764
EMBER-7.680
Tokenade
Token ID671
Feature activation+1.29e+01

Pos logit contributions
 lifestyles+2.982
 voices+2.779
 personalities+2.688
 behaviour+2.589
 techn+2.545
Neg logit contributions
 semester-13.974
Feb-12.666
EMBER-12.475
 weeks-12.214
 hrs-12.151
Token his
Token ID465
Feature activation+4.83e+00

Pos logit contributions
 lifestyles+7.502
 personalities+7.339
 voices+6.993
 behaviour+6.967
 techn+6.930
Neg logit contributions
 semester-12.548
Feb-11.503
EMBER-10.922
imeo-10.792
imester-10.687
Token as
Token ID355
Feature activation+2.62e+00

Pos logit contributions
 semester+1.388
Feb+1.200
 weeks+1.106
EMBER+1.091
imeo+1.063
Neg logit contributions
 lifestyles-1.693
 personalities-1.628
 behaviour-1.570
 techn-1.562
 voices-1.558
Token the
Token ID262
Feature activation+2.75e+00

Pos logit contributions
 lifestyles+1.743
 personalities+1.672
 behaviour+1.581
 techn+1.576
 voices+1.575
Neg logit contributions
 semester-2.620
Feb-2.370
EMBER-2.222
 weeks-2.202
imeo-2.170
Token cab
Token ID16212
Feature activation+3.90e+00

Pos logit contributions
 lifestyles+2.277
 personalities+2.201
 behaviour+2.106
 techn+2.104
 voices+2.103
Neg logit contributions
 semester-2.300
Feb-2.044
EMBER-1.891
 weeks-1.862
imeo-1.838
Tokenler
Token ID1754
Feature activation+6.95e+00

Pos logit contributions
 lifestyles+2.814
 personalities+2.726
 behaviour+2.593
 techn+2.579
 voices+2.575
Neg logit contributions
 semester-3.652
Feb-3.271
EMBER-3.041
 weeks-3.023
imeo-3.001
Token
Token ID447
Feature activation-1.01e+00

Pos logit contributions
 lifestyles+6.480
 personalities+6.347
 behaviour+6.132
 voices+6.114
 techn+6.091
Neg logit contributions
 semester-4.781
Feb-4.161
EMBER-3.785
imeo-3.694
imester-3.653
Token
Token ID247
Feature activation+1.94e+01

Pos logit contributions
 semester+0.819
Feb+0.721
EMBER+0.663
 weeks+0.661
imeo+0.645
Neg logit contributions
 lifestyles-0.868
 personalities-0.837
 behaviour-0.803
 techn-0.800
 voices-0.798
Tokens
Token ID82
Feature activation+8.03e+00

Pos logit contributions
 personalities+14.841
 lifestyles+14.787
 voices+14.489
 behaviour+14.267
 Responsibility+14.183
Neg logit contributions
 semester-12.083
Feb-10.404
EMBER-9.805
imeo-9.654
iatus-9.450
Token most
Token ID749
Feature activation-2.69e+00

Pos logit contributions
 lifestyles+6.273
 personalities+6.129
 voices+5.928
 behaviour+5.912
 techn+5.860
Neg logit contributions
 semester-6.563
Feb-5.919
EMBER-5.443
imeo-5.335
imester-5.301
Token watched
Token ID7342
Feature activation+4.04e+00

Pos logit contributions
 semester+2.066
Feb+1.794
 weeks+1.675
EMBER+1.618
 hrs+1.591
Neg logit contributions
 lifestyles-2.435
 personalities-2.325
 behaviour-2.241
 techn-2.228
 Responsibility-2.215
Token series
Token ID2168
Feature activation-2.85e+00

Pos logit contributions
 lifestyles+3.238
 personalities+3.139
 behaviour+2.994
 techn+2.992
 voices+2.983
Neg logit contributions
 semester-3.454
Feb-3.093
EMBER-2.859
 weeks-2.814
imeo-2.800
Token launch
Token ID4219
Feature activation-1.00e+00

Pos logit contributions
 semester+2.077
Feb+1.799
 weeks+1.648
EMBER+1.633
 hrs+1.581
Neg logit contributions
 lifestyles-2.680
 personalities-2.580
 behaviour-2.487
 techn-2.480
 voices-2.471
Tokenthe
Token ID1169
Feature activation+6.54e+00

Pos logit contributions
 lifestyles+4.959
 personalities+4.825
 behaviour+4.593
 techn+4.588
 voices+4.570
Neg logit contributions
 semester-5.741
Feb-5.074
EMBER-4.762
 weeks-4.711
imeo-4.662
Token petty
Token ID25229
Feature activation+9.11e+00

Pos logit contributions
 lifestyles+4.647
 personalities+4.527
 behaviour+4.326
 techn+4.321
 voices+4.290
Neg logit contributions
 semester-6.061
Feb-5.522
EMBER-5.163
imeo-5.077
 weeks-5.042
Token-
Token ID12
Feature activation+1.41e+01

Pos logit contributions
 lifestyles+8.438
 personalities+8.276
 techn+7.942
 behaviour+7.901
 voices+7.885
Neg logit contributions
 semester-6.261
Feb-5.550
EMBER-5.110
imeo-4.947
 weeks-4.856
Tokenbour
Token ID6084
Feature activation+7.06e+00

Pos logit contributions
 lifestyles+7.490
 personalities+7.093
 techn+6.948
 behaviour+6.752
 nationalism+6.568
Neg logit contributions
 semester-14.244
Feb-12.643
EMBER-12.257
 weeks-12.117
 hrs-12.097
Tokenge
Token ID469
Feature activation+8.32e+00

Pos logit contributions
 lifestyles+2.027
 personalities+1.760
 behaviour+1.647
 techn+1.587
 voices+1.576
Neg logit contributions
 semester-9.528
Feb-8.866
EMBER-8.632
 weeks-8.441
imeo-8.373
Tokenois
Token ID10924
Feature activation+1.92e+01

Pos logit contributions
 lifestyles+7.263
 personalities+7.047
 techn+6.815
 behaviour+6.776
 voices+6.693
Neg logit contributions
 semester-6.241
Feb-5.432
EMBER-5.069
 weeks-4.934
 hrs-4.840
Token intellig
Token ID10878
Feature activation+9.95e+00

Pos logit contributions
 lifestyles+15.491
 personalities+15.464
 techn+15.219
 voices+14.809
 personality+14.803
Neg logit contributions
 semester-11.954
Feb-10.960
EMBER-10.302
imester-10.045
imeo-9.999
Tokenents
Token ID658
Feature activation+1.50e+01

Pos logit contributions
 lifestyles+5.751
 personalities+5.679
 techn+5.513
 voices+5.385
 behaviour+5.314
Neg logit contributions
 semester-9.865
Feb-9.023
EMBER-8.603
 weeks-8.357
 apiece-8.259
Tokenia
Token ID544
Feature activation+6.00e+00

Pos logit contributions
 lifestyles+6.640
 voices+6.144
 techn+6.128
 personalities+6.082
 behaviour+5.996
Neg logit contributions
 semester-15.926
Feb-14.508
EMBER-14.108
 weeks-13.748
imeo-13.668
Token resisted
Token ID26643
Feature activation+1.11e+01

Pos logit contributions
 lifestyles+5.356
 personalities+5.227
 voices+5.058
 techn+5.047
 behaviour+5.040
Neg logit contributions
 semester-4.434
Feb-3.918
EMBER-3.607
imeo-3.530
 weeks-3.513
Token en
Token ID551
Feature activation+2.74e+00

Pos logit contributions
 lifestyles+9.804
 personalities+9.599
 techn+9.365
 behaviour+9.295
 voices+9.266
Neg logit contributions
 semester-7.840
Feb-6.874
EMBER-6.414
imeo-6.149
 hrs-6.113
Token may
Token ID743
Feature activation-2.68e+00

Pos logit contributions
 semester+1.118
Feb+0.976
 weeks+0.897
EMBER+0.891
 hrs+0.869
Neg logit contributions
 lifestyles-1.289
 personalities-1.244
 behaviour-1.191
 techn-1.189
 voices-1.187
Token hear
Token ID3285
Feature activation+1.49e+00

Pos logit contributions
 semester+2.138
Feb+1.851
 weeks+1.742
EMBER+1.699
 hrs+1.673
Neg logit contributions
 lifestyles-2.339
 personalities-2.254
 behaviour-2.145
 techn-2.140
 voices-2.131
Token that
Token ID326
Feature activation+2.57e+00

Pos logit contributions
 lifestyles+1.139
 personalities+1.090
 behaviour+1.037
 techn+1.034
 voices+1.026
Neg logit contributions
 semester-1.354
Feb-1.205
 weeks-1.127
EMBER-1.119
 hrs-1.095
Token GHC
Token ID46615
Feature activation+4.92e+00

Pos logit contributions
 lifestyles+1.964
 personalities+1.888
 behaviour+1.803
 techn+1.795
 voices+1.791
Neg logit contributions
 semester-2.336
Feb-2.091
EMBER-1.944
 weeks-1.932
imeo-1.899
Token
Token ID447
Feature activation+1.10e+00

Pos logit contributions
 lifestyles+4.044
 personalities+3.931
 behaviour+3.793
 voices+3.756
 techn+3.753
Neg logit contributions
 semester-4.094
Feb-3.643
EMBER-3.344
 weeks-3.304
imeo-3.283
Token
Token ID247
Feature activation+1.92e+01

Pos logit contributions
 lifestyles+0.871
 personalities+0.849
 behaviour+0.810
 voices+0.809
 techn+0.803
Neg logit contributions
 semester-0.944
Feb-0.838
 weeks-0.775
imeo-0.770
EMBER-0.770
Tokens
Token ID82
Feature activation+1.12e+01

Pos logit contributions
 personalities+10.213
 behaviour+10.193
 lifestyles+10.023
 voices+9.649
 Behavior+9.540
Neg logit contributions
 semester-16.880
Feb-15.327
EMBER-14.687
imeo-14.472
iatus-14.030
Token garbage
Token ID15413
Feature activation+9.24e+00

Pos logit contributions
 lifestyles+8.419
 behaviour+8.306
 personalities+8.235
 voices+7.901
 techn+7.900
Neg logit contributions
 semester-9.159
Feb-8.492
EMBER-7.864
imeo-7.769
imester-7.539
Token collector
Token ID22967
Feature activation+8.31e+00

Pos logit contributions
 lifestyles+5.086
 personalities+4.846
 behaviour+4.825
 techn+4.638
 voices+4.523
Neg logit contributions
 semester-9.831
Feb-9.128
EMBER-8.566
imeo-8.498
imester-8.344
Token is
Token ID318
Feature activation+2.78e+00

Pos logit contributions
 lifestyles+6.041
 personalities+5.875
 behaviour+5.761
 voices+5.602
 techn+5.602
Neg logit contributions
 semester-7.437
Feb-6.830
EMBER-6.364
imeo-6.283
 hrs-6.096
Token well
Token ID880
Feature activation-5.33e+00

Pos logit contributions
 lifestyles+2.228
 personalities+2.152
 behaviour+2.073
 techn+2.058
 voices+2.046
Neg logit contributions
 semester-2.392
Feb-2.137
EMBER-1.980
 weeks-1.953
imeo-1.929
Token
Token ID198
Feature activation-4.59e+00

Pos logit contributions
 lifestyles+3.003
 personalities+2.875
 behaviour+2.750
 voices+2.745
 techn+2.744
Neg logit contributions
 semester-3.650
Feb-3.246
EMBER-3.019
 weeks-3.007
imeo-2.968
Token
Token ID198
Feature activation-1.83e+00

Pos logit contributions
 semester+3.353
Feb+3.011
 weeks+2.730
EMBER+2.669
 hrs+2.619
Neg logit contributions
 lifestyles-4.307
 personalities-4.174
 techn-3.976
 behaviour-3.932
 opinions-3.898
Token
Token ID447
Feature activation-4.85e+00

Pos logit contributions
 semester+1.325
Feb+1.169
EMBER+1.058
 weeks+1.043
imeo+1.018
Neg logit contributions
 lifestyles-1.726
 personalities-1.671
 techn-1.604
 behaviour-1.603
 voices-1.598
Token
Token ID250
Feature activation+1.18e+01

Pos logit contributions
 semester+3.726
Feb+3.267
EMBER+3.006
 weeks+2.995
 hrs+2.933
Neg logit contributions
 lifestyles-4.355
 personalities-4.172
 behaviour-4.025
 techn-4.016
 voices-3.974
TokenT
Token ID51
Feature activation+7.33e-01

Pos logit contributions
 lifestyles+9.267
 personalities+8.948
 behaviour+8.719
 Behavior+8.672
 voices+8.664
Neg logit contributions
 semester-9.139
Feb-7.316
 weeks-7.232
imester-7.063
 hrs-7.023
Tokenoxic
Token ID18047
Feature activation+1.91e+01

Pos logit contributions
 lifestyles+0.514
 personalities+0.493
 behaviour+0.469
 techn+0.467
 voices+0.466
Neg logit contributions
 semester-0.710
Feb-0.637
EMBER-0.595
 weeks-0.592
 hrs-0.583
Token or
Token ID393
Feature activation+1.18e+01

Pos logit contributions
 lifestyles+14.101
 personalities+13.455
 behaviour+13.252
 elements+12.915
 voices+12.839
Neg logit contributions
 semester-13.849
Feb-12.485
EMBER-11.645
imeo-11.600
 hrs-11.147
Token harmful
Token ID13568
Feature activation+1.60e+01

Pos logit contributions
 lifestyles+8.141
 personalities+7.670
 behaviour+7.623
 techn+7.518
 Resistance+7.380
Neg logit contributions
 semester-10.446
Feb-9.454
EMBER-8.992
 hrs-8.670
imeo-8.578
Token al
Token ID435
Feature activation+5.42e+00

Pos logit contributions
 lifestyles+12.750
 behaviour+12.056
 personalities+12.030
 voices+11.693
 elements+11.690
Neg logit contributions
 semester-11.727
Feb-10.789
EMBER-9.938
imeo-9.881
imester-9.672
Tokengal
Token ID13528
Feature activation+1.58e+01

Pos logit contributions
 lifestyles+3.824
 personalities+3.633
 voices+3.524
 behaviour+3.493
 techn+3.434
Neg logit contributions
 semester-5.105
Feb-4.554
EMBER-4.342
 weeks-4.234
 hrs-4.196
Token blo
Token ID24924
Feature activation+5.16e+00

Pos logit contributions
 lifestyles+10.666
 personalities+9.969
 behaviour+9.920
 voices+9.685
 techn+9.416
Neg logit contributions
 semester-13.710
Feb-12.371
EMBER-11.664
imeo-11.624
 hrs-11.350
Token the
Token ID262
Feature activation+5.16e+00

Pos logit contributions
 lifestyles+5.999
 personalities+5.929
 voices+5.587
 behaviour+5.586
 techn+5.573
Neg logit contributions
 semester-10.452
Feb-9.581
imeo-8.934
EMBER-8.931
 hrs-8.771
Token Russian
Token ID3394
Feature activation+5.99e+00

Pos logit contributions
 lifestyles+3.000
 personalities+2.876
 behaviour+2.703
 techn+2.690
 voices+2.688
Neg logit contributions
 semester-5.559
Feb-5.083
EMBER-4.775
 weeks-4.729
imeo-4.719
Token government
Token ID1230
Feature activation-9.39e-01

Pos logit contributions
 lifestyles+2.925
 personalities+2.762
 behaviour+2.583
 techn+2.563
 voices+2.551
Neg logit contributions
 semester-6.988
Feb-6.462
EMBER-6.054
 weeks-6.035
imeo-6.011
Token,
Token ID11
Feature activation+5.50e+00

Pos logit contributions
 semester+0.604
Feb+0.513
 weeks+0.461
EMBER+0.459
 hrs+0.442
Neg logit contributions
 lifestyles-0.967
 personalities-0.938
 behaviour-0.905
 techn-0.903
 voices-0.901
Token misogyn
Token ID22795
Feature activation+1.09e+01

Pos logit contributions
 lifestyles+4.109
 personalities+3.986
 voices+3.804
 techn+3.793
 behaviour+3.781
Neg logit contributions
 semester-4.979
Feb-4.465
EMBER-4.161
 weeks-4.076
imeo-4.068
Tokenistic
Token ID2569
Feature activation+1.91e+01

Pos logit contributions
 lifestyles+4.263
 personalities+3.959
 behaviour+3.794
 voices+3.624
 techn+3.580
Neg logit contributions
 semester-13.275
Feb-12.130
EMBER-11.629
 weeks-11.425
 hrs-11.375
Token and
Token ID290
Feature activation+9.46e+00

Pos logit contributions
 lifestyles+15.166
 behaviour+14.789
 personalities+14.726
 voices+14.252
 opinions+14.216
Neg logit contributions
 semester-13.284
Feb-12.336
imeo-11.745
iatus-11.506
imester-11.490
Token hateful
Token ID30367
Feature activation+1.26e+01

Pos logit contributions
 lifestyles+6.164
 personalities+5.933
 behaviour+5.765
 techn+5.686
 voices+5.604
Neg logit contributions
 semester-9.111
Feb-8.317
imeo-7.765
EMBER-7.753
 hrs-7.629
Token rhetoric
Token ID13214
Feature activation+3.76e+00

Pos logit contributions
 lifestyles+10.844
 personalities+10.655
 behaviour+10.503
 voices+10.303
 opinions+10.248
Neg logit contributions
 semester-9.180
Feb-8.198
imeo-7.648
EMBER-7.555
iatus-7.521
Token and
Token ID290
Feature activation+4.39e+00

Pos logit contributions
 lifestyles+3.507
 personalities+3.420
 voices+3.293
 behaviour+3.290
 techn+3.276
Neg logit contributions
 semester-2.738
Feb-2.381
EMBER-2.181
imeo-2.131
 weeks-2.117
Token general
Token ID2276
Feature activation+2.78e+00

Pos logit contributions
 lifestyles+2.799
 personalities+2.669
 behaviour+2.529
 voices+2.506
 techn+2.501
Neg logit contributions
 semester-4.529
Feb-4.111
EMBER-3.862
 weeks-3.829
imeo-3.791
Token.[
Token ID3693
Feature activation+2.50e+00

Pos logit contributions
 lifestyles+10.832
 personalities+10.626
 behaviour+10.502
 voices+10.419
 techn+10.265
Neg logit contributions
 semester-4.343
Feb-3.632
EMBER-3.196
imeo-3.097
imester-3.031
Token107
Token ID15982
Feature activation-1.31e+00

Pos logit contributions
 lifestyles+2.550
 personalities+2.479
 behaviour+2.401
 voices+2.399
 techn+2.388
Neg logit contributions
 semester-1.614
Feb-1.341
EMBER-1.215
 weeks-1.212
imeo-1.173
Token]
Token ID60
Feature activation+5.42e+00

Pos logit contributions
 semester+1.008
Feb+0.890
 weeks+0.810
EMBER+0.806
imeo+0.792
Neg logit contributions
 lifestyles-1.171
 personalities-1.126
 behaviour-1.082
 techn-1.074
 voices-1.072
Token Soc
Token ID3345
Feature activation+9.64e+00

Pos logit contributions
 lifestyles+3.904
 personalities+3.739
 behaviour+3.570
 Resistance+3.569
 voices+3.564
Neg logit contributions
 semester-5.076
Feb-4.510
EMBER-4.231
 weeks-4.202
imeo-4.169
Tokenio
Token ID952
Feature activation+1.12e+01

Pos logit contributions
 lifestyles+6.440
 personalities+6.150
 behaviour+5.886
 techn+5.831
 voices+5.829
Neg logit contributions
 semester-9.186
Feb-8.168
EMBER-7.839
 weeks-7.725
 hrs-7.616
Tokeneconomic
Token ID17079
Feature activation+1.90e+01

Pos logit contributions
 lifestyles+10.197
 personalities+9.947
 behaviour+9.663
 techn+9.620
 personality+9.377
Neg logit contributions
 semester-7.710
Feb-6.683
EMBER-6.140
 weeks-6.097
 hrs-6.076
Token factors
Token ID5087
Feature activation+8.24e+00

Pos logit contributions
 lifestyles+15.095
 behaviour+14.592
 personalities+14.431
 Behavior+14.088
 voices+14.027
Neg logit contributions
 semester-13.000
Feb-12.274
EMBER-11.650
imeo-10.972
imester-10.790
Token also
Token ID635
Feature activation+5.51e-01

Pos logit contributions
 lifestyles+7.231
 personalities+7.073
 behaviour+6.857
 voices+6.785
 techn+6.749
Neg logit contributions
 semester-6.035
Feb-5.403
EMBER-4.980
imeo-4.875
 weeks-4.742
Token have
Token ID423
Feature activation+4.35e+00

Pos logit contributions
 lifestyles+0.444
 personalities+0.427
 behaviour+0.407
 techn+0.407
 voices+0.405
Neg logit contributions
 semester-0.478
Feb-0.423
 weeks-0.392
EMBER-0.390
 hrs-0.382
Token a
Token ID257
Feature activation+3.17e+00

Pos logit contributions
 lifestyles+3.407
 personalities+3.292
 behaviour+3.140
 voices+3.129
 techn+3.113
Neg logit contributions
 semester-3.837
Feb-3.453
EMBER-3.210
 weeks-3.147
 hrs-3.114
Token direct
Token ID1277
Feature activation+8.27e+00

Pos logit contributions
 lifestyles+2.187
 personalities+2.103
 behaviour+2.007
 techn+1.991
 voices+1.984
Neg logit contributions
 semester-3.088
Feb-2.815
EMBER-2.626
 weeks-2.594
 hrs-2.566
Token
Token ID447
Feature activation-6.01e-01

Pos logit contributions
 lifestyles+3.033
 personalities+2.918
 behaviour+2.790
 techn+2.777
 voices+2.772
Neg logit contributions
 semester-3.464
Feb-3.095
EMBER-2.879
 weeks-2.851
imeo-2.816
Token
Token ID247
Feature activation+1.41e+01

Pos logit contributions
 semester+0.434
Feb+0.376
EMBER+0.342
 weeks+0.340
 hrs+0.331
Neg logit contributions
 lifestyles-0.573
 personalities-0.553
 behaviour-0.534
 techn-0.532
 voices-0.529
Token practice
Token ID3357
Feature activation+5.97e+00

Pos logit contributions
 lifestyles+13.205
 personalities+12.972
 Resistance+12.605
 voices+12.540
 techn+12.420
Neg logit contributions
 semester-8.436
Feb-7.016
imeo-6.387
EMBER-6.267
 weeks-6.237
Token of
Token ID286
Feature activation+9.38e+00

Pos logit contributions
 lifestyles+6.292
 personalities+6.095
 behaviour+5.974
 techn+5.921
 voices+5.888
Neg logit contributions
 semester-3.471
Feb-2.929
EMBER-2.603
imeo-2.574
 weeks-2.511
Token incentiv
Token ID39678
Feature activation+1.49e+01

Pos logit contributions
 lifestyles+6.577
 personalities+6.247
 behaviour+6.078
 techn+6.038
 voices+5.926
Neg logit contributions
 semester-8.444
Feb-7.781
imeo-7.266
EMBER-7.263
 hrs-7.089
Tokenizing
Token ID2890
Feature activation+1.90e+01

Pos logit contributions
 lifestyles+6.590
 personalities+6.044
 behaviour+5.973
 techn+5.618
 voices+5.513
Neg logit contributions
 semester-16.020
Feb-15.131
EMBER-14.163
imeo-14.138
 hrs-14.018
Token businesses
Token ID5692
Feature activation+3.39e+00

Pos logit contributions
 lifestyles+15.229
 behaviour+14.537
 personalities+14.474
 techn+14.242
 masculinity+14.156
Neg logit contributions
 semester-11.910
Feb-11.413
EMBER-10.587
imeo-10.540
imester-10.067
Token to
Token ID284
Feature activation+3.59e+00

Pos logit contributions
 lifestyles+3.204
 personalities+3.099
 behaviour+2.996
 techn+2.981
 voices+2.969
Neg logit contributions
 semester-2.448
Feb-2.121
EMBER-1.933
 weeks-1.901
imeo-1.890
Token build
Token ID1382
Feature activation+3.55e+00

Pos logit contributions
 lifestyles+2.719
 personalities+2.612
 behaviour+2.505
 techn+2.489
 voices+2.482
Neg logit contributions
 semester-3.250
Feb-2.929
EMBER-2.719
 weeks-2.683
imeo-2.666
Token here
Token ID994
Feature activation-1.14e+01

Pos logit contributions
 lifestyles+2.597
 personalities+2.484
 behaviour+2.365
 techn+2.357
 voices+2.349
Neg logit contributions
 semester-3.336
Feb-3.006
EMBER-2.801
 weeks-2.774
imeo-2.744
Token.
Token ID13
Feature activation+6.26e+00

Pos logit contributions
 semester+9.284
Feb+8.190
 weeks+7.788
.+7.712
EMBER+7.454
Neg logit contributions
 lifestyles-8.561
 personalities-8.365
 techn-7.977
 behaviour-7.928
 voices-7.871
Token
Token ID198
Feature activation-1.99e+00

Pos logit contributions
 lifestyles+3.735
 personalities+3.585
 techn+3.412
 voices+3.405
 behaviour+3.396
Neg logit contributions
 semester-4.855
Feb-4.373
EMBER-4.077
 weeks-4.033
imeo-3.994
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
 semester+1.585
Feb+1.401
 weeks+1.284
EMBER+1.278
 hrs+1.246
Neg logit contributions
 lifestyles-1.749
 personalities-1.690
 techn-1.612
 behaviour-1.612
 voices-1.600
Token"
Token ID1
Feature activation+3.90e+00

Pos logit contributions
 semester+0.859
Feb+0.750
EMBER+0.681
 weeks+0.676
imeo+0.658
Neg logit contributions
 lifestyles-1.104
 personalities-1.069
 behaviour-1.028
 techn-1.025
 voices-1.023
TokenAIR
Token ID42149
Feature activation+7.20e+00

Pos logit contributions
 lifestyles+3.538
 personalities+3.422
 behaviour+3.297
 voices+3.289
 techn+3.281
Neg logit contributions
 semester-2.917
Feb-2.468
 weeks-2.296
EMBER-2.263
imeo-2.245
Token
Token ID447
Feature activation+1.35e+00

Pos logit contributions
 lifestyles+5.203
 personalities+5.001
 voices+4.780
 techn+4.766
 behaviour+4.703
Neg logit contributions
 semester-6.590
Feb-5.972
EMBER-5.564
imeo-5.537
 weeks-5.494
Token
Token ID247
Feature activation+1.90e+01

Pos logit contributions
 lifestyles+1.053
 personalities+1.028
 voices+0.977
 behaviour+0.967
 techn+0.964
Neg logit contributions
 semester-1.177
Feb-1.047
 weeks-0.973
imeo-0.968
EMBER-0.959
Tokens
Token ID82
Feature activation+1.01e+01

Pos logit contributions
 lifestyles+14.129
 personalities+13.821
 voices+13.480
 techn+13.321
 opinions+13.298
Neg logit contributions
 semester-13.013
Feb-11.525
imeo-11.109
EMBER-10.985
 apiece-10.566
Token Health
Token ID3893
Feature activation+9.23e+00

Pos logit contributions
 lifestyles+7.407
 personalities+7.090
 techn+6.781
 opinions+6.779
 voices+6.776
Neg logit contributions
 semester-8.749
Feb-8.010
EMBER-7.438
imeo-7.428
imester-7.263
Token and
Token ID290
Feature activation+1.58e+01

Pos logit contributions
 lifestyles+7.286
 personalities+6.940
 techn+6.769
 Responsibility+6.721
 Resistance+6.705
Neg logit contributions
 semester-7.660
Feb-6.769
EMBER-6.392
 weeks-6.214
imeo-6.209
Token Social
Token ID5483
Feature activation+1.17e+01

Pos logit contributions
 lifestyles+8.981
 Behavior+8.490
 Resistance+8.170
 personalities+8.048
 Responsibility+7.988
Neg logit contributions
 semester-15.267
Feb-13.929
EMBER-13.487
imeo-13.286
imester-13.238
Token Development
Token ID7712
Feature activation+8.39e+00

Pos logit contributions
 lifestyles+7.720
 Responsibility+7.347
 Behavior+7.211
 personalities+7.147
 Resistance+7.014
Neg logit contributions
 semester-10.981
Feb-9.786
EMBER-9.379
imeo-9.101
 weeks-9.040
Token
Token ID198
Feature activation-3.01e+00

Pos logit contributions
 lifestyles+4.275
 personalities+4.093
 Resistance+3.970
 voices+3.940
 techn+3.939
Neg logit contributions
 semester-5.169
Feb-4.582
EMBER-4.291
 weeks-4.257
imeo-4.212
Token
Token ID198
Feature activation-6.82e-01

Pos logit contributions
 semester+2.307
Feb+2.053
 weeks+1.873
EMBER+1.848
 hrs+1.805
Neg logit contributions
 lifestyles-2.740
 personalities-2.649
 techn-2.523
 behaviour-2.513
 voices-2.487
TokenOur
Token ID5122
Feature activation+6.63e+00

Pos logit contributions
 semester+0.512
Feb+0.448
EMBER+0.408
 weeks+0.406
imeo+0.395
Neg logit contributions
 lifestyles-0.629
 personalities-0.608
 behaviour-0.584
 techn-0.583
 voices-0.581
Token nation
Token ID3277
Feature activation+6.10e-01

Pos logit contributions
 lifestyles+4.890
 personalities+4.675
 voices+4.507
 techn+4.447
 behaviour+4.431
Neg logit contributions
 semester-6.022
Feb-5.519
EMBER-5.128
imeo-5.043
 hrs-5.010
Token
Token ID447
Feature activation-1.97e+00

Pos logit contributions
 lifestyles+0.537
 personalities+0.518
 voices+0.498
 techn+0.497
 behaviour+0.497
Neg logit contributions
 semester-0.482
Feb-0.425
EMBER-0.391
 weeks-0.386
imeo-0.381
Token
Token ID247
Feature activation+1.90e+01

Pos logit contributions
 semester+1.603
Feb+1.411
EMBER+1.297
 weeks+1.295
imeo+1.265
Neg logit contributions
 lifestyles-1.691
 personalities-1.633
 behaviour-1.564
 techn-1.560
 voices-1.557
Tokens
Token ID82
Feature activation+8.41e+00

Pos logit contributions
 lifestyles+10.306
 personalities+9.851
 voices+9.732
 Responsibility+9.311
 Resistance+9.221
Neg logit contributions
 semester-16.683
Feb-15.084
EMBER-14.534
imeo-14.339
iatus-14.177
Token capital
Token ID3139
Feature activation-1.27e+00

Pos logit contributions
 lifestyles+5.873
 personalities+5.602
 voices+5.367
 techn+5.325
 behaviour+5.314
Neg logit contributions
 semester-7.881
Feb-7.260
EMBER-6.768
imeo-6.606
 hrs-6.592
Token is
Token ID318
Feature activation+2.12e+00

Pos logit contributions
 semester+1.116
Feb+0.987
 weeks+0.917
EMBER+0.912
 hrs+0.892
Neg logit contributions
 lifestyles-1.004
 personalities-0.965
 behaviour-0.924
 techn-0.920
 voices-0.913
Token rep
Token ID1128
Feature activation-5.86e-01

Pos logit contributions
 lifestyles+1.707
 personalities+1.644
 behaviour+1.571
 techn+1.570
 voices+1.564
Neg logit contributions
 semester-1.825
Feb-1.624
EMBER-1.503
 weeks-1.492
imeo-1.466
Tokenlete
Token ID5807
Feature activation+2.88e+00

Pos logit contributions
 semester+0.554
Feb+0.497
 weeks+0.462
EMBER+0.462
imeo+0.453
Neg logit contributions
 lifestyles-0.429
 personalities-0.412
 behaviour-0.391
 voices-0.389
 techn-0.386
Token.
Token ID13
Feature activation+5.52e+00

Pos logit contributions
 semester+0.725
Feb+0.595
EMBER+0.518
 weeks+0.517
imeo+0.494
Neg logit contributions
 lifestyles-1.511
 personalities-1.470
 behaviour-1.424
 techn-1.421
 voices-1.419
Token The
Token ID383
Feature activation+5.22e+00

Pos logit contributions
 lifestyles+3.781
 personalities+3.609
 techn+3.462
 Resistance+3.462
 voices+3.457
Neg logit contributions
 semester-5.335
Feb-4.757
EMBER-4.456
 weeks-4.431
imeo-4.417
Token Center
Token ID3337
Feature activation-5.12e-01

Pos logit contributions
 lifestyles+3.814
 personalities+3.669
 techn+3.495
 behaviour+3.488
 voices+3.484
Neg logit contributions
 semester-4.854
Feb-4.379
EMBER-4.073
imeo-4.016
 weeks-4.011
Token for
Token ID329
Feature activation+4.97e+00

Pos logit contributions
 semester+0.407
Feb+0.358
 weeks+0.328
EMBER+0.327
 hrs+0.319
Neg logit contributions
 lifestyles-0.450
 personalities-0.433
 behaviour-0.416
 techn-0.414
 voices-0.413
Token Respons
Token ID20549
Feature activation+5.36e+00

Pos logit contributions
 lifestyles+2.182
 personalities+2.027
 techn+1.892
 behaviour+1.869
 voices+1.851
Neg logit contributions
 semester-6.090
Feb-5.610
EMBER-5.338
 weeks-5.288
imeo-5.254
Tokenive
Token ID425
Feature activation+1.89e+01

Pos logit contributions
 lifestyles+1.782
 personalities+1.603
 behaviour+1.483
 techn+1.468
 voices+1.419
Neg logit contributions
 semester-7.160
Feb-6.590
EMBER-6.326
 weeks-6.269
 hrs-6.213
Token Politics
Token ID17554
Feature activation+3.16e+00

Pos logit contributions
 Technology+5.907
 Behavior+5.626
 lifestyles+5.279
 techn+5.209
 Resistance+5.133
Neg logit contributions
 semester-23.592
imeo-21.568
��-21.458
Feb-21.445
imester-21.252
Token has
Token ID468
Feature activation+1.37e+00

Pos logit contributions
 lifestyles+2.510
 personalities+2.423
 voices+2.315
 techn+2.314
 behaviour+2.299
Neg logit contributions
 semester-2.738
Feb-2.447
EMBER-2.284
 weeks-2.241
imeo-2.231
Token the
Token ID262
Feature activation+3.37e+00

Pos logit contributions
 lifestyles+1.189
 personalities+1.148
 behaviour+1.101
 techn+1.097
 voices+1.095
Neg logit contributions
 semester-1.095
Feb-0.962
EMBER-0.884
 weeks-0.883
imeo-0.860
Token full
Token ID1336
Feature activation-1.55e+00

Pos logit contributions
 lifestyles+2.652
 personalities+2.557
 techn+2.440
 voices+2.436
 behaviour+2.433
Neg logit contributions
 semester-2.966
Feb-2.652
EMBER-2.467
 weeks-2.434
imeo-2.405
Token list
Token ID1351
Feature activation-5.19e+00

Pos logit contributions
 semester+1.509
Feb+1.350
 weeks+1.274
EMBER+1.255
 hrs+1.238
Neg logit contributions
 lifestyles-1.085
 personalities-1.031
 behaviour-0.982
 voices-0.971
 techn-0.970
Token,
Token ID11
Feature activation+6.28e+00

Pos logit contributions
 semester+4.138
Feb+3.578
 weeks+3.342
EMBER+3.260
 hrs+3.238
Neg logit contributions
 lifestyles-5.016
 personalities-4.804
 behaviour-4.655
 techn-4.632
 voices-4.571
Token the
Token ID262
Feature activation+4.54e+00

Pos logit contributions
 lifestyles+4.855
 personalities+4.701
 voices+4.485
 behaviour+4.467
 techn+4.452
Neg logit contributions
 semester-5.492
Feb-4.919
EMBER-4.597
imeo-4.482
 weeks-4.469
Token way
Token ID835
Feature activation-1.48e+00

Pos logit contributions
 lifestyles+3.434
 personalities+3.317
 voices+3.170
 behaviour+3.157
 techn+3.137
Neg logit contributions
 semester-4.089
Feb-3.682
EMBER-3.456
 weeks-3.376
imeo-3.352
Token "
Token ID366
Feature activation+3.79e+00

Pos logit contributions
 semester+1.419
Feb+1.262
 weeks+1.194
EMBER+1.169
 hrs+1.161
Neg logit contributions
 lifestyles-1.052
 personalities-1.002
 behaviour-0.956
 techn-0.948
 voices-0.938
Tokenhom
Token ID26452
Feature activation+4.55e+00

Pos logit contributions
 lifestyles+3.193
 personalities+3.088
 behaviour+2.956
 voices+2.951
 techn+2.938
Neg logit contributions
 semester-3.119
Feb-2.719
EMBER-2.534
 weeks-2.520
imeo-2.466
Tokenosexual
Token ID8542
Feature activation+1.89e+01

Pos logit contributions
 lifestyles+3.014
 personalities+2.854
 behaviour+2.734
 voices+2.703
 techn+2.689
Neg logit contributions
 semester-4.566
Feb-4.100
EMBER-3.862
 weeks-3.829
 hrs-3.782
Tokens
Token ID82
Feature activation+9.52e+00

Pos logit contributions
 lifestyles+15.615
 personalities+14.919
 behaviour+14.630
 voices+14.441
 behavior+14.049
Neg logit contributions
 semester-12.669
Feb-11.722
EMBER-10.684
imester-10.584
imeo-10.417
Token"
Token ID1
Feature activation+8.51e+00

Pos logit contributions
 lifestyles+8.123
 personalities+7.821
 voices+7.525
 behaviour+7.497
 techn+7.397
Neg logit contributions
 semester-7.194
Feb-6.485
EMBER-5.979
imeo-5.828
imester-5.742
Token are
Token ID389
Feature activation+3.36e+00

Pos logit contributions
 lifestyles+7.000
 personalities+6.761
 voices+6.532
 behaviour+6.496
 techn+6.403
Neg logit contributions
 semester-6.800
Feb-6.194
EMBER-5.815
imeo-5.591
imester-5.532
Token described
Token ID3417
Feature activation+5.98e+00

Pos logit contributions
 lifestyles+2.825
 personalities+2.736
 behaviour+2.614
 techn+2.606
 voices+2.605
Neg logit contributions
 semester-2.779
Feb-2.476
EMBER-2.284
 weeks-2.251
imeo-2.221
Token in
Token ID287
Feature activation+1.42e+00

Pos logit contributions
 lifestyles+5.419
 personalities+5.236
 voices+5.081
 behaviour+5.060
 techn+4.993
Neg logit contributions
 semester-4.423
Feb-3.893
EMBER-3.647
imeo-3.487
imester-3.446
Token new
Token ID649
Feature activation+1.88e+00

Pos logit contributions
 lifestyles+2.725
 personalities+2.619
 techn+2.492
 behaviour+2.489
 voices+2.478
Neg logit contributions
 semester-3.405
Feb-3.061
EMBER-2.867
 weeks-2.822
imeo-2.791
Token hardware
Token ID6890
Feature activation+1.26e+00

Pos logit contributions
 lifestyles+1.319
 personalities+1.262
 behaviour+1.198
 techn+1.193
 voices+1.190
Neg logit contributions
 semester-1.833
Feb-1.649
EMBER-1.540
 weeks-1.538
imeo-1.508
Token,
Token ID11
Feature activation+7.16e+00

Pos logit contributions
 lifestyles+1.236
 personalities+1.198
 behaviour+1.154
 techn+1.152
 voices+1.149
Neg logit contributions
 semester-0.874
Feb-0.751
 weeks-0.678
EMBER-0.677
 hrs-0.656
Token Assassin
Token ID21401
Feature activation+7.57e+00

Pos logit contributions
 lifestyles+4.889
 personalities+4.679
 voices+4.440
 behaviour+4.432
 techn+4.431
Neg logit contributions
 semester-6.949
Feb-6.300
EMBER-5.927
 weeks-5.799
imeo-5.769
Token
Token ID447
Feature activation+1.65e+00

Pos logit contributions
 lifestyles+6.448
 personalities+6.248
 voices+6.015
 behaviour+5.939
 techn+5.921
Neg logit contributions
 semester-5.986
Feb-5.319
EMBER-4.933
imeo-4.834
 weeks-4.770
Token
Token ID247
Feature activation+1.88e+01

Pos logit contributions
 lifestyles+1.283
 personalities+1.256
 voices+1.197
 behaviour+1.185
 opinions+1.172
Neg logit contributions
 semester-1.440
Feb-1.272
 weeks-1.189
imeo-1.185
EMBER-1.177
Tokens
Token ID82
Feature activation+1.13e+01

Pos logit contributions
 voices+8.161
 lifestyles+7.860
 personalities+7.670
 behaviour+7.288
 opinions+7.116
Neg logit contributions
 semester-18.601
 challeng-18.231
 occas-16.902
 conclud-16.848
��-16.771
Token Creed
Token ID24299
Feature activation+9.38e+00

Pos logit contributions
 lifestyles+6.589
 personalities+6.204
 behaviour+6.040
 Resistance+6.007
 voices+6.003
Neg logit contributions
 semester-11.381
Feb-10.553
imeo-9.790
EMBER-9.718
 weeks-9.499
Token®
Token ID7461
Feature activation+1.49e+01

Pos logit contributions
 lifestyles+7.210
 personalities+6.930
 voices+6.638
 Resistance+6.528
 behaviour+6.517
Neg logit contributions
 semester-7.985
Feb-7.197
imeo-6.640
EMBER-6.560
 weeks-6.469
Token Liberation
Token ID29235
Feature activation+1.06e+01

Pos logit contributions
 lifestyles+9.276
 personalities+8.842
 Resistance+8.550
 voices+8.404
 behaviour+8.163
Neg logit contributions
 semester-13.719
Feb-12.487
imeo-11.821
EMBER-11.494
imester-11.374
Token HD
Token ID5572
Feature activation+1.24e+00

Pos logit contributions
 lifestyles+7.062
 personalities+6.725
 voices+6.531
 behaviour+6.399
 techn+6.350
Neg logit contributions
 semester-9.744
Feb-8.992
EMBER-8.366
imeo-8.269
iatus-8.079
Token;
Token ID26
Feature activation+5.83e+00

Pos logit contributions
 semester+3.503
Feb+3.027
 weeks+2.829
EMBER+2.766
 hrs+2.676
Neg logit contributions
 lifestyles-4.059
 personalities-3.924
 behaviour-3.746
 voices-3.727
 techn-3.711
Token thus
Token ID4145
Feature activation+2.67e+00

Pos logit contributions
 lifestyles+4.655
 personalities+4.481
 techn+4.299
 behaviour+4.299
 voices+4.271
Neg logit contributions
 semester-5.004
Feb-4.467
EMBER-4.145
imeo-4.084
 weeks-4.061
Token,
Token ID11
Feature activation+7.03e+00

Pos logit contributions
 lifestyles+2.311
 personalities+2.233
 behaviour+2.142
 techn+2.138
 voices+2.131
Neg logit contributions
 semester-2.142
Feb-1.888
EMBER-1.736
 weeks-1.721
imeo-1.694
Token Israel
Token ID2692
Feature activation+2.83e+00

Pos logit contributions
 lifestyles+5.426
 personalities+5.232
 techn+5.013
 behaviour+5.010
 voices+4.982
Neg logit contributions
 semester-6.171
Feb-5.543
EMBER-5.181
imeo-5.089
 hrs-5.016
Token
Token ID447
Feature activation-1.62e+00

Pos logit contributions
 lifestyles+2.215
 personalities+2.130
 behaviour+2.035
 techn+2.031
 voices+2.028
Neg logit contributions
 semester-2.514
Feb-2.245
EMBER-2.089
 weeks-2.072
imeo-2.044
Token
Token ID247
Feature activation+1.87e+01

Pos logit contributions
 semester+1.353
Feb+1.194
 weeks+1.101
EMBER+1.100
imeo+1.079
Neg logit contributions
 lifestyles-1.359
 personalities-1.314
 behaviour-1.256
 voices-1.253
 techn-1.251
Tokens
Token ID82
Feature activation+9.46e+00

Pos logit contributions
 voices+9.564
 personalities+9.520
 lifestyles+9.512
 behaviour+9.092
 Responsibility+8.862
Neg logit contributions
 semester-16.644
 challeng-15.657
Feb-14.982
��-14.625
iatus-14.483
Token ongoing
Token ID7044
Feature activation+3.13e+00

Pos logit contributions
 lifestyles+6.854
 personalities+6.572
 behaviour+6.426
 techn+6.384
 voices+6.310
Neg logit contributions
 semester-8.439
Feb-7.759
EMBER-7.220
imeo-7.191
 hrs-7.061
Token Juda
Token ID24771
Feature activation+7.98e+00

Pos logit contributions
 lifestyles+1.936
 personalities+1.843
 behaviour+1.732
 techn+1.726
 voices+1.722
Neg logit contributions
 semester-3.294
Feb-2.985
 weeks-2.807
EMBER-2.805
 hrs-2.750
Tokenisation
Token ID5612
Feature activation+9.07e+00

Pos logit contributions
 lifestyles+3.339
 personalities+3.034
 behaviour+2.954
 voices+2.825
 techn+2.776
Neg logit contributions
 semester-9.687
Feb-9.044
EMBER-8.522
 hrs-8.456
 weeks-8.453
Token and
Token ID290
Feature activation+8.06e+00

Pos logit contributions
 lifestyles+8.097
 behaviour+7.753
 personalities+7.734
 techn+7.612
 voices+7.548
Neg logit contributions
 semester-6.339
Feb-5.850
EMBER-5.450
imeo-5.407
 hrs-5.094
Token for
Token ID329
Feature activation-1.40e+00

Pos logit contributions
 semester+5.930
Feb+5.083
 weeks+4.794
 hrs+4.649
 apiece+4.616
Neg logit contributions
 lifestyles-6.749
 personalities-6.543
 techn-6.235
 behaviour-6.189
 voices-6.158
Token shorter
Token ID12238
Feature activation-2.25e+00

Pos logit contributions
 semester+1.156
Feb+1.010
 weeks+0.940
EMBER+0.929
 hrs+0.911
Neg logit contributions
 lifestyles-1.190
 personalities-1.150
 behaviour-1.099
 techn-1.098
 voices-1.091
Token tours
Token ID21284
Feature activation-1.27e+01

Pos logit contributions
 semester+2.020
Feb+1.789
 weeks+1.684
EMBER+1.656
 hrs+1.634
Neg logit contributions
 lifestyles-1.743
 personalities-1.680
 behaviour-1.596
 techn-1.595
 voices-1.582
Token throughout
Token ID3690
Feature activation-1.11e+01

Pos logit contributions
 semester+9.042
Feb+7.703
 weeks+7.529
.+7.091
 apiece+7.058
Neg logit contributions
 lifestyles-10.898
 personalities-10.619
 Responsibility-10.194
 techn-10.158
 Flavoring-10.116
Token the
Token ID262
Feature activation-1.29e+01

Pos logit contributions
 semester+10.554
Feb+9.172
 weeks+9.031
 afternoon+8.577
 hrs+8.490
Neg logit contributions
 lifestyles-7.404
 personalities-7.175
 voices-6.790
 Responsibility-6.730
 techn-6.678
Token day
Token ID1110
Feature activation-2.67e+01

Pos logit contributions
 semester+7.145
 weeks+5.095
Feb+5.022
 afternoon+4.944
 hrs+4.348
Neg logit contributions
 lifestyles-13.714
 personalities-13.461
 Responsibility-13.117
 voices-12.929
 techn-12.749
Token).
Token ID737
Feature activation+1.87e+00

Pos logit contributions
 semester+17.372
.+15.620
Feb+15.074
 weeks+14.980
 apiece+14.337
Neg logit contributions
 lifestyles-17.170
 personalities-16.673
 Flavoring-16.273
 Responsibility-15.834
 techn-15.785
Token
Token ID198
Feature activation-3.79e+00

Pos logit contributions
 lifestyles+1.510
 personalities+1.455
 behaviour+1.390
 techn+1.385
 voices+1.382
Neg logit contributions
 semester-1.615
Feb-1.435
EMBER-1.327
 weeks-1.325
 hrs-1.295
Token
Token ID198
Feature activation-1.89e+00

Pos logit contributions
 semester+2.833
Feb+2.530
 weeks+2.301
EMBER+2.262
 hrs+2.214
Neg logit contributions
 lifestyles-3.493
 personalities-3.387
 techn-3.221
 behaviour-3.200
 voices-3.166
TokenAll
Token ID3237
Feature activation-2.02e+00

Pos logit contributions
 semester+1.372
Feb+1.210
EMBER+1.094
 weeks+1.079
imeo+1.051
Neg logit contributions
 lifestyles-1.792
 personalities-1.735
 techn-1.668
 behaviour-1.668
 voices-1.660
Token tickets
Token ID8587
Feature activation-6.53e-01

Pos logit contributions
 semester+1.797
Feb+1.586
 weeks+1.495
EMBER+1.476
 hrs+1.443
Neg logit contributions
 lifestyles-1.562
 personalities-1.510
 behaviour-1.443
 techn-1.440
 voices-1.425
Token.
Token ID13
Feature activation-1.03e+01

Pos logit contributions
.+4.210
 semester+3.978
Feb+3.767
 weeks+2.401
EMBER+2.344
Neg logit contributions
 lifestyles-21.905
 personalities-21.523
 practition-21.077
avorite-20.810
 techn-20.559
Tokenm
Token ID76
Feature activation-1.96e+01

Pos logit contributions
 semester+5.684
Feb+5.585
.+4.851
 weeks+4.688
 hrs+4.472
Neg logit contributions
 lifestyles-10.872
 personalities-10.490
 techn-9.933
 behaviour-9.915
 opinions-9.839
Token.
Token ID13
Feature activation-1.12e+01

Pos logit contributions
.+6.914
 semester+6.885
Feb+6.058
EMBER+5.217
 weeks+5.117
Neg logit contributions
 lifestyles-21.556
 personalities-21.162
 behaviour-20.345
avorite-20.194
 techn-20.119
Token ET
Token ID12152
Feature activation-1.27e+01

Pos logit contributions
 semester+8.509
Feb+7.655
 weeks+7.253
 hrs+7.053
EMBER+6.975
Neg logit contributions
 lifestyles-9.014
 personalities-8.663
 behaviour-8.299
 voices-8.235
 Responsibility-8.228
Token on
Token ID319
Feature activation-1.17e+01

Pos logit contributions
 semester+7.116
Feb+6.151
 weeks+5.756
.+5.600
EMBER+5.529
Neg logit contributions
 lifestyles-12.811
 personalities-12.330
 behaviour-12.026
 Responsibility-12.019
 voices-11.795
Token Sunday
Token ID3502
Feature activation-2.66e+01

Pos logit contributions
 semester+6.958
Feb+6.061
 weeks+5.711
EMBER+5.241
 afternoon+5.161
Neg logit contributions
 lifestyles-11.367
 personalities-11.007
 behaviour-10.590
 voices-10.479
 techn-10.378
Token.
Token ID13
Feature activation-6.63e+00

Pos logit contributions
 semester+17.270
.+16.473
Feb+15.259
 afternoon+14.826
 weeks+14.497
Neg logit contributions
 lifestyles-18.023
 personalities-17.131
 behaviour-16.506
 voices-16.290
 Responsibility-16.244
Token
Token ID198
Feature activation-9.17e+00

Pos logit contributions
 semester+4.953
Feb+4.381
 weeks+4.038
EMBER+3.939
 hrs+3.929
Neg logit contributions
 lifestyles-5.903
 personalities-5.736
 behaviour-5.522
 voices-5.419
 techn-5.399
Token
Token ID198
Feature activation-5.36e+00

Pos logit contributions
 semester+5.684
Feb+5.210
.+4.685
 weeks+4.633
EMBER+4.384
Neg logit contributions
 lifestyles-9.233
 personalities-9.022
 techn-8.546
avorite-8.423
 behaviour-8.401
TokenWith
Token ID3152
Feature activation+2.50e+00

Pos logit contributions
 semester+3.914
Feb+3.620
EMBER+3.219
 weeks+3.128
 hrs+3.057
Neg logit contributions
 lifestyles-4.968
 personalities-4.812
 techn-4.633
 behaviour-4.606
 voices-4.565
Token Josh
Token ID8518
Feature activation+1.15e+00

Pos logit contributions
 lifestyles+1.773
 personalities+1.699
 behaviour+1.611
 techn+1.607
 voices+1.604
Neg logit contributions
 semester-2.404
Feb-2.166
EMBER-2.022
 weeks-2.010
imeo-1.981
Token.
Token ID13
Feature activation-1.09e+01

Pos logit contributions
.+4.810
 semester+4.445
Feb+4.296
 weeks+2.938
EMBER+2.848
Neg logit contributions
 lifestyles-21.752
 personalities-21.371
 practition-21.269
avorite-20.788
 techn-20.423
Tokenm
Token ID76
Feature activation-1.73e+01

Pos logit contributions
 semester+5.923
Feb+5.846
.+5.097
 weeks+4.918
 hrs+4.655
Neg logit contributions
 lifestyles-11.530
 personalities-11.141
 techn-10.552
 behaviour-10.515
 opinions-10.445
Token.
Token ID13
Feature activation-1.03e+01

Pos logit contributions
 semester+5.354
.+5.074
Feb+4.592
 weeks+3.767
EMBER+3.726
Neg logit contributions
 lifestyles-20.550
 personalities-20.248
avorite-19.426
 behaviour-19.346
 techn-19.335
Token ET
Token ID12152
Feature activation-1.19e+01

Pos logit contributions
 semester+8.097
Feb+7.357
 weeks+6.973
 hrs+6.726
EMBER+6.699
Neg logit contributions
 lifestyles-8.262
 personalities-7.974
 behaviour-7.545
 Responsibility-7.440
 voices-7.438
Token on
Token ID319
Feature activation-1.18e+01

Pos logit contributions
 semester+6.528
Feb+5.605
 weeks+5.262
.+5.065
EMBER+5.062
Neg logit contributions
 lifestyles-12.267
 personalities-11.824
 behaviour-11.549
 Responsibility-11.499
 voices-11.309
Token Sunday
Token ID3502
Feature activation-2.65e+01

Pos logit contributions
 semester+7.025
Feb+6.219
 weeks+5.828
EMBER+5.418
.+5.304
Neg logit contributions
 lifestyles-11.416
 personalities-11.045
 behaviour-10.672
 voices-10.536
 techn-10.427
Token.
Token ID13
Feature activation-6.56e+00

Pos logit contributions
 semester+16.024
.+15.605
Feb+13.974
 afternoon+13.493
 weeks+13.371
Neg logit contributions
 lifestyles-19.241
 personalities-18.310
 behaviour-17.690
 voices-17.362
 masculinity-17.358
Token
Token ID198
Feature activation-8.36e+00

Pos logit contributions
 semester+4.591
Feb+4.050
 weeks+3.709
 hrs+3.623
EMBER+3.603
Neg logit contributions
 lifestyles-6.155
 personalities-6.023
 behaviour-5.758
 voices-5.654
 techn-5.642
Token
Token ID198
Feature activation-5.38e+00

Pos logit contributions
 semester+5.302
Feb+4.846
 weeks+4.337
.+4.333
EMBER+4.120
Neg logit contributions
 lifestyles-8.366
 personalities-8.166
 techn-7.741
 behaviour-7.611
avorite-7.575
TokenI
Token ID40
Feature activation-5.07e+00

Pos logit contributions
 semester+3.725
Feb+3.466
EMBER+3.063
 weeks+2.967
 hrs+2.886
Neg logit contributions
 lifestyles-5.181
 personalities-5.004
 techn-4.850
 behaviour-4.805
 voices-4.759
Token touched
Token ID12615
Feature activation+2.97e+00

Pos logit contributions
 semester+4.022
Feb+3.530
 weeks+3.274
EMBER+3.257
imeo+3.169
Neg logit contributions
 lifestyles-4.429
 personalities-4.252
 behaviour-4.078
 techn-4.050
 voices-4.025
Token vs
Token ID3691
Feature activation-6.50e+00

Pos logit contributions
 lifestyles+0.069
 personalities+0.066
 behaviour+0.063
 techn+0.063
 voices+0.063
Neg logit contributions
 semester-0.068
Feb-0.060
 weeks-0.055
EMBER-0.055
 hrs-0.054
Token.
Token ID13
Feature activation+1.57e+00

Pos logit contributions
 semester+1.821
Feb+1.284
 weeks+0.934
EMBER+0.890
 hrs+0.794
Neg logit contributions
 lifestyles-8.899
 personalities-8.724
 techn-8.467
 behaviour-8.455
 voices-8.381
Token Seattle
Token ID7312
Feature activation-6.36e+00

Pos logit contributions
 lifestyles+1.111
 personalities+1.064
 behaviour+1.011
 voices+1.007
 techn+1.007
Neg logit contributions
 semester-1.514
Feb-1.360
EMBER-1.272
 weeks-1.262
imeo-1.247
Token Seahawks
Token ID16732
Feature activation-9.46e+00

Pos logit contributions
 semester+4.048
Feb+3.509
 weeks+3.320
EMBER+3.119
 hrs+3.093
Neg logit contributions
 lifestyles-6.313
 personalities-6.069
 behaviour-5.915
 techn-5.844
 masculinity-5.831
Token on
Token ID319
Feature activation-1.12e+01

Pos logit contributions
 semester+5.644
Feb+4.889
 weeks+4.524
EMBER+4.338
.+4.243
Neg logit contributions
 lifestyles-9.520
 personalities-9.226
 behaviour-8.938
 voices-8.887
 techn-8.854
Token Thursday
Token ID3635
Feature activation-2.62e+01

Pos logit contributions
 semester+7.098
Feb+6.138
 weeks+5.850
EMBER+5.315
 afternoon+5.304
Neg logit contributions
 lifestyles-10.652
 personalities-10.285
 behaviour-9.828
 voices-9.776
 opinions-9.610
Token.
Token ID13
Feature activation-6.42e+00

Pos logit contributions
 semester+17.838
.+16.885
Feb+15.826
 afternoon+15.591
 weeks+15.122
Neg logit contributions
 lifestyles-16.871
 personalities-16.032
 masculinity-15.068
 behaviour-15.063
 Policies-15.060
Token
Token ID198
Feature activation-9.33e+00

Pos logit contributions
 semester+4.791
Feb+4.238
 weeks+3.909
EMBER+3.805
 hrs+3.787
Neg logit contributions
 lifestyles-5.704
 personalities-5.559
 behaviour-5.331
 techn-5.229
 voices-5.228
Token
Token ID198
Feature activation-5.71e+00

Pos logit contributions
 semester+5.715
Feb+5.249
.+4.745
 weeks+4.690
EMBER+4.432
Neg logit contributions
 lifestyles-9.433
 personalities-9.202
 techn-8.718
avorite-8.635
 behaviour-8.579
TokenOf
Token ID5189
Feature activation+4.26e+00

Pos logit contributions
 semester+4.089
Feb+3.854
EMBER+3.401
 weeks+3.321
 hrs+3.212
Neg logit contributions
 lifestyles-5.334
 personalities-5.146
 techn-4.973
 behaviour-4.946
 voices-4.868
Token corner
Token ID5228
Feature activation+6.02e+00

Pos logit contributions
 lifestyles+2.890
 personalities+2.771
 behaviour+2.615
 techn+2.614
 voices+2.613
Neg logit contributions
 semester-4.213
Feb-3.815
EMBER-3.565
 weeks-3.533
imeo-3.489
Token shooting
Token ID4395
Feature activation-3.58e-01

Pos logit contributions
 semester+1.669
Feb+1.495
 weeks+1.437
EMBER+1.398
 hrs+1.379
Neg logit contributions
 lifestyles-1.014
 personalities-0.955
 techn-0.909
 behaviour-0.899
 Responsibility-0.897
Token incidents
Token ID10207
Feature activation-4.64e+00

Pos logit contributions
 semester+0.392
Feb+0.357
 weeks+0.337
EMBER+0.336
 hrs+0.330
Neg logit contributions
 lifestyles-0.207
 personalities-0.196
 behaviour-0.184
 techn-0.183
 voices-0.182
Token earlier
Token ID2961
Feature activation-1.44e+01

Pos logit contributions
 semester+3.352
Feb+2.906
 weeks+2.669
EMBER+2.612
 hrs+2.552
Neg logit contributions
 lifestyles-4.395
 personalities-4.235
 techn-4.075
 behaviour-4.074
 voices-4.043
Token in
Token ID287
Feature activation-1.00e+01

Pos logit contributions
 semester+10.035
Feb+8.863
 weeks+8.590
.+8.399
 hrs+7.915
Neg logit contributions
 lifestyles-12.293
 personalities-11.729
 Responsibility-11.329
 Flavoring-11.279
 techn-11.248
Token the
Token ID262
Feature activation-9.44e+00

Pos logit contributions
 semester+9.374
 weeks+8.326
Feb+8.198
 afternoon+7.637
 months+7.569
Neg logit contributions
 lifestyles-6.727
 personalities-6.447
 techn-6.132
 voices-6.050
 Responsibility-6.021
Token day
Token ID1110
Feature activation-2.53e+01

Pos logit contributions
 semester+5.622
 weeks+4.261
Feb+4.142
 afternoon+3.969
 hrs+3.546
Neg logit contributions
 lifestyles-9.895
 personalities-9.636
 Responsibility-9.386
 techn-9.321
 Flavoring-9.296
Token.
Token ID13
Feature activation-9.85e-01

Pos logit contributions
 semester+16.878
.+16.442
Feb+15.457
 weeks+15.017
 afternoon+14.287
Neg logit contributions
 lifestyles-16.736
 Flavoring-15.906
 personalities-15.570
 Responsibility-15.216
 Behavior-15.147
Token
Token ID198
Feature activation-8.18e+00

Pos logit contributions
 semester+0.769
Feb+0.690
 weeks+0.625
EMBER+0.625
 hrs+0.614
Neg logit contributions
 lifestyles-0.882
 personalities-0.848
 techn-0.809
 behaviour-0.805
 voices-0.803
Token
Token ID198
Feature activation-4.94e+00

Pos logit contributions
 semester+5.286
Feb+4.881
 weeks+4.347
.+4.293
EMBER+4.177
Neg logit contributions
 lifestyles-8.083
 personalities-7.826
 techn-7.455
 behaviour-7.298
avorite-7.292
TokenAccording
Token ID4821
Feature activation-1.33e+00

Pos logit contributions
 semester+3.510
Feb+3.264
EMBER+2.890
 weeks+2.792
 hrs+2.746
Neg logit contributions
 lifestyles-4.705
 personalities-4.509
 techn-4.354
 voices-4.294
 behaviour-4.285
Token to
Token ID284
Feature activation+1.88e+00

Pos logit contributions
 semester+0.886
Feb+0.758
 weeks+0.682
EMBER+0.680
 hrs+0.657
Neg logit contributions
 lifestyles-1.334
 personalities-1.293
 techn-1.245
 behaviour-1.244
 voices-1.239
Token as
Token ID355
Feature activation-3.26e+00

Pos logit contributions
 semester+4.859
Feb+4.201
 weeks+4.015
EMBER+3.813
 hrs+3.719
Neg logit contributions
 lifestyles-6.579
 personalities-6.290
 Behavior-6.036
 behaviour-6.035
 voices-6.022
Token prime
Token ID6994
Feature activation-7.63e+00

Pos logit contributions
 semester+3.510
Feb+3.191
 weeks+3.099
EMBER+3.050
 hrs+2.977
Neg logit contributions
 lifestyles-1.858
 personalities-1.725
 voices-1.612
 behaviour-1.604
 opinions-1.579
Token minister
Token ID5342
Feature activation-8.87e+00

Pos logit contributions
 semester+7.165
Feb+6.404
 weeks+6.224
EMBER+6.087
 hrs+5.928
Neg logit contributions
 lifestyles-5.209
 personalities-4.957
 Resistance-4.739
 Flavoring-4.728
 Controls-4.714
Token later
Token ID1568
Feature activation-1.77e+01

Pos logit contributions
 semester+5.751
Feb+4.919
 weeks+4.691
EMBER+4.460
.+4.336
Neg logit contributions
 lifestyles-8.682
 personalities-8.302
 behaviour-7.965
 Behavior-7.960
 Resistance-7.951
Token that
Token ID326
Feature activation-1.59e+01

Pos logit contributions
 semester+11.009
Feb+9.604
.+9.537
 weeks+9.455
EMBER+8.834
Neg logit contributions
 lifestyles-14.993
 personalities-14.505
 Controls-14.032
 Policies-13.984
 Responsibility-13.919
Token day
Token ID1110
Feature activation-2.49e+01

Pos logit contributions
 semester+9.816
 weeks+7.903
Feb+7.850
 afternoon+7.819
.+7.069
Neg logit contributions
 lifestyles-14.552
 personalities-14.174
 Controls-13.799
 voices-13.488
 Flavoring-13.436
Token.[
Token ID3693
Feature activation-8.28e+00

Pos logit contributions
 semester+15.808
.+15.394
 weeks+14.001
Feb+13.778
 afternoon+13.130
Neg logit contributions
 lifestyles-17.179
 personalities-16.080
 Behavior-15.612
 Controls-15.513
 Responsibility-15.365
Token195
Token ID22186
Feature activation-3.84e+00

Pos logit contributions
 semester+4.097
Feb+3.862
EMBER+3.078
 weeks+3.067
imeo+3.051
Neg logit contributions
 lifestyles-9.017
 personalities-8.653
 voices-8.408
 techn-8.379
 Responsibility-8.364
Token]
Token ID60
Feature activation+1.16e+00

Pos logit contributions
 semester+2.877
Feb+2.518
 weeks+2.304
EMBER+2.276
imeo+2.232
Neg logit contributions
 lifestyles-3.491
 personalities-3.360
 behaviour-3.235
 voices-3.205
 techn-3.193
Token
Token ID198
Feature activation-5.93e+00

Pos logit contributions
 lifestyles+0.908
 personalities+0.870
 behaviour+0.829
 techn+0.824
 voices+0.823
Neg logit contributions
 semester-1.042
Feb-0.933
 weeks-0.868
EMBER-0.867
 hrs-0.846
Token
Token ID198
Feature activation-4.12e+00

Pos logit contributions
 semester+4.051
Feb+3.644
 weeks+3.314
EMBER+3.193
.+3.188
Neg logit contributions
 lifestyles-5.747
 personalities-5.595
 techn-5.306
 behaviour-5.207
 opinions-5.190
Token broke
Token ID6265
Feature activation-5.49e+00

Pos logit contributions
 semester+6.356
Feb+5.560
 weeks+5.173
.+4.907
 hrs+4.859
Neg logit contributions
 lifestyles-8.826
 personalities-8.405
 techn-8.174
 Responsibility-8.100
 voices-8.097
Token out
Token ID503
Feature activation-1.25e+01

Pos logit contributions
 semester+3.803
Feb+3.280
 weeks+3.066
EMBER+2.921
 hrs+2.879
Neg logit contributions
 lifestyles-5.325
 personalities-5.139
 techn-4.951
 voices-4.937
 behaviour-4.912
Token in
Token ID287
Feature activation-5.83e+00

Pos logit contributions
 semester+8.490
Feb+7.429
 weeks+7.315
.+6.942
 hrs+6.653
Neg logit contributions
 lifestyles-11.204
 personalities-10.710
 Behavior-10.345
 techn-10.283
 Policies-10.242
Token France
Token ID4881
Feature activation-1.00e+01

Pos logit contributions
 semester+5.267
Feb+4.700
 weeks+4.577
 hrs+4.309
EMBER+4.308
Neg logit contributions
 lifestyles-4.267
 personalities-4.096
 techn-3.862
 voices-3.859
 behaviour-3.805
Token on
Token ID319
Feature activation-8.99e+00

Pos logit contributions
 semester+7.193
Feb+6.368
 weeks+6.096
EMBER+5.837
.+5.798
Neg logit contributions
 lifestyles-8.838
 personalities-8.463
 voices-8.121
 techn-8.084
 behaviour-8.065
Token Monday
Token ID3321
Feature activation-2.47e+01

Pos logit contributions
 semester+5.902
Feb+5.190
 weeks+4.949
EMBER+4.576
 hrs+4.499
Neg logit contributions
 lifestyles-8.335
 personalities-8.127
 voices-7.822
 techn-7.764
 behaviour-7.651
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
 semester+16.768
.+15.763
 afternoon+15.200
Feb+14.832
 weeks+14.531
Neg logit contributions
 lifestyles-16.609
 Policies-15.469
 Behavior-15.394
 personalities-15.325
 Controls-14.945
Token
Token ID198
Feature activation-7.75e+00

Pos logit contributions
 semester+0.144
Feb+0.128
 weeks+0.118
EMBER+0.117
 hrs+0.115
Neg logit contributions
 lifestyles-0.158
 personalities-0.152
 techn-0.145
 behaviour-0.145
 voices-0.145
Token
Token ID198
Feature activation-5.36e+00

Pos logit contributions
 semester+5.066
Feb+4.620
 weeks+4.141
.+4.080
EMBER+3.990
Neg logit contributions
 lifestyles-7.645
 personalities-7.444
 techn-7.088
 opinions-6.930
 behaviour-6.911
TokenATT
Token ID17139
Feature activation-1.11e+00

Pos logit contributions
 semester+3.741
Feb+3.486
EMBER+3.107
 weeks+3.003
 hrs+2.933
Neg logit contributions
 lifestyles-5.065
 personalities-4.904
 techn-4.747
 voices-4.676
 behaviour-4.655
TokenENTION
Token ID45589
Feature activation+5.06e+00

Pos logit contributions
 semester+0.706
Feb+0.604
EMBER+0.550
 weeks+0.541
 hrs+0.522
Neg logit contributions
 lifestyles-1.150
 personalities-1.116
 techn-1.078
 behaviour-1.072
 voices-1.070
Token for
Token ID329
Feature activation+4.12e-01

Pos logit contributions
 semester+3.466
Feb+2.962
 weeks+2.688
EMBER+2.620
 hrs+2.595
Neg logit contributions
 lifestyles-4.981
 personalities-4.840
 behaviour-4.641
 techn-4.616
 voices-4.608
Token shorter
Token ID12238
Feature activation-1.73e+00

Pos logit contributions
 lifestyles+0.302
 personalities+0.290
 behaviour+0.276
 techn+0.275
 voices+0.274
Neg logit contributions
 semester-0.387
Feb-0.346
 weeks-0.323
EMBER-0.322
 hrs-0.316
Token tours
Token ID21284
Feature activation-9.94e+00

Pos logit contributions
 semester+1.577
Feb+1.399
 weeks+1.315
EMBER+1.294
 hrs+1.279
Neg logit contributions
 lifestyles-1.322
 personalities-1.272
 behaviour-1.210
 techn-1.207
 voices-1.200
Token throughout
Token ID3690
Feature activation-6.84e+00

Pos logit contributions
 semester+7.401
Feb+6.410
 weeks+6.118
.+5.749
 hrs+5.744
Neg logit contributions
 lifestyles-8.673
 personalities-8.417
 Flavoring-8.031
 behaviour-8.003
 Responsibility-7.979
Token the
Token ID262
Feature activation-7.54e+00

Pos logit contributions
 semester+6.912
Feb+6.154
 weeks+5.918
EMBER+5.718
 hrs+5.642
Neg logit contributions
 lifestyles-4.457
 personalities-4.289
 behaviour-4.041
 voices-4.023
 techn-3.996
Token day
Token ID1110
Feature activation-2.46e+01

Pos logit contributions
 semester+5.082
Feb+3.961
 weeks+3.887
 afternoon+3.543
EMBER+3.516
Neg logit contributions
 lifestyles-7.538
 personalities-7.357
 Responsibility-7.097
 voices-7.049
 behaviour-7.024
Token).
Token ID737
Feature activation+8.88e-01

Pos logit contributions
 semester+16.878
.+15.268
Feb+15.253
 weeks+14.614
 apiece+13.998
Neg logit contributions
 lifestyles-15.947
 personalities-15.730
 Flavoring-15.642
 masculinity-14.870
 Responsibility-14.830
Token
Token ID198
Feature activation-4.79e+00

Pos logit contributions
 lifestyles+0.705
 personalities+0.679
 behaviour+0.648
 techn+0.645
 voices+0.643
Neg logit contributions
 semester-0.782
Feb-0.697
EMBER-0.645
 weeks-0.644
 hrs-0.630
Token
Token ID198
Feature activation-2.78e+00

Pos logit contributions
 semester+3.484
Feb+3.127
 weeks+2.832
EMBER+2.770
 hrs+2.718
Neg logit contributions
 lifestyles-4.497
 personalities-4.356
 techn-4.148
 behaviour-4.108
 opinions-4.064
TokenW
Token ID54
Feature activation-7.89e-01

Pos logit contributions
 semester+1.990
Feb+1.772
EMBER+1.595
 weeks+1.565
 hrs+1.526
Neg logit contributions
 lifestyles-2.646
 personalities-2.565
 techn-2.466
 behaviour-2.466
 voices-2.452
Tokenright
Token ID3506
Feature activation+4.96e+00

Pos logit contributions
 semester+0.721
Feb+0.645
EMBER+0.600
 weeks+0.599
imeo+0.587
Neg logit contributions
 lifestyles-0.599
 personalities-0.577
 behaviour-0.547
 techn-0.546
 voices-0.545
Token travel
Token ID3067
Feature activation-2.53e+00

Pos logit contributions
 semester+2.060
Feb+1.863
 weeks+1.772
EMBER+1.763
 hrs+1.728
Neg logit contributions
 lifestyles-1.138
 personalities-1.072
 behaviour-1.001
 techn-0.992
 voices-0.991
Token agent
Token ID5797
Feature activation-1.81e+00

Pos logit contributions
 semester+2.945
Feb+2.681
 weeks+2.570
EMBER+2.547
 hrs+2.498
Neg logit contributions
 lifestyles-1.286
 personalities-1.192
 voices-1.097
 behaviour-1.093
 techn-1.078
Token earlier
Token ID2961
Feature activation-1.37e+01

Pos logit contributions
 semester+1.299
Feb+1.122
 weeks+1.030
EMBER+1.017
 hrs+0.990
Neg logit contributions
 lifestyles-1.724
 personalities-1.665
 behaviour-1.601
 techn-1.595
 voices-1.594
Token in
Token ID287
Feature activation-1.19e+01

Pos logit contributions
 semester+9.703
 weeks+8.450
Feb+8.421
 hrs+7.722
.+7.715
Neg logit contributions
 lifestyles-11.466
 personalities-11.003
 Responsibility-10.590
 Flavoring-10.540
 techn-10.527
Token the
Token ID262
Feature activation-1.14e+01

Pos logit contributions
 semester+10.833
Feb+9.513
 weeks+9.445
 afternoon+8.804
 hrs+8.649
Neg logit contributions
 lifestyles-8.075
 personalities-7.790
 Responsibility-7.206
 voices-7.192
 Controls-7.157
Token week
Token ID1285
Feature activation-2.46e+01

Pos logit contributions
 semester+6.765
 weeks+5.105
Feb+4.974
 afternoon+4.759
 hrs+4.265
Neg logit contributions
 lifestyles-11.833
 personalities-11.523
 Responsibility-11.177
 Flavoring-11.069
 Controls-11.031
Token to
Token ID284
Feature activation-4.42e+00

Pos logit contributions
 semester+16.904
 weeks+15.144
.+14.878
Feb+14.625
 afternoon+14.224
Neg logit contributions
 lifestyles-15.831
 personalities-14.980
 Flavoring-14.364
 masculinity-14.356
 Controls-14.199
Token a
Token ID257
Feature activation-6.25e+00

Pos logit contributions
 semester+3.872
Feb+3.457
 weeks+3.259
EMBER+3.158
 hrs+3.108
Neg logit contributions
 lifestyles-3.458
 personalities-3.295
 behaviour-3.082
 voices-3.076
 techn-3.064
Token different
Token ID1180
Feature activation-9.04e+00

Pos logit contributions
 semester+6.014
Feb+5.297
 weeks+5.116
EMBER+4.897
 hrs+4.804
Neg logit contributions
 lifestyles-4.344
 personalities-4.138
 voices-3.853
 behaviour-3.822
 opinions-3.784
Token flight
Token ID5474
Feature activation-1.23e+01

Pos logit contributions
 semester+8.140
Feb+6.998
 weeks+6.902
EMBER+6.554
 hrs+6.466
Neg logit contributions
 lifestyles-6.531
 personalities-6.155
 voices-5.746
 behaviour-5.705
 masculinity-5.703
Token (
Token ID357
Feature activation-4.84e+00

Pos logit contributions
 semester+9.550
Feb+8.303
 weeks+8.191
.+7.887
 hrs+7.661
Neg logit contributions
 lifestyles-9.758
 personalities-9.180
 Flavoring-9.002
 voices-8.741
 masculinity-8.696
Token the
Token ID262
Feature activation-1.97e+00

Pos logit contributions
 lifestyles+0.872
 personalities+0.825
 behaviour+0.774
 voices+0.769
 techn+0.766
Neg logit contributions
 semester-1.772
Feb-1.621
EMBER-1.528
 weeks-1.520
imeo-1.505
Token Week
Token ID6119
Feature activation-1.19e+01

Pos logit contributions
 semester+1.535
Feb+1.334
 weeks+1.233
EMBER+1.223
 hrs+1.186
Neg logit contributions
 lifestyles-1.772
 personalities-1.711
 techn-1.641
 behaviour-1.640
 voices-1.634
Token recognition
Token ID9465
Feature activation-5.04e+00

Pos logit contributions
 semester+10.962
Feb+9.478
.+9.420
 weeks+9.367
 apiece+9.206
Neg logit contributions
 lifestyles-7.623
 personalities-7.030
 techn-6.871
 behaviour-6.805
 masculinity-6.755
Token the
Token ID262
Feature activation-3.68e+00

Pos logit contributions
 semester+2.747
Feb+2.227
 weeks+1.994
EMBER+1.953
 apiece+1.846
Neg logit contributions
 lifestyles-5.658
 personalities-5.471
 techn-5.308
 behaviour-5.303
 voices-5.270
Token following
Token ID1708
Feature activation-1.43e+01

Pos logit contributions
 semester+2.961
Feb+2.523
 weeks+2.389
EMBER+2.328
 hrs+2.249
Neg logit contributions
 lifestyles-3.230
 personalities-3.104
 techn-2.988
 behaviour-2.968
 voices-2.945
Token day
Token ID1110
Feature activation-2.44e+01

Pos logit contributions
 semester+9.793
 weeks+7.712
Feb+7.683
 afternoon+7.257
EMBER+6.728
Neg logit contributions
 lifestyles-12.958
 personalities-12.489
 Controls-12.337
 Responsibility-12.135
 techn-12.076
Token.[
Token ID3693
Feature activation-7.92e+00

Pos logit contributions
 semester+15.102
.+14.137
Feb+13.120
 weeks+12.919
 apiece+12.132
Neg logit contributions
 lifestyles-17.940
 personalities-16.985
 Controls-16.653
 Responsibility-16.557
 Behavior-16.398
Token113
Token ID16616
Feature activation-5.87e+00

Pos logit contributions
 semester+4.382
Feb+3.796
 weeks+3.365
EMBER+3.157
.+3.094
Neg logit contributions
 lifestyles-8.340
 personalities-8.090
 techn-7.803
 behaviour-7.776
 masculinity-7.762
Token]
Token ID60
Feature activation+6.29e-01

Pos logit contributions
 semester+4.138
Feb+3.550
 weeks+3.251
EMBER+3.167
imeo+3.137
Neg logit contributions
 lifestyles-5.526
 personalities-5.351
 behaviour-5.129
 voices-5.045
 techn-5.044
Token He
Token ID679
Feature activation-3.89e+00

Pos logit contributions
 lifestyles+0.428
 personalities+0.409
 behaviour+0.387
 techn+0.386
 voices+0.383
Neg logit contributions
 semester-0.625
Feb-0.565
EMBER-0.528
 weeks-0.528
 hrs-0.517
Token was
Token ID373
Feature activation-4.39e+00

Pos logit contributions
 semester+2.943
Feb+2.542
 weeks+2.360
EMBER+2.291
 hrs+2.247
Neg logit contributions
 lifestyles-3.553
 personalities-3.428
 behaviour-3.294
 techn-3.280
 Resistance-3.265
Token my
Token ID616
Feature activation-2.96e+00

Pos logit contributions
 lifestyles+3.522
 personalities+3.373
 behaviour+3.220
 voices+3.190
 techn+3.182
Neg logit contributions
 semester-4.582
Feb-4.140
EMBER-3.870
 weeks-3.814
imeo-3.795
Token research
Token ID2267
Feature activation-3.71e+00

Pos logit contributions
 semester+3.129
Feb+2.750
 weeks+2.669
EMBER+2.583
 hrs+2.572
Neg logit contributions
 lifestyles-1.797
 personalities-1.719
 techn-1.629
 voices-1.583
 Flavoring-1.583
Token back
Token ID736
Feature activation-1.19e+01

Pos logit contributions
 semester+2.853
Feb+2.458
 weeks+2.288
EMBER+2.244
 hrs+2.192
Neg logit contributions
 lifestyles-3.328
 personalities-3.230
 techn-3.103
 voices-3.081
 behaviour-3.075
Token in
Token ID287
Feature activation-9.49e+00

Pos logit contributions
 semester+8.034
Feb+6.958
 weeks+6.384
EMBER+6.145
.+6.134
Neg logit contributions
 lifestyles-10.835
 personalities-10.548
 techn-10.026
 behaviour-10.018
 voices-9.950
Token the
Token ID262
Feature activation-8.80e+00

Pos logit contributions
 semester+8.570
Feb+7.434
 weeks+7.125
EMBER+6.804
.+6.651
Neg logit contributions
 lifestyles-6.834
 personalities-6.634
 behaviour-6.137
 techn-6.118
 voices-6.115
Token spring
Token ID6076
Feature activation-2.43e+01

Pos logit contributions
 semester+7.653
Feb+6.473
 weeks+6.401
EMBER+6.032
 afternoon+5.977
Neg logit contributions
 lifestyles-6.732
 personalities-6.446
 Flavoring-6.067
 techn-6.051
 voices-6.038
Token of
Token ID286
Feature activation-1.09e+01

Pos logit contributions
 semester+19.601
.+16.638
 weeks+15.911
Feb+15.603
 months+15.094
Neg logit contributions
 personalities-14.556
 lifestyles-14.453
 Flavoring-13.404
 Responsibility-13.357
 voices-13.203
Token 2000
Token ID4751
Feature activation-1.74e+01

Pos logit contributions
 semester+7.973
Feb+6.535
 weeks+6.184
EMBER+5.926
.+5.861
Neg logit contributions
 lifestyles-9.499
 personalities-9.333
 Flavoring-8.863
 techn-8.726
 behaviour-8.703
Token.
Token ID13
Feature activation+1.23e+00

Pos logit contributions
 semester+13.260
.+11.349
Feb+11.202
 weeks+10.850
 hrs+10.342
Neg logit contributions
 lifestyles-12.906
 personalities-12.429
 techn-12.047
 masculinity-11.849
 behaviour-11.794
Token He
Token ID679
Feature activation-5.53e-01

Pos logit contributions
 lifestyles+0.869
 personalities+0.833
 behaviour+0.790
 techn+0.787
 voices+0.784
Neg logit contributions
 semester-1.189
Feb-1.070
EMBER-0.999
 weeks-0.998
 hrs-0.978
Token ignored
Token ID9514
Feature activation+8.35e+00

Pos logit contributions
 semester+0.467
Feb+0.410
 weeks+0.381
EMBER+0.377
 hrs+0.370
Neg logit contributions
 lifestyles-0.459
 personalities-0.442
 behaviour-0.423
 techn-0.422
 voices-0.416
Token greatly
Token ID9257
Feature activation-5.28e+00

Pos logit contributions
 semester+4.031
Feb+3.495
 weeks+3.293
EMBER+3.189
 hrs+3.147
Neg logit contributions
 lifestyles-4.558
 personalities-4.353
 behaviour-4.206
 Responsibility-4.202
 voices-4.194
Token improved
Token ID6596
Feature activation+2.76e+00

Pos logit contributions
 semester+4.281
Feb+3.761
 weeks+3.534
EMBER+3.410
 hrs+3.408
Neg logit contributions
 lifestyles-4.419
 personalities-4.235
 behaviour-4.065
 Responsibility-4.054
 voices-4.045
Token in
Token ID287
Feature activation-2.19e+00

Pos logit contributions
 lifestyles+3.290
 personalities+3.212
 behaviour+3.121
 techn+3.116
 voices+3.107
Neg logit contributions
 semester-1.286
Feb-1.046
EMBER-0.879
 weeks-0.849
imeo-0.840
Token the
Token ID262
Feature activation-4.20e+00

Pos logit contributions
 semester+2.160
Feb+1.931
 weeks+1.837
EMBER+1.805
 hrs+1.778
Neg logit contributions
 lifestyles-1.488
 personalities-1.415
 behaviour-1.338
 voices-1.336
 techn-1.329
Token last
Token ID938
Feature activation-1.87e+01

Pos logit contributions
 semester+2.629
Feb+2.109
 weeks+2.070
EMBER+1.905
 hrs+1.879
Neg logit contributions
 lifestyles-4.343
 personalities-4.208
 behaviour-4.054
 voices-4.023
 techn-4.020
Token year
Token ID614
Feature activation-2.42e+01

Pos logit contributions
 semester+13.486
 weeks+11.295
 months+10.348
Feb+10.294
.+10.194
Neg logit contributions
 lifestyles-14.711
 personalities-14.045
 voices-13.438
avorite-13.428
 Responsibility-13.377
Token or
Token ID393
Feature activation-6.90e+00

Pos logit contributions
 semester+16.606
.+15.357
Feb+13.926
 weeks+13.924
 apiece+13.016
Neg logit contributions
 lifestyles-16.306
 personalities-15.621
 Behavior-15.156
 behaviour-15.024
 Responsibility-14.907
Token so
Token ID523
Feature activation-1.93e+01

Pos logit contributions
 semester+5.020
Feb+4.208
 weeks+3.952
EMBER+3.766
 hrs+3.693
Neg logit contributions
 lifestyles-6.461
 personalities-6.205
 voices-5.983
 techn-5.967
 Resistance-5.901
Token.
Token ID13
Feature activation+1.73e+00

Pos logit contributions
 semester+12.918
.+11.661
Feb+10.698
 weeks+10.605
EMBER+9.850
Neg logit contributions
 lifestyles-14.974
 personalities-14.310
 Responsibility-13.925
 masculinity-13.658
 behaviour-13.633
Token I
Token ID314
Feature activation-6.37e+00

Pos logit contributions
 lifestyles+1.255
 personalities+1.201
 behaviour+1.142
 techn+1.134
 voices+1.131
Neg logit contributions
 semester-1.644
Feb-1.482
 weeks-1.378
EMBER-1.376
 hrs-1.349
Token believe
Token ID1975
Feature activation+3.25e+00

Pos logit contributions
 semester+4.920
Feb+4.300
 weeks+3.994
EMBER+3.975
imeo+3.855
Neg logit contributions
 lifestyles-5.582
 personalities-5.347
 behaviour-5.120
 techn-5.067
 voices-5.067
Token porn
Token ID8483
Feature activation+2.84e+00

Pos logit contributions
 lifestyles+0.940
 personalities+0.913
 techn+0.874
 behaviour+0.872
 voices+0.871
Neg logit contributions
 semester-0.789
Feb-0.692
EMBER-0.632
 weeks-0.622
imeo-0.621
Token to
Token ID284
Feature activation-1.73e+00

Pos logit contributions
 lifestyles+2.791
 personalities+2.724
 techn+2.611
 voices+2.609
 behaviour+2.606
Neg logit contributions
 semester-1.919
Feb-1.669
EMBER-1.493
imeo-1.464
 weeks-1.443
Token share
Token ID2648
Feature activation-8.32e-01

Pos logit contributions
 semester+1.456
Feb+1.276
 weeks+1.189
EMBER+1.181
imeo+1.151
Neg logit contributions
 lifestyles-1.442
 personalities-1.387
 behaviour-1.328
 voices-1.322
 techn-1.318
Token throughout
Token ID3690
Feature activation-5.52e+00

Pos logit contributions
 semester+0.531
Feb+0.451
EMBER+0.403
 weeks+0.399
imeo+0.390
Neg logit contributions
 lifestyles-0.860
 personalities-0.835
 behaviour-0.806
 techn-0.804
 voices-0.804
Token the
Token ID262
Feature activation-6.13e+00

Pos logit contributions
 semester+5.558
Feb+4.924
 weeks+4.762
EMBER+4.619
 hrs+4.511
Neg logit contributions
 lifestyles-3.630
 personalities-3.499
 behaviour-3.314
 voices-3.286
 techn-3.252
Token week
Token ID1285
Feature activation-2.42e+01

Pos logit contributions
 semester+3.257
Feb+2.412
 weeks+2.352
EMBER+2.040
 hrs+1.978
Neg logit contributions
 lifestyles-7.010
 personalities-6.882
 behaviour-6.651
 voices-6.620
 techn-6.586
Token,
Token ID11
Feature activation+1.66e-01

Pos logit contributions
 semester+15.886
.+14.969
 weeks+13.965
Feb+13.407
EMBER+12.802
Neg logit contributions
 lifestyles-16.693
 personalities-16.070
 Responsibility-15.870
 Controls-15.654
 Behavior-15.640
Token so
Token ID523
Feature activation-3.87e+00

Pos logit contributions
 lifestyles+0.134
 personalities+0.128
 behaviour+0.123
 techn+0.122
 voices+0.122
Neg logit contributions
 semester-0.145
Feb-0.127
 weeks-0.120
EMBER-0.118
 hrs-0.115
Token I
Token ID314
Feature activation-6.40e+00

Pos logit contributions
 semester+3.402
Feb+2.987
 weeks+2.839
EMBER+2.788
 hrs+2.736
Neg logit contributions
 lifestyles-3.036
 personalities-2.914
 behaviour-2.795
 techn-2.767
 voices-2.746
Token
Token ID447
Feature activation-6.85e+00

Pos logit contributions
 semester+4.878
Feb+4.200
 weeks+3.950
EMBER+3.871
 hrs+3.793
Neg logit contributions
 lifestyles-5.720
 personalities-5.496
 behaviour-5.294
 techn-5.234
 Resistance-5.218
Token
Token ID247
Feature activation+1.09e+01

Pos logit contributions
 semester+5.015
Feb+4.425
EMBER+4.080
 weeks+3.952
 hrs+3.890
Neg logit contributions
 lifestyles-6.349
 personalities-6.052
 behaviour-5.903
 techn-5.875
 voices-5.771
Token exchange
Token ID5163
Feature activation-6.27e+00

Pos logit contributions
 semester+2.037
Feb+1.795
 weeks+1.668
EMBER+1.636
 hrs+1.604
Neg logit contributions
 lifestyles-2.119
 personalities-2.032
 behaviour-1.943
 techn-1.937
 voices-1.932
Token from
Token ID422
Feature activation-1.61e-02

Pos logit contributions
 semester+4.791
Feb+4.195
 weeks+3.970
EMBER+3.758
 hrs+3.701
Neg logit contributions
 lifestyles-5.609
 personalities-5.343
 behaviour-5.145
 techn-5.091
 Responsibility-5.084
Token earlier
Token ID2961
Feature activation-1.23e+01

Pos logit contributions
 semester+0.015
Feb+0.014
 weeks+0.013
EMBER+0.013
 hrs+0.013
Neg logit contributions
 lifestyles-0.012
 personalities-0.011
 behaviour-0.010
 techn-0.010
 voices-0.010
Token in
Token ID287
Feature activation-1.20e+01

Pos logit contributions
 semester+9.500
Feb+8.452
 weeks+8.323
.+7.594
 hrs+7.569
Neg logit contributions
 lifestyles-9.886
 personalities-9.406
 Flavoring-9.310
 techn-9.078
 masculinity-8.888
Token the
Token ID262
Feature activation-1.06e+01

Pos logit contributions
 semester+10.905
Feb+9.634
 weeks+9.385
 months+8.634
 afternoon+8.547
Neg logit contributions
 lifestyles-8.322
 personalities-7.892
 techn-7.476
 Responsibility-7.351
 Flavoring-7.337
Token day
Token ID1110
Feature activation-2.42e+01

Pos logit contributions
 semester+8.672
Feb+7.039
 weeks+6.992
 afternoon+6.504
 months+6.291
Neg logit contributions
 lifestyles-8.691
 personalities-8.335
 Flavoring-8.119
 Responsibility-8.015
 techn-7.981
Token on
Token ID319
Feature activation-6.79e+00

Pos logit contributions
 semester+17.729
.+16.293
 weeks+16.262
Feb+16.194
 months+14.821
Neg logit contributions
 lifestyles-14.971
 Flavoring-14.609
 personalities-13.938
 Responsibility-13.762
 Policies-13.507
Token Nov
Token ID5267
Feature activation-1.98e+01

Pos logit contributions
 semester+4.734
Feb+4.183
 weeks+3.820
EMBER+3.645
 hrs+3.578
Neg logit contributions
 lifestyles-6.364
 personalities-6.133
 techn-5.891
 behaviour-5.875
 voices-5.857
Token.
Token ID13
Feature activation-1.06e+01

Pos logit contributions
 semester+9.294
.+8.931
Feb+8.077
EMBER+7.304
 weeks+7.179
Neg logit contributions
 lifestyles-19.659
 personalities-19.395
avorite-18.969
 practition-18.550
 techn-18.490
Token 12
Token ID1105
Feature activation-1.99e+01

Pos logit contributions
 semester+6.015
Feb+5.150
 weeks+4.646
EMBER+4.561
.+4.380
Neg logit contributions
 lifestyles-11.030
 personalities-10.809
 techn-10.345
 behaviour-10.270
 opinions-10.138
Token between
Token ID1022
Feature activation-4.18e+00

Pos logit contributions
 semester+14.792
Feb+12.981
.+12.550
 weeks+12.375
 afternoon+11.593
Neg logit contributions
 lifestyles-14.464
 personalities-13.747
 Flavoring-13.414
 behaviour-13.096
 Responsibility-13.064
Token.
Token ID13
Feature activation-6.79e+00

Pos logit contributions
 semester+4.432
Feb+3.662
.+3.130
EMBER+2.949
 weeks+2.778
Neg logit contributions
 lifestyles-15.792
 personalities-15.287
 behaviour-14.661
 techn-14.576
 opinions-14.572
Tokenm
Token ID76
Feature activation-1.36e+01

Pos logit contributions
 semester+4.571
Feb+4.169
 weeks+3.732
EMBER+3.680
 hrs+3.625
Neg logit contributions
 lifestyles-6.649
 personalities-6.409
 behaviour-6.098
 techn-6.050
 opinions-6.016
Token.
Token ID13
Feature activation-8.05e+00

Pos logit contributions
 semester+6.150
Feb+5.353
.+4.972
EMBER+4.655
 weeks+4.558
Neg logit contributions
 lifestyles-14.950
 personalities-14.479
 behaviour-14.171
 voices-14.045
 techn-13.851
Token ET
Token ID12152
Feature activation-1.06e+01

Pos logit contributions
 semester+6.661
Feb+6.071
 weeks+5.673
EMBER+5.531
 hrs+5.527
Neg logit contributions
 lifestyles-6.364
 personalities-6.067
 behaviour-5.863
 voices-5.713
 techn-5.694
Token on
Token ID319
Feature activation-1.01e+01

Pos logit contributions
 semester+7.925
Feb+7.191
 weeks+6.673
EMBER+6.622
 hrs+6.551
Neg logit contributions
 lifestyles-8.954
 personalities-8.595
 behaviour-8.304
 techn-8.140
 voices-8.104
Token Sunday
Token ID3502
Feature activation-2.41e+01

Pos logit contributions
 semester+7.796
Feb+7.084
 weeks+6.756
 hrs+6.405
EMBER+6.289
Neg logit contributions
 lifestyles-8.152
 personalities-7.795
 behaviour-7.567
 voices-7.403
 techn-7.378
Token.
Token ID13
Feature activation-5.10e+00

Pos logit contributions
 semester+17.295
.+16.297
Feb+16.136
 weeks+15.334
 afternoon+15.322
Neg logit contributions
 lifestyles-15.469
 personalities-14.327
 behaviour-14.031
 masculinity-13.706
 Flavoring-13.689
Token
Token ID198
Feature activation-1.13e+01

Pos logit contributions
 semester+4.509
Feb+4.114
 weeks+3.848
EMBER+3.800
 hrs+3.744
Neg logit contributions
 lifestyles-3.888
 personalities-3.774
 behaviour-3.608
 techn-3.558
 voices-3.494
Token
Token ID198
Feature activation-9.11e+00

Pos logit contributions
 semester+6.436
Feb+5.998
.+5.505
 weeks+5.302
EMBER+4.947
Neg logit contributions
 lifestyles-11.525
 personalities-11.222
avorite-10.799
 techn-10.694
 practition-10.491
TokenN
Token ID45
Feature activation-2.84e+00

Pos logit contributions
 semester+6.361
Feb+6.138
EMBER+5.374
 weeks+5.138
BU+5.002
Neg logit contributions
 lifestyles-8.439
 personalities-8.126
 techn-7.962
 behaviour-7.849
 voices-7.694
Tokenorman
Token ID26183
Feature activation+3.37e-01

Pos logit contributions
 semester+2.136
Feb+1.880
EMBER+1.736
 weeks+1.723
imeo+1.662
Neg logit contributions
 lifestyles-2.594
 personalities-2.514
 behaviour-2.413
 voices-2.395
 techn-2.391
Token in
Token ID287
Feature activation-7.72e+00

Pos logit contributions
 semester+2.941
Feb+2.528
 weeks+2.287
EMBER+2.253
 hrs+2.196
Neg logit contributions
 lifestyles-4.346
 personalities-4.215
 behaviour-4.059
 techn-4.037
 voices-4.033
Token a
Token ID257
Feature activation-8.97e+00

Pos logit contributions
 semester+6.758
Feb+6.213
 weeks+5.868
EMBER+5.536
 hrs+5.478
Neg logit contributions
 lifestyles-5.761
 personalities-5.484
 behaviour-5.199
 Resistance-5.063
 masculinity-5.062
Token phone
Token ID3072
Feature activation-8.76e+00

Pos logit contributions
 semester+7.687
Feb+6.907
 weeks+6.507
EMBER+6.153
imeo+6.054
Neg logit contributions
 lifestyles-6.914
 personalities-6.612
 behaviour-6.275
 Resistance-6.122
 voices-6.086
Token interview
Token ID2720
Feature activation-1.08e+01

Pos logit contributions
 semester+5.612
Feb+4.790
 weeks+4.493
imeo+4.250
.+4.197
Neg logit contributions
 lifestyles-8.578
 personalities-8.275
 Resistance-8.019
 behaviour-7.927
 Policies-7.814
Token on
Token ID319
Feature activation-7.31e+00

Pos logit contributions
 semester+6.145
Feb+5.181
 weeks+4.881
.+4.583
EMBER+4.366
Neg logit contributions
 lifestyles-11.476
 personalities-11.134
 behaviour-10.774
 Behavior-10.594
 Resistance-10.590
Token Friday
Token ID3217
Feature activation-2.41e+01

Pos logit contributions
 semester+4.923
Feb+4.262
 weeks+4.013
 hrs+3.655
EMBER+3.597
Neg logit contributions
 lifestyles-7.035
 personalities-6.816
 behaviour-6.509
 voices-6.453
 Resistance-6.396
Token.
Token ID13
Feature activation+1.65e-01

Pos logit contributions
 semester+14.619
.+13.475
 afternoon+12.870
Feb+12.401
 weeks+12.293
Neg logit contributions
 lifestyles-19.286
 personalities-18.782
 Policies-17.918
 Responsibility-17.889
 behaviour-17.730
Token
Token ID198
Feature activation-6.58e+00

Pos logit contributions
 lifestyles+0.138
 personalities+0.133
 behaviour+0.127
 techn+0.126
 voices+0.126
Neg logit contributions
 semester-0.139
Feb-0.123
 weeks-0.114
EMBER-0.113
 hrs-0.111
Token
Token ID198
Feature activation-3.75e+00

Pos logit contributions
 semester+4.512
Feb+4.105
 weeks+3.694
EMBER+3.571
.+3.554
Neg logit contributions
 lifestyles-6.374
 personalities-6.180
 techn-5.877
 behaviour-5.817
 opinions-5.745
TokenCurrently
Token ID21327
Feature activation-6.26e+00

Pos logit contributions
 semester+2.684
Feb+2.442
EMBER+2.149
 weeks+2.140
 hrs+2.068
Neg logit contributions
 lifestyles-3.569
 personalities-3.448
 behaviour-3.309
 techn-3.290
 voices-3.284
Token,
Token ID11
Feature activation+3.27e+00

Pos logit contributions
 semester+4.334
Feb+3.673
 weeks+3.470
 hrs+3.232
EMBER+3.158
Neg logit contributions
 lifestyles-5.973
 personalities-5.777
 behaviour-5.589
 Responsibility-5.515
 Resistance-5.471
Token areas
Token ID3006
Feature activation-5.97e+00

Pos logit contributions
 lifestyles+3.650
 personalities+3.388
 behaviour+3.226
 voices+3.184
 techn+3.103
Neg logit contributions
 semester-7.340
Feb-6.706
EMBER-6.360
imeo-6.323
imester-6.236
Token in
Token ID287
Feature activation-5.17e+00

Pos logit contributions
 semester+4.368
Feb+3.735
 weeks+3.578
EMBER+3.402
 hrs+3.320
Neg logit contributions
 lifestyles-5.405
 personalities-5.226
 techn-5.049
 voices-4.999
 behaviour-4.995
Token the
Token ID262
Feature activation-7.17e+00

Pos logit contributions
 semester+4.864
Feb+4.302
 weeks+4.250
EMBER+4.027
 hrs+3.932
Neg logit contributions
 lifestyles-3.500
 personalities-3.405
 voices-3.186
 techn-3.185
 Behavior-3.162
Token last
Token ID938
Feature activation-2.31e+01

Pos logit contributions
 semester+5.384
 weeks+4.560
Feb+4.469
EMBER+4.185
 hrs+4.061
Neg logit contributions
 lifestyles-6.233
 personalities-6.080
 techn-5.791
 Flavoring-5.711
 Resistance-5.708
Token six
Token ID2237
Feature activation-1.98e+01

Pos logit contributions
 semester+16.560
 weeks+14.210
 months+13.246
 year+13.198
 month+12.783
Neg logit contributions
avorite-15.660
 lifestyles-15.545
 Flavoring-15.471
 personalities-15.314
 Controls-14.881
Token months
Token ID1933
Feature activation-2.40e+01

Pos logit contributions
 semester+13.157
 weeks+12.899
 months+12.144
.+10.751
Feb+10.652
Neg logit contributions
 lifestyles-14.721
 Flavoring-14.448
 personalities-14.440
 Behavior-14.277
 Responsibility-14.262
Token and
Token ID290
Feature activation-3.91e+00

Pos logit contributions
 semester+16.434
.+15.377
 weeks+14.009
Feb+13.332
 apiece+12.984
Neg logit contributions
 lifestyles-15.715
 personalities-15.104
 Behavior-15.048
 Responsibility-14.921
 Policies-14.857
Token now
Token ID783
Feature activation-9.60e+00

Pos logit contributions
 semester+3.537
Feb+3.108
 weeks+3.031
EMBER+2.858
 hrs+2.836
Neg logit contributions
 lifestyles-2.851
 personalities-2.763
 techn-2.656
 Behavior-2.592
 Responsibility-2.585
Token makes
Token ID1838
Feature activation-7.55e-01

Pos logit contributions
 semester+9.173
 weeks+8.111
Feb+8.019
.+7.529
 hrs+7.515
Neg logit contributions
 lifestyles-5.782
 personalities-5.601
 Flavoring-5.561
 Behavior-5.551
 Resistance-5.484
Token appointments
Token ID23976
Feature activation+1.86e+00

Pos logit contributions
 semester+0.567
Feb+0.490
 weeks+0.459
EMBER+0.446
 hrs+0.435
Neg logit contributions
 lifestyles-0.690
 personalities-0.668
 techn-0.642
 behaviour-0.638
 voices-0.636
Token by
Token ID416
Feature activation+4.33e-01

Pos logit contributions
 lifestyles+1.690
 personalities+1.635
 behaviour+1.581
 voices+1.571
 techn+1.564
Neg logit contributions
 semester-1.405
Feb-1.240
EMBER-1.137
imeo-1.123
imester-1.090
Token when
Token ID618
Feature activation-7.81e+00

Pos logit contributions
 semester+7.195
Feb+6.264
 weeks+6.069
EMBER+5.768
.+5.748
Neg logit contributions
 lifestyles-7.655
 personalities-7.339
 Responsibility-6.995
 behaviour-6.940
 voices-6.930
Token it
Token ID340
Feature activation-1.54e+01

Pos logit contributions
 semester+6.893
Feb+6.097
 weeks+5.835
EMBER+5.724
 hrs+5.538
Neg logit contributions
 lifestyles-5.824
 personalities-5.532
 behaviour-5.206
 masculinity-5.181
 techn-5.170
Token arrives
Token ID14443
Feature activation-1.60e+01

Pos logit contributions
 semester+11.707
 weeks+10.215
Feb+10.153
.+9.632
 hrs+9.569
Neg logit contributions
 lifestyles-11.368
 personalities-10.839
 masculinity-10.543
 Flavoring-10.539
 techn-10.276
Token at
Token ID379
Feature activation-8.99e+00

Pos logit contributions
 semester+10.695
 weeks+9.353
Feb+9.313
.+9.283
EMBER+8.584
Neg logit contributions
 lifestyles-13.663
 personalities-13.181
 Flavoring-12.595
 techn-12.456
 Responsibility-12.437
Token the
Token ID262
Feature activation-8.81e+00

Pos logit contributions
 semester+8.378
Feb+7.392
 weeks+7.237
EMBER+7.044
 hrs+6.937
Neg logit contributions
 lifestyles-6.197
 personalities-5.842
 behaviour-5.387
 voices-5.379
 masculinity-5.360
Token end
Token ID886
Feature activation-2.39e+01

Pos logit contributions
 semester+8.114
Feb+7.063
 weeks+6.923
EMBER+6.753
 hrs+6.560
Neg logit contributions
 lifestyles-6.099
 personalities-5.836
 masculinity-5.460
 nationalism-5.390
 behaviour-5.388
Token of
Token ID286
Feature activation-1.11e+01

Pos logit contributions
 semester+16.938
.+14.518
Feb+14.454
 weeks+14.408
EMBER+13.538
Neg logit contributions
 lifestyles-16.221
 personalities-15.539
 voices-14.779
 masculinity-14.643
 behaviour-14.397
Token this
Token ID428
Feature activation-1.50e+01

Pos logit contributions
 semester+10.215
Feb+8.932
 weeks+8.728
EMBER+8.244
 hrs+7.991
Neg logit contributions
 lifestyles-7.707
 personalities-7.495
 voices-6.964
 behaviour-6.820
 techn-6.809
Token month
Token ID1227
Feature activation-2.12e+01

Pos logit contributions
 semester+13.046
 weeks+11.064
Feb+10.732
 months+10.008
 afternoon+9.883
Neg logit contributions
 lifestyles-10.497
 personalities-10.258
 voices-9.628
 Responsibility-9.535
 Flavoring-9.494
Token.
Token ID13
Feature activation+5.05e-01

Pos logit contributions
 semester+14.707
.+13.215
Feb+12.599
 weeks+12.232
EMBER+11.679
Neg logit contributions
 lifestyles-15.523
 personalities-15.138
 Controls-14.107
 behaviour-14.051
 techn-14.046
Token
Token ID198
Feature activation-5.34e+00

Pos logit contributions
 lifestyles+0.388
 personalities+0.373
 behaviour+0.355
 techn+0.354
 voices+0.353
Neg logit contributions
 semester-0.457
Feb-0.409
EMBER-0.381
 weeks-0.380
 hrs-0.371
Token happened
Token ID3022
Feature activation-1.17e+01

Pos logit contributions
 semester+8.339
Feb+7.262
 weeks+7.123
.+6.846
 hrs+6.728
Neg logit contributions
 lifestyles-7.812
 personalities-7.417
 Flavoring-7.230
 techn-7.045
 Responsibility-7.009
Token to
Token ID284
Feature activation-6.93e+00

Pos logit contributions
 semester+8.420
Feb+7.284
 weeks+7.251
 hrs+6.719
.+6.582
Neg logit contributions
 lifestyles-10.004
 personalities-9.596
 Responsibility-9.232
 Flavoring-9.230
 masculinity-9.092
Token me
Token ID502
Feature activation-1.30e+01

Pos logit contributions
 semester+6.864
Feb+6.165
 weeks+5.981
 hrs+5.752
EMBER+5.724
Neg logit contributions
 lifestyles-4.410
 personalities-4.113
 Responsibility-3.879
 voices-3.831
 Flavoring-3.819
Token at
Token ID379
Feature activation-1.11e+01

Pos logit contributions
 semester+9.477
 weeks+8.201
Feb+8.187
.+7.687
 hrs+7.675
Neg logit contributions
 lifestyles-10.868
 personalities-10.435
 Responsibility-9.943
 techn-9.866
 voices-9.785
Token some
Token ID617
Feature activation-1.32e+01

Pos logit contributions
 semester+9.837
Feb+8.473
 weeks+8.341
 hrs+8.010
EMBER+7.819
Neg logit contributions
 lifestyles-7.775
 personalities-7.392
 voices-6.873
 behaviour-6.857
 Responsibility-6.854
Token point
Token ID966
Feature activation-2.39e+01

Pos logit contributions
 semester+8.445
 weeks+6.984
Feb+6.950
 hrs+6.515
.+6.250
Neg logit contributions
 lifestyles-12.069
 personalities-11.556
 Responsibility-11.097
 Policies-11.042
 nationalism-11.039
Token).
Token ID737
Feature activation+1.54e-01

Pos logit contributions
 semester+16.119
 weeks+14.493
.+14.458
Feb+13.786
 apiece+13.287
Neg logit contributions
 lifestyles-16.046
 personalities-15.431
 Policies-14.503
 masculinity-14.459
 nationalism-14.451
Token The
Token ID383
Feature activation+3.16e+00

Pos logit contributions
 lifestyles+0.109
 personalities+0.105
 behaviour+0.099
 techn+0.099
 voices+0.098
Neg logit contributions
 semester-0.148
Feb-0.133
 weeks-0.125
EMBER-0.124
 hrs-0.122
Token flash
Token ID7644
Feature activation+2.38e+00

Pos logit contributions
 lifestyles+2.476
 personalities+2.387
 behaviour+2.296
 techn+2.278
 voices+2.272
Neg logit contributions
 semester-2.795
Feb-2.500
EMBER-2.316
 weeks-2.289
imeo-2.268
Token process
Token ID1429
Feature activation-3.50e+00

Pos logit contributions
 lifestyles+1.801
 personalities+1.734
 behaviour+1.660
 techn+1.651
 voices+1.641
Neg logit contributions
 semester-2.172
Feb-1.946
EMBER-1.810
 weeks-1.798
imeo-1.769
Token fails
Token ID10143
Feature activation-2.57e+00

Pos logit contributions
 semester+2.947
Feb+2.573
 weeks+2.426
EMBER+2.362
 hrs+2.358
Neg logit contributions
 lifestyles-2.859
 personalities-2.724
 techn-2.596
 voices-2.588
 behaviour-2.569
Token:
Token ID25
Feature activation-1.59e+00

Pos logit contributions
 lifestyles+0.830
 personalities+0.801
 behaviour+0.768
 voices+0.768
 techn+0.766
Neg logit contributions
 semester-0.757
Feb-0.666
EMBER-0.606
 weeks-0.604
imeo-0.599
Token at
Token ID379
Feature activation-6.31e+00

Pos logit contributions
 semester+1.561
Feb+1.408
 weeks+1.327
EMBER+1.313
 hrs+1.294
Neg logit contributions
 lifestyles-1.098
 personalities-1.051
 behaviour-1.001
 techn-0.989
 voices-0.983
Token Arizona
Token ID7943
Feature activation-4.91e+00

Pos logit contributions
 semester+5.908
Feb+5.326
 weeks+5.080
EMBER+4.942
 hrs+4.942
Neg logit contributions
 lifestyles-4.425
 personalities-4.254
 behaviour-4.047
 techn-4.006
 voices-3.925
Token Cardinals
Token ID18071
Feature activation-7.38e+00

Pos logit contributions
 semester+3.948
Feb+3.481
 weeks+3.251
EMBER+3.208
 hrs+3.127
Neg logit contributions
 lifestyles-4.221
 personalities-4.056
 behaviour-3.897
 techn-3.859
 voices-3.856
Token on
Token ID319
Feature activation-1.11e+01

Pos logit contributions
 semester+4.517
Feb+3.853
 weeks+3.513
EMBER+3.447
 hrs+3.325
Neg logit contributions
 lifestyles-7.593
 personalities-7.353
 behaviour-7.079
 techn-7.077
 voices-7.073
Token Thursday
Token ID3635
Feature activation-2.39e+01

Pos logit contributions
 semester+7.530
Feb+6.612
 weeks+6.325
EMBER+5.817
 hrs+5.794
Neg logit contributions
 lifestyles-9.914
 personalities-9.602
 behaviour-9.161
 voices-9.086
 techn-9.029
Token.
Token ID13
Feature activation-4.97e+00

Pos logit contributions
 semester+17.015
.+15.352
Feb+15.039
 afternoon+14.845
 weeks+14.469
Neg logit contributions
 lifestyles-16.140
 personalities-15.275
 Policies-14.422
 masculinity-14.399
 behaviour-14.357
Token
Token ID198
Feature activation-9.50e+00

Pos logit contributions
 semester+4.311
Feb+3.853
 weeks+3.620
EMBER+3.553
 hrs+3.528
Neg logit contributions
 lifestyles-3.892
 personalities-3.765
 behaviour-3.602
 techn-3.535
 voices-3.514
Token
Token ID198
Feature activation-6.67e+00

Pos logit contributions
 semester+5.868
Feb+5.388
.+4.857
 weeks+4.809
EMBER+4.549
Neg logit contributions
 lifestyles-9.541
 personalities-9.307
 techn-8.842
avorite-8.724
 behaviour-8.675
TokenWhen
Token ID2215
Feature activation-1.00e+00

Pos logit contributions
 semester+4.890
Feb+4.620
EMBER+4.146
 weeks+3.980
 hrs+3.892
Neg logit contributions
 lifestyles-6.067
 personalities-5.845
 techn-5.600
 behaviour-5.591
 voices-5.496
Token other
Token ID584
Feature activation-1.53e+00

Pos logit contributions
 semester+0.949
Feb+0.846
 weeks+0.802
EMBER+0.787
 hrs+0.775
Neg logit contributions
 lifestyles-0.724
 personalities-0.689
 behaviour-0.661
 techn-0.654
 voices-0.646
Token ambition
Token ID20505
Feature activation+4.21e+00

Pos logit contributions
 lifestyles+4.901
 personalities+4.680
 behaviour+4.465
 voices+4.427
 techn+4.424
Neg logit contributions
 semester-6.786
Feb-6.255
EMBER-5.849
imeo-5.809
imester-5.756
Token to
Token ID284
Feature activation+3.60e+00

Pos logit contributions
 lifestyles+4.250
 personalities+4.120
 behaviour+3.986
 techn+3.979
 voices+3.969
Neg logit contributions
 semester-2.754
Feb-2.389
EMBER-2.134
imeo-2.099
 weeks-2.085
Token establish
Token ID4474
Feature activation+6.21e+00

Pos logit contributions
 lifestyles+2.659
 personalities+2.552
 behaviour+2.433
 techn+2.432
 voices+2.415
Neg logit contributions
 semester-3.342
Feb-3.014
EMBER-2.809
 weeks-2.782
imeo-2.758
Token a
Token ID257
Feature activation+1.08e+00

Pos logit contributions
 lifestyles+4.170
 personalities+3.980
 techn+3.773
 behaviour+3.758
 voices+3.742
Neg logit contributions
 semester-6.173
Feb-5.618
EMBER-5.276
imeo-5.192
 weeks-5.168
Token
Token ID564
Feature activation-1.50e+00

Pos logit contributions
 lifestyles+0.681
 personalities+0.650
 behaviour+0.610
 voices+0.608
 techn+0.603
Neg logit contributions
 semester-1.132
Feb-1.020
 weeks-0.964
EMBER-0.956
 hrs-0.937
Token
Token ID250
Feature activation+1.28e+01

Pos logit contributions
 semester+1.157
Feb+1.010
EMBER+0.928
 weeks+0.925
 hrs+0.898
Neg logit contributions
 lifestyles-1.360
 personalities-1.307
 behaviour-1.259
 techn-1.247
 voices-1.237
TokenGreat
Token ID13681
Feature activation+3.56e+00

Pos logit contributions
 lifestyles+10.424
 personalities+10.093
 techn+9.819
 Resistance+9.794
 nationalism+9.790
Neg logit contributions
 semester-9.485
Feb-8.096
 weeks-7.557
 hrs-7.524
EMBER-7.438
Token Zionist
Token ID29390
Feature activation+1.21e+01

Pos logit contributions
 lifestyles+2.537
 personalities+2.432
 behaviour+2.308
 techn+2.305
 voices+2.296
Neg logit contributions
 semester-3.403
Feb-3.058
EMBER-2.855
 weeks-2.846
imeo-2.796
Token Empire
Token ID8065
Feature activation+3.52e+00

Pos logit contributions
 lifestyles+8.729
 Resistance+8.531
 techn+8.391
 personalities+8.366
 Responsibility+8.248
Neg logit contributions
 semester-10.016
Feb-9.227
imeo-8.834
imester-8.468
EMBER-8.464
Token
Token ID447
Feature activation-5.02e+00

Pos logit contributions
 lifestyles+3.432
 personalities+3.327
 techn+3.225
 behaviour+3.207
 voices+3.201
Neg logit contributions
 semester-2.421
Feb-2.100
EMBER-1.881
imeo-1.863
 weeks-1.860
Token
Token ID251
Feature activation+1.00e+01

Pos logit contributions
 semester+3.701
Feb+3.233
EMBER+2.967
 weeks+2.935
 hrs+2.849
Neg logit contributions
 lifestyles-4.647
 personalities-4.465
 behaviour-4.310
 techn-4.303
 voices-4.248
Token
Token ID851
Feature activation+2.05e+00

Pos logit contributions
 lifestyles+5.213
 personalities+5.095
 behaviour+4.985
 techn+4.984
 voices+4.967
Neg logit contributions
 semester-1.958
Feb-1.542
EMBER-1.303
imeo-1.256
 weeks-1.235
Token but
Token ID475
Feature activation+1.87e+00

Pos logit contributions
 lifestyles+1.333
 personalities+1.267
 behaviour+1.197
 techn+1.189
 voices+1.185
Neg logit contributions
 semester-2.100
Feb-1.903
 weeks-1.786
EMBER-1.781
 hrs-1.750
Token it
Token ID340
Feature activation-4.51e+00

Pos logit contributions
 lifestyles+1.433
 personalities+1.375
 behaviour+1.309
 techn+1.303
 voices+1.301
Neg logit contributions
 semester-1.700
Feb-1.518
 weeks-1.413
EMBER-1.409
 hrs-1.379
Token won
Token ID1839
Feature activation-1.96e+00

Pos logit contributions
 semester+3.875
Feb+3.417
 weeks+3.241
 hrs+3.134
EMBER+3.071
Neg logit contributions
 lifestyles-3.567
 personalities-3.442
 behaviour-3.272
 techn-3.244
 opinions-3.240
Token
Token ID447
Feature activation-7.05e+00

Pos logit contributions
 semester+1.472
Feb+1.292
 weeks+1.178
EMBER+1.170
 hrs+1.143
Neg logit contributions
 lifestyles-1.800
 personalities-1.743
 behaviour-1.670
 techn-1.665
 voices-1.658
Token
Token ID247
Feature activation+1.03e+01

Pos logit contributions
 semester+5.101
Feb+4.474
EMBER+4.060
 weeks+4.029
 hrs+3.970
Neg logit contributions
 lifestyles-6.567
 personalities-6.251
 behaviour-6.114
 techn-6.061
 voices-5.964
Tokent
Token ID83
Feature activation-4.74e-01

Pos logit contributions
 lifestyles+7.863
 personalities+7.660
 voices+7.396
 techn+7.367
 behaviour+7.352
Neg logit contributions
 semester-8.471
Feb-7.449
EMBER-7.043
imeo-6.858
 weeks-6.769
Token if
Token ID611
Feature activation-1.06e+00

Pos logit contributions
 semester+0.344
Feb+0.298
EMBER+0.271
 weeks+0.270
imeo+0.263
Neg logit contributions
 lifestyles-0.449
 personalities-0.434
 behaviour-0.418
 techn-0.417
 voices-0.416
Token leaders
Token ID2766
Feature activation+2.37e+00

Pos logit contributions
 semester+1.037
Feb+0.940
 weeks+0.886
EMBER+0.873
 hrs+0.862
Neg logit contributions
 lifestyles-0.727
 personalities-0.691
 behaviour-0.654
 voices-0.641
 Responsibility-0.636
Token don
Token ID836
Feature activation-4.37e+00

Pos logit contributions
 lifestyles+2.082
 personalities+2.015
 behaviour+1.939
 techn+1.939
 voices+1.934
Neg logit contributions
 semester-1.860
Feb-1.636
EMBER-1.504
 weeks-1.484
imeo-1.464
Token
Token ID447
Feature activation-6.75e+00

Pos logit contributions
 semester+2.950
Feb+2.608
 weeks+2.336
EMBER+2.330
 hrs+2.240
Neg logit contributions
 lifestyles-4.301
 personalities-4.182
 techn-3.998
 behaviour-3.989
 voices-3.949
Token a
Token ID257
Feature activation+2.97e+00

Pos logit contributions
 lifestyles+2.512
 personalities+2.406
 behaviour+2.284
 voices+2.282
 techn+2.273
Neg logit contributions
 semester-3.340
Feb-3.018
EMBER-2.817
 weeks-2.786
imeo-2.752
Token shotgun
Token ID18607
Feature activation-3.19e+00

Pos logit contributions
 lifestyles+2.050
 personalities+1.959
 behaviour+1.863
 techn+1.859
 voices+1.853
Neg logit contributions
 semester-2.899
Feb-2.629
EMBER-2.461
 weeks-2.440
imeo-2.411
Token,
Token ID11
Feature activation+4.05e+00

Pos logit contributions
 semester+1.968
Feb+1.638
 weeks+1.486
EMBER+1.444
 hrs+1.399
Neg logit contributions
 lifestyles-3.349
 personalities-3.253
 behaviour-3.151
 techn-3.132
 voices-3.124
Token you
Token ID345
Feature activation-5.41e+00

Pos logit contributions
 lifestyles+2.800
 personalities+2.677
 behaviour+2.537
 techn+2.534
 voices+2.533
Neg logit contributions
 semester-3.949
Feb-3.570
EMBER-3.343
 weeks-3.309
imeo-3.276
Token
Token ID447
Feature activation-8.01e+00

Pos logit contributions
 semester+3.758
Feb+3.215
 weeks+2.976
EMBER+2.899
 hrs+2.829
Neg logit contributions
 lifestyles-5.151
 personalities-5.004
 techn-4.802
 behaviour-4.787
 voices-4.739
Token
Token ID247
Feature activation+9.89e+00

Pos logit contributions
 semester+5.704
Feb+5.015
EMBER+4.622
 weeks+4.430
 hrs+4.416
Neg logit contributions
 lifestyles-7.536
 personalities-7.199
 techn-7.047
 behaviour-7.026
 voices-6.851
Tokenve
Token ID303
Feature activation+4.71e-02

Pos logit contributions
 lifestyles+5.088
 personalities+4.845
 voices+4.757
 techn+4.663
 behaviour+4.640
Neg logit contributions
 semester-10.408
Feb-9.416
EMBER-8.957
 weeks-8.869
imeo-8.858
Token got
Token ID1392
Feature activation+9.83e-01

Pos logit contributions
 lifestyles+0.045
 personalities+0.044
 behaviour+0.042
 techn+0.042
 voices+0.042
Neg logit contributions
 semester-0.034
Feb-0.029
 weeks-0.027
EMBER-0.026
 hrs-0.026
Token a
Token ID257
Feature activation+6.66e-01

Pos logit contributions
 lifestyles+0.713
 personalities+0.683
 behaviour+0.650
 techn+0.648
 voices+0.644
Neg logit contributions
 semester-0.932
Feb-0.833
 weeks-0.780
EMBER-0.776
 hrs-0.761
Token gun
Token ID2485
Feature activation-3.45e+00

Pos logit contributions
 lifestyles+0.487
 personalities+0.467
 behaviour+0.444
 techn+0.442
 voices+0.441
Neg logit contributions
 semester-0.628
Feb-0.562
 weeks-0.524
EMBER-0.524
 hrs-0.512
Token in
Token ID287
Feature activation-1.95e+00

Pos logit contributions
 semester+2.187
Feb+1.830
 weeks+1.661
EMBER+1.623
 apiece+1.563
Neg logit contributions
 lifestyles-3.574
 personalities-3.466
 behaviour-3.354
 techn-3.333
 voices-3.330
Token
Token ID447
Feature activation-5.31e+00

Pos logit contributions
 lifestyles+2.838
 personalities+2.707
 voices+2.578
 behaviour+2.574
 techn+2.565
Neg logit contributions
 semester-4.030
Feb-3.607
EMBER-3.392
 weeks-3.365
imeo-3.338
Token
Token ID251
Feature activation+9.70e+00

Pos logit contributions
 semester+3.982
Feb+3.496
EMBER+3.180
 weeks+3.168
 hrs+3.119
Neg logit contributions
 lifestyles-4.853
 personalities-4.644
 behaviour-4.512
 techn-4.499
 voices-4.410
Token
Token ID198
Feature activation-3.16e+00

Pos logit contributions
 lifestyles+6.968
 Resistance+6.673
 personalities+6.647
 Behavior+6.606
 voices+6.507
Neg logit contributions
 semester-8.468
Feb-7.416
EMBER-7.038
imeo-6.960
 weeks-6.878
Token
Token ID198
Feature activation-1.63e+00

Pos logit contributions
 semester+2.431
Feb+2.162
 weeks+1.973
EMBER+1.951
 hrs+1.904
Neg logit contributions
 lifestyles-2.867
 personalities-2.773
 techn-2.643
 behaviour-2.631
 voices-2.604
TokenTrans
Token ID8291
Feature activation+6.44e+00

Pos logit contributions
 semester+1.223
Feb+1.086
EMBER+0.981
 weeks+0.973
 hrs+0.947
Neg logit contributions
 lifestyles-1.497
 personalities-1.446
 techn-1.389
 behaviour-1.389
 voices-1.379
Tokengender
Token ID8388
Feature activation+1.39e+01

Pos logit contributions
 lifestyles+3.551
 personalities+3.371
 voices+3.145
 behaviour+3.111
 techn+3.066
Neg logit contributions
 semester-7.151
Feb-6.528
EMBER-6.219
 weeks-6.138
imeo-6.102
Token identity
Token ID5369
Feature activation+8.67e+00

Pos logit contributions
 lifestyles+10.946
 personalities+10.553
 voices+10.261
 behaviour+9.954
 opinions+9.818
Neg logit contributions
 semester-11.210
Feb-10.095
EMBER-9.578
imeo-9.343
iatus-9.071
Token may
Token ID743
Feature activation+2.10e+00

Pos logit contributions
 lifestyles+6.976
 personalities+6.748
 voices+6.457
 behaviour+6.422
 techn+6.373
Neg logit contributions
 semester-7.190
Feb-6.496
EMBER-6.103
imeo-6.024
 hrs-5.802
Token be
Token ID307
Feature activation+1.44e+00

Pos logit contributions
 lifestyles+1.728
 personalities+1.665
 behaviour+1.595
 techn+1.589
 voices+1.588
Neg logit contributions
 semester-1.786
Feb-1.587
EMBER-1.469
 weeks-1.454
imeo-1.430
Token a
Token ID257
Feature activation+2.04e+00

Pos logit contributions
 lifestyles+1.146
 personalities+1.103
 behaviour+1.053
 techn+1.049
 voices+1.048
Neg logit contributions
 semester-1.266
Feb-1.123
 weeks-1.042
EMBER-1.039
imeo-1.014
Token relatively
Token ID5365
Feature activation+2.96e+00

Pos logit contributions
 lifestyles+1.461
 personalities+1.399
 behaviour+1.330
 techn+1.325
 voices+1.321
Neg logit contributions
 semester-1.943
Feb-1.747
EMBER-1.630
 weeks-1.625
imeo-1.595
Token think
Token ID892
Feature activation+3.13e+00

Pos logit contributions
 lifestyles+0.460
 personalities+0.445
 behaviour+0.427
 voices+0.425
 techn+0.424
Neg logit contributions
 semester-0.428
Feb-0.378
EMBER-0.348
 weeks-0.344
imeo-0.338
Token one
Token ID530
Feature activation-6.83e+00

Pos logit contributions
 lifestyles+2.558
 personalities+2.473
 voices+2.366
 behaviour+2.356
 techn+2.350
Neg logit contributions
 semester-2.654
Feb-2.380
EMBER-2.206
 weeks-2.158
imeo-2.157
Token side
Token ID1735
Feature activation-3.30e+00

Pos logit contributions
 semester+6.761
Feb+5.792
 weeks+5.619
.+5.337
EMBER+5.322
Neg logit contributions
 lifestyles-4.457
 personalities-4.253
 techn-4.053
 Responsibility-4.039
 Resistance-3.999
Token is
Token ID318
Feature activation-5.63e-01

Pos logit contributions
 semester+3.034
Feb+2.657
 weeks+2.526
EMBER+2.460
 hrs+2.431
Neg logit contributions
 lifestyles-2.444
 personalities-2.343
 behaviour-2.249
 techn-2.245
 Responsibility-2.217
Token superior
Token ID9098
Feature activation+9.06e+00

Pos logit contributions
 semester+0.496
Feb+0.435
 weeks+0.410
EMBER+0.401
 hrs+0.394
Neg logit contributions
 lifestyles-0.444
 personalities-0.424
 behaviour-0.406
 techn-0.403
 voices-0.402
Token;
Token ID26
Feature activation+9.98e+00

Pos logit contributions
 lifestyles+9.857
 personalities+9.655
 behaviour+9.341
 voices+9.313
 opinions+9.256
Neg logit contributions
 semester-4.712
Feb-4.157
EMBER-3.650
imeo-3.515
 hrs-3.441
Token usually
Token ID3221
Feature activation-3.40e+00

Pos logit contributions
 lifestyles+7.282
 personalities+7.077
 voices+6.809
 opinions+6.734
 behaviour+6.697
Neg logit contributions
 semester-8.612
Feb-7.963
EMBER-7.401
imeo-7.322
iatus-7.138
Token it
Token ID340
Feature activation-7.21e+00

Pos logit contributions
 semester+2.913
Feb+2.521
 weeks+2.400
EMBER+2.306
 hrs+2.287
Neg logit contributions
 lifestyles-2.736
 personalities-2.610
 behaviour-2.514
 techn-2.504
 Responsibility-2.493
Token
Token ID447
Feature activation-6.39e+00

Pos logit contributions
 semester+5.898
Feb+5.097
 weeks+4.875
 hrs+4.628
.+4.565
Neg logit contributions
 lifestyles-5.854
 personalities-5.594
 behaviour-5.392
 techn-5.371
 Resistance-5.368
Token
Token ID247
Feature activation+1.12e+01

Pos logit contributions
 semester+4.756
Feb+4.177
EMBER+3.790
 weeks+3.775
 hrs+3.705
Neg logit contributions
 lifestyles-5.871
 personalities-5.590
 behaviour-5.458
 techn-5.446
 voices-5.318
Tokens
Token ID82
Feature activation+3.69e+00

Pos logit contributions
 lifestyles+6.159
 personalities+6.003
 voices+5.813
 opinions+5.684
 techn+5.634
Neg logit contributions
 semester-11.264
Feb-10.172
EMBER-9.953
imeo-9.426
 weeks-9.367
TokenOne
Token ID3198
Feature activation-4.90e+00

Pos logit contributions
 semester+1.739
Feb+1.559
EMBER+1.403
 weeks+1.376
 hrs+1.335
Neg logit contributions
 lifestyles-2.360
 personalities-2.295
 techn-2.204
 behaviour-2.195
 voices-2.195
Token of
Token ID286
Feature activation+2.59e+00

Pos logit contributions
 semester+3.754
Feb+3.193
 weeks+3.014
EMBER+2.937
imeo+2.830
Neg logit contributions
 lifestyles-4.392
 personalities-4.253
 voices-4.041
 techn-4.030
 behaviour-4.023
Token the
Token ID262
Feature activation+1.91e+00

Pos logit contributions
 lifestyles+1.489
 personalities+1.411
 behaviour+1.322
 techn+1.316
 voices+1.313
Neg logit contributions
 semester-2.846
Feb-2.589
 weeks-2.443
EMBER-2.443
imeo-2.398
Token best
Token ID1266
Feature activation+2.67e+00

Pos logit contributions
 lifestyles+1.350
 personalities+1.293
 behaviour+1.226
 techn+1.221
 voices+1.220
Neg logit contributions
 semester-1.845
Feb-1.664
EMBER-1.551
 weeks-1.544
imeo-1.520
Token ways
Token ID2842
Feature activation-2.22e-01

Pos logit contributions
 lifestyles+1.654
 personalities+1.573
 behaviour+1.481
 techn+1.474
 voices+1.473
Neg logit contributions
 semester-2.801
Feb-2.551
EMBER-2.390
 weeks-2.377
imeo-2.350
Token to
Token ID284
Feature activation-1.57e-01

Pos logit contributions
 semester+0.150
Feb+0.127
 weeks+0.116
EMBER+0.116
 hrs+0.111
Neg logit contributions
 lifestyles-0.221
 personalities-0.215
 behaviour-0.207
 voices-0.207
 techn-0.207
Token achieve
Token ID4620
Feature activation+6.03e+00

Pos logit contributions
 semester+0.145
Feb+0.128
 weeks+0.121
EMBER+0.120
 hrs+0.117
Neg logit contributions
 lifestyles-0.118
 personalities-0.114
 techn-0.108
 behaviour-0.108
 voices-0.108
Token effort
Token ID3626
Feature activation+2.37e+00

Pos logit contributions
 lifestyles+4.526
 personalities+4.281
 behaviour+4.134
 techn+4.084
 voices+4.068
Neg logit contributions
 semester-5.448
Feb-4.948
EMBER-4.559
imeo-4.493
 hrs-4.446
Tokenless
Token ID1203
Feature activation+6.16e+00

Pos logit contributions
 lifestyles+1.689
 personalities+1.613
 behaviour+1.536
 techn+1.529
 voices+1.520
Neg logit contributions
 semester-2.280
Feb-2.052
EMBER-1.911
 weeks-1.902
imeo-1.877
Token and
Token ID290
Feature activation+5.25e+00

Pos logit contributions
 lifestyles+4.775
 personalities+4.506
 behaviour+4.391
 techn+4.299
 voices+4.283
Neg logit contributions
 semester-5.462
Feb-4.928
EMBER-4.518
imeo-4.478
 hrs-4.406
Token long
Token ID890
Feature activation-5.15e+00

Pos logit contributions
 lifestyles+4.069
 personalities+3.841
 behaviour+3.742
 techn+3.732
 voices+3.661
Neg logit contributions
 semester-4.590
Feb-4.148
EMBER-3.825
imeo-3.764
 hrs-3.734
Token their
Token ID511
Feature activation-2.40e+00

Pos logit contributions
 semester+1.946
Feb+1.744
 weeks+1.662
EMBER+1.628
imeo+1.600
Neg logit contributions
 lifestyles-1.336
 personalities-1.272
 behaviour-1.205
 voices-1.193
 techn-1.189
Token screens
Token ID8947
Feature activation-1.01e+01

Pos logit contributions
 semester+2.193
Feb+1.931
 weeks+1.842
EMBER+1.809
 hrs+1.765
Neg logit contributions
 lifestyles-1.776
 personalities-1.703
 behaviour-1.620
 techn-1.609
 Resistance-1.605
Token.
Token ID13
Feature activation+5.00e+00

Pos logit contributions
 semester+6.464
Feb+5.501
 weeks+5.248
.+5.054
 apiece+4.885
Neg logit contributions
 lifestyles-9.852
 personalities-9.496
 Responsibility-9.112
 behaviour-9.098
 Resistance-9.083
Token L
Token ID406
Feature activation+3.45e-01

Pos logit contributions
 lifestyles+3.581
 personalities+3.427
 techn+3.294
 voices+3.285
 behaviour+3.275
Neg logit contributions
 semester-4.698
Feb-4.176
EMBER-3.917
 weeks-3.880
imeo-3.856
Tokenapt
Token ID2373
Feature activation+4.07e+00

Pos logit contributions
 lifestyles+0.305
 personalities+0.295
 behaviour+0.283
 techn+0.282
 voices+0.281
Neg logit contributions
 semester-0.272
Feb-0.238
EMBER-0.218
 weeks-0.218
imeo-0.212
Tokenops
Token ID2840
Feature activation+5.73e+00

Pos logit contributions
 lifestyles+3.589
 personalities+3.455
 behaviour+3.340
 techn+3.335
 voices+3.323
Neg logit contributions
 semester-3.197
Feb-2.790
EMBER-2.578
 weeks-2.512
 hrs-2.477
Token must
Token ID1276
Feature activation+1.30e+00

Pos logit contributions
 lifestyles+5.027
 personalities+4.872
 behaviour+4.689
 techn+4.689
 voices+4.671
Neg logit contributions
 semester-4.377
Feb-3.885
EMBER-3.604
imeo-3.507
 weeks-3.444
Token already
Token ID1541
Feature activation-4.27e+00

Pos logit contributions
 lifestyles+1.077
 personalities+1.040
 behaviour+0.999
 techn+0.998
 voices+0.993
Neg logit contributions
 semester-1.088
Feb-0.967
EMBER-0.893
 weeks-0.883
imeo-0.869
Token be
Token ID307
Feature activation-1.18e+00

Pos logit contributions
 semester+3.388
Feb+2.899
 weeks+2.748
EMBER+2.637
 hrs+2.631
Neg logit contributions
 lifestyles-3.748
 personalities-3.601
 Resistance-3.410
 voices-3.402
 behaviour-3.399
Token pulled
Token ID5954
Feature activation+4.40e+00

Pos logit contributions
 semester+0.867
Feb+0.749
 weeks+0.684
EMBER+0.679
 hrs+0.659
Neg logit contributions
 lifestyles-1.106
 personalities-1.071
 behaviour-1.027
 voices-1.024
 techn-1.023
Token out
Token ID503
Feature activation-3.81e+00

Pos logit contributions
 lifestyles+3.999
 personalities+3.870
 behaviour+3.751
 voices+3.737
 techn+3.718
Neg logit contributions
 semester-3.206
Feb-2.857
EMBER-2.644
imeo-2.600
 hrs-2.503
Token them
Token ID606
Feature activation-4.52e+00

Pos logit contributions
 lifestyles+0.493
 personalities+0.469
 behaviour+0.444
 techn+0.441
 voices+0.436
Neg logit contributions
 semester-0.832
Feb-0.753
 weeks-0.713
EMBER-0.703
 hrs-0.694
Token from
Token ID422
Feature activation-1.82e+00

Pos logit contributions
 semester+3.551
Feb+3.071
 weeks+2.940
EMBER+2.757
 apiece+2.733
Neg logit contributions
 lifestyles-3.896
 personalities-3.782
 Responsibility-3.628
 behaviour-3.625
 Resistance-3.567
Token complaining
Token ID18705
Feature activation+1.16e+00

Pos logit contributions
 semester+1.573
Feb+1.390
 weeks+1.301
EMBER+1.281
 hrs+1.245
Neg logit contributions
 lifestyles-1.461
 personalities-1.397
 behaviour-1.339
 techn-1.334
 voices-1.315
Token to
Token ID284
Feature activation+6.50e-01

Pos logit contributions
 lifestyles+1.162
 personalities+1.129
 voices+1.094
 behaviour+1.091
 techn+1.088
Neg logit contributions
 semester-0.780
Feb-0.666
EMBER-0.599
 weeks-0.585
imeo-0.583
Token Congress
Token ID3162
Feature activation-9.73e+00

Pos logit contributions
 lifestyles+0.429
 personalities+0.408
 behaviour+0.386
 techn+0.382
 voices+0.380
Neg logit contributions
 semester-0.658
Feb-0.594
 weeks-0.562
EMBER-0.558
 hrs-0.546
Token about
Token ID546
Feature activation+1.17e+00

Pos logit contributions
 semester+6.717
Feb+5.868
 weeks+5.694
.+5.498
EMBER+5.386
Neg logit contributions
 lifestyles-8.787
 personalities-8.410
 behaviour-8.125
 techn-8.026
 Behavior-7.985
Token IRS
Token ID14440
Feature activation+4.13e+00

Pos logit contributions
 lifestyles+0.756
 personalities+0.724
 techn+0.679
 behaviour+0.679
 voices+0.676
Neg logit contributions
 semester-1.190
Feb-1.073
 weeks-1.016
EMBER-1.002
imeo-0.984
Token
Token ID447
Feature activation-1.68e+00

Pos logit contributions
 lifestyles+2.420
 personalities+2.292
 behaviour+2.168
 techn+2.148
 voices+2.133
Neg logit contributions
 semester-4.490
Feb-4.090
EMBER-3.854
 weeks-3.833
imeo-3.797
Token
Token ID246
Feature activation+1.10e+01

Pos logit contributions
 semester+1.365
Feb+1.202
 weeks+1.106
EMBER+1.105
 hrs+1.080
Neg logit contributions
 lifestyles-1.451
 personalities-1.391
 behaviour-1.339
 techn-1.330
 voices-1.324
Token targeting
Token ID10822
Feature activation+6.59e+00

Pos logit contributions
 lifestyles+9.826
 personalities+9.459
 behaviour+9.451
 opinions+9.156
 techn+9.153
Neg logit contributions
 semester-7.966
Feb-6.857
EMBER-6.368
imeo-6.334
imester-6.174
Token and
Token ID290
Feature activation+6.60e+00

Pos logit contributions
 lifestyles+8.167
 personalities+7.959
 behaviour+7.829
 opinions+7.721
 techn+7.718
Neg logit contributions
 semester-2.738
Feb-2.073
EMBER-1.752
imeo-1.744
 hrs-1.609
Token a
Token ID257
Feature activation-3.98e+00

Pos logit contributions
 semester+0.010
Feb+0.009
 weeks+0.009
EMBER+0.009
 hrs+0.008
Neg logit contributions
 lifestyles-0.007
 personalities-0.007
 behaviour-0.006
 voices-0.006
 techn-0.006
Token sense
Token ID2565
Feature activation-4.80e+00

Pos logit contributions
 semester+3.465
Feb+2.976
 weeks+2.840
EMBER+2.777
 hrs+2.689
Neg logit contributions
 lifestyles-3.166
 personalities-3.042
 Responsibility-2.880
 behaviour-2.869
 voices-2.867
Token,
Token ID11
Feature activation+2.86e+00

Pos logit contributions
 semester+2.541
Feb+2.020
 weeks+1.823
EMBER+1.745
 apiece+1.664
Neg logit contributions
 lifestyles-5.350
 personalities-5.209
 behaviour-5.064
 Responsibility-5.036
 techn-5.017
Token is
Token ID318
Feature activation+9.26e-01

Pos logit contributions
 lifestyles+2.171
 personalities+2.086
 behaviour+1.990
 techn+1.985
 voices+1.978
Neg logit contributions
 semester-2.610
Feb-2.336
EMBER-2.173
 weeks-2.158
imeo-2.127
Token this
Token ID428
Feature activation-2.60e+00

Pos logit contributions
 lifestyles+0.702
 personalities+0.673
 behaviour+0.641
 techn+0.637
 voices+0.636
Neg logit contributions
 semester-0.846
Feb-0.752
 weeks-0.703
EMBER-0.699
 hrs-0.682
Token idea
Token ID2126
Feature activation+2.75e-01

Pos logit contributions
 semester+2.557
Feb+2.260
 weeks+2.151
EMBER+2.106
 hrs+2.062
Neg logit contributions
 lifestyles-1.769
 personalities-1.685
 voices-1.587
 Responsibility-1.581
 behaviour-1.577
Token of
Token ID286
Feature activation+9.15e+00

Pos logit contributions
 lifestyles+0.278
 personalities+0.270
 behaviour+0.260
 techn+0.260
 voices+0.259
Neg logit contributions
 semester-0.181
Feb-0.155
EMBER-0.139
 weeks-0.138
imeo-0.135
Token the
Token ID262
Feature activation+6.42e+00

Pos logit contributions
 lifestyles+6.878
 personalities+6.672
 techn+6.382
 voices+6.334
 behaviour+6.304
Neg logit contributions
 semester-7.990
Feb-7.360
EMBER-6.820
imeo-6.747
imester-6.669
Token global
Token ID3298
Feature activation+6.45e+00

Pos logit contributions
 lifestyles+4.559
 personalities+4.382
 techn+4.189
 behaviour+4.157
 voices+4.126
Neg logit contributions
 semester-6.044
Feb-5.542
EMBER-5.140
imeo-5.056
 weeks-5.050
Token community
Token ID2055
Feature activation+1.73e+00

Pos logit contributions
 lifestyles+4.968
 personalities+4.780
 techn+4.599
 behaviour+4.580
 voices+4.535
Neg logit contributions
 semester-5.665
Feb-5.171
EMBER-4.752
 weeks-4.677
imeo-4.675
Token,
Token ID11
Feature activation+7.91e+00

Pos logit contributions
 lifestyles+1.772
 personalities+1.723
 behaviour+1.663
 techn+1.662
 voices+1.659
Neg logit contributions
 semester-1.112
Feb-0.955
EMBER-0.852
 weeks-0.841
imeo-0.827
Token that
Token ID326
Feature activation-9.99e+00

Pos logit contributions
 semester+2.173
Feb+1.953
 weeks+1.833
EMBER+1.816
 hrs+1.796
Neg logit contributions
 lifestyles-1.721
 personalities-1.639
 behaviour-1.555
 techn-1.552
 voices-1.537
Token time
Token ID640
Feature activation-1.29e+01

Pos logit contributions
 semester+5.939
Feb+4.789
 weeks+4.542
 hrs+4.183
 afternoon+4.134
Neg logit contributions
 lifestyles-10.401
 personalities-9.936
 voices-9.511
 techn-9.503
 opinions-9.408
Token (
Token ID357
Feature activation-5.48e+00

Pos logit contributions
 semester+11.755
Feb+10.567
 weeks+10.469
.+10.079
 hrs+9.779
Neg logit contributions
 lifestyles-7.816
 personalities-7.146
 techn-6.728
 behaviour-6.696
 Behavior-6.636
Tokenstart
Token ID9688
Feature activation-9.42e+00

Pos logit contributions
 semester+3.827
Feb+3.522
EMBER+3.073
 weeks+3.024
 hrs+2.926
Neg logit contributions
 lifestyles-5.253
 personalities-5.054
 techn-4.877
 voices-4.848
 behaviour-4.839
Token of
Token ID286
Feature activation-8.76e-01

Pos logit contributions
 semester+5.980
Feb+5.200
 weeks+4.701
EMBER+4.527
 hrs+4.452
Neg logit contributions
 lifestyles-9.423
 personalities-9.154
 voices-8.752
 opinions-8.664
 techn-8.641
Token the
Token ID262
Feature activation-1.78e+00

Pos logit contributions
 semester+0.781
Feb+0.690
 weeks+0.645
EMBER+0.637
 hrs+0.623
Neg logit contributions
 lifestyles-0.690
 personalities-0.663
 voices-0.630
 behaviour-0.628
 techn-0.628
Token exercise
Token ID5517
Feature activation-1.66e+00

Pos logit contributions
 semester+1.791
Feb+1.590
 weeks+1.515
EMBER+1.487
 hrs+1.459
Neg logit contributions
 lifestyles-1.196
 personalities-1.137
 voices-1.074
 techn-1.065
 behaviour-1.065
Token),
Token ID828
Feature activation+3.78e+00

Pos logit contributions
 semester+1.110
Feb+0.947
 weeks+0.854
EMBER+0.847
 hrs+0.820
Neg logit contributions
 lifestyles-1.667
 personalities-1.616
 techn-1.554
 behaviour-1.554
 voices-1.553
Token "
Token ID366
Feature activation+2.88e+00

Pos logit contributions
 lifestyles+2.662
 personalities+2.554
 behaviour+2.424
 techn+2.415
 voices+2.410
Neg logit contributions
 semester-3.656
Feb-3.290
EMBER-3.074
 weeks-3.057
imeo-3.013
TokenEastern
Token ID46109
Feature activation+1.02e+01

Pos logit contributions
 lifestyles+2.676
 personalities+2.597
 behaviour+2.500
 techn+2.492
 voices+2.490
Neg logit contributions
 semester-2.132
Feb-1.826
 weeks-1.672
EMBER-1.671
imeo-1.636
Token"
Token ID1
Feature activation+1.01e+01

Pos logit contributions
 lifestyles+8.425
 personalities+8.267
 Resistance+7.962
 voices+7.958
 behaviour+7.890
Neg logit contributions
 semester-7.860
Feb-6.993
EMBER-6.377
imeo-6.375
 weeks-6.233
Token where
Token ID810
Feature activation-2.03e+00

Pos logit contributions
 semester+2.009
Feb+1.781
 weeks+1.683
EMBER+1.647
imeo+1.617
Neg logit contributions
 lifestyles-1.642
 personalities-1.570
 techn-1.494
 behaviour-1.488
 voices-1.485
Token it
Token ID340
Feature activation-6.56e+00

Pos logit contributions
 semester+1.957
Feb+1.734
 weeks+1.653
EMBER+1.611
 hrs+1.581
Neg logit contributions
 lifestyles-1.438
 personalities-1.364
 behaviour-1.313
 techn-1.312
 voices-1.285
Token got
Token ID1392
Feature activation-2.97e+00

Pos logit contributions
 semester+5.207
Feb+4.485
 weeks+4.259
 hrs+4.049
EMBER+4.000
Neg logit contributions
 lifestyles-5.640
 personalities-5.331
 techn-5.197
 behaviour-5.182
 Resistance-5.111
Token interesting
Token ID3499
Feature activation-1.38e-01

Pos logit contributions
 semester+2.361
Feb+2.040
 weeks+1.916
EMBER+1.872
 hrs+1.835
Neg logit contributions
 lifestyles-2.591
 personalities-2.480
 behaviour-2.394
 techn-2.377
 voices-2.368
Token.
Token ID13
Feature activation+3.46e+00

Pos logit contributions
 semester+0.048
Feb+0.034
EMBER+0.026
 weeks+0.026
imeo+0.024
Neg logit contributions
 lifestyles-0.183
 personalities-0.180
 behaviour-0.175
 techn-0.174
 voices-0.174
Token All
Token ID1439
Feature activation-4.13e+00

Pos logit contributions
 lifestyles+2.360
 personalities+2.255
 behaviour+2.135
 voices+2.133
 techn+2.126
Neg logit contributions
 semester-3.414
Feb-3.072
EMBER-2.879
 weeks-2.862
imeo-2.826
Token four
Token ID1440
Feature activation-4.81e+00

Pos logit contributions
 semester+3.535
Feb+3.024
 weeks+2.921
EMBER+2.787
 hrs+2.753
Neg logit contributions
 lifestyles-3.294
 personalities-3.152
 behaviour-3.081
 techn-3.064
 Behavior-2.996
Token people
Token ID661
Feature activation-3.74e+00

Pos logit contributions
 semester+3.430
Feb+2.867
 weeks+2.755
 hrs+2.573
EMBER+2.543
Neg logit contributions
 lifestyles-4.516
 personalities-4.310
 behaviour-4.273
 techn-4.256
 Behavior-4.158
Token I
Token ID314
Feature activation-6.85e+00

Pos logit contributions
 semester+3.237
Feb+2.824
 weeks+2.665
EMBER+2.610
 hrs+2.557
Neg logit contributions
 lifestyles-2.991
 personalities-2.873
 behaviour-2.767
 techn-2.756
 voices-2.699
Token brought
Token ID3181
Feature activation-1.24e+00

Pos logit contributions
 semester+5.186
Feb+4.410
 weeks+4.166
EMBER+4.106
 hrs+3.952
Neg logit contributions
 lifestyles-6.145
 personalities-5.863
 behaviour-5.658
 techn-5.622
 Resistance-5.570
Token this
Token ID428
Feature activation-7.56e+00

Pos logit contributions
 semester+0.972
Feb+0.844
 weeks+0.789
EMBER+0.762
 hrs+0.755
Neg logit contributions
 lifestyles-1.101
 personalities-1.059
 behaviour-1.025
 techn-1.024
 voices-1.006
Token's
Token ID338
Feature activation+3.74e+00

Pos logit contributions
 semester+1.201
Feb+1.018
 weeks+0.917
EMBER+0.901
 hrs+0.880
Neg logit contributions
 lifestyles-1.924
 personalities-1.867
 techn-1.803
 behaviour-1.803
 voices-1.787
Token)
Token ID8
Feature activation+7.03e+00

Pos logit contributions
 lifestyles+3.843
 personalities+3.729
 behaviour+3.603
 voices+3.592
 techn+3.583
Neg logit contributions
 semester-2.400
Feb-2.049
EMBER-1.837
 weeks-1.811
imeo-1.771
Token fantasy
Token ID8842
Feature activation+5.77e+00

Pos logit contributions
 lifestyles+5.188
 personalities+5.023
 opinions+4.779
 behaviour+4.766
 voices+4.760
Neg logit contributions
 semester-6.319
Feb-5.756
EMBER-5.340
imeo-5.274
 weeks-5.230
Token mate
Token ID16133
Feature activation+5.05e-01

Pos logit contributions
 lifestyles+6.592
 personalities+6.372
 voices+6.202
 behaviour+6.196
 techn+6.155
Neg logit contributions
 semester-2.896
Feb-2.489
imeo-2.111
EMBER-2.108
imester-2.006
Token.
Token ID13
Feature activation+4.00e+00

Pos logit contributions
 lifestyles+0.568
 personalities+0.553
 behaviour+0.536
 techn+0.535
 voices+0.534
Neg logit contributions
 semester-0.276
Feb-0.227
EMBER-0.198
 weeks-0.196
imeo-0.190
Token
Token ID198
Feature activation-4.05e+00

Pos logit contributions
 lifestyles+2.595
 personalities+2.471
 behaviour+2.332
 techn+2.331
 voices+2.326
Neg logit contributions
 semester-4.071
Feb-3.676
EMBER-3.451
 weeks-3.441
imeo-3.396
Token
Token ID198
Feature activation-2.22e+00

Pos logit contributions
 semester+3.050
Feb+2.724
 weeks+2.473
EMBER+2.448
 hrs+2.386
Neg logit contributions
 lifestyles-3.709
 personalities-3.594
 techn-3.424
 behaviour-3.397
 voices-3.368
TokenBut
Token ID1537
Feature activation+3.15e+00

Pos logit contributions
 semester+1.636
Feb+1.478
EMBER+1.329
 weeks+1.301
 hrs+1.266
Neg logit contributions
 lifestyles-2.073
 personalities-2.006
 techn-1.927
 behaviour-1.924
 voices-1.915
Token the
Token ID262
Feature activation+4.54e+00

Pos logit contributions
 lifestyles+2.584
 personalities+2.493
 behaviour+2.382
 techn+2.377
 voices+2.373
Neg logit contributions
 semester-2.671
Feb-2.374
EMBER-2.194
 weeks-2.165
imeo-2.146
Token correct
Token ID3376
Feature activation+5.26e+00

Pos logit contributions
 lifestyles+3.394
 personalities+3.260
 behaviour+3.102
 voices+3.092
 techn+3.091
Neg logit contributions
 semester-4.166
Feb-3.755
EMBER-3.504
 weeks-3.441
imeo-3.435
Token one
Token ID530
Feature activation-7.55e+00

Pos logit contributions
 lifestyles+3.634
 personalities+3.488
 behaviour+3.315
 techn+3.299
 voices+3.295
Neg logit contributions
 semester-5.098
Feb-4.642
EMBER-4.349
 weeks-4.276
imeo-4.269
Tokenitude
Token ID3984
Feature activation-8.02e-01

Pos logit contributions
 lifestyles+0.097
 personalities+0.093
 behaviour+0.088
 techn+0.088
 voices+0.088
Neg logit contributions
 semester-0.137
Feb-0.124
EMBER-0.115
 weeks-0.115
imeo-0.113
Token 34
Token ID4974
Feature activation-6.03e+00

Pos logit contributions
 semester+0.645
Feb+0.567
EMBER+0.521
 weeks+0.521
 hrs+0.507
Neg logit contributions
 lifestyles-0.697
 personalities-0.672
 behaviour-0.644
 techn-0.642
 voices-0.642
Token00
Token ID405
Feature activation-3.33e+00

Pos logit contributions
 semester+4.030
Feb+3.517
 weeks+3.213
EMBER+3.159
 hrs+3.142
Neg logit contributions
 lifestyles-5.936
 personalities-5.738
 techn-5.506
 behaviour-5.504
 voices-5.468
Token m
Token ID285
Feature activation-6.79e+00

Pos logit contributions
 semester+2.700
Feb+2.393
 weeks+2.211
EMBER+2.200
 hrs+2.182
Neg logit contributions
 lifestyles-2.845
 personalities-2.743
 techn-2.613
 behaviour-2.604
 voices-2.597
Token;
Token ID26
Feature activation+9.46e-01

Pos logit contributions
 semester+4.816
Feb+4.251
 weeks+3.905
EMBER+3.897
 hrs+3.818
Neg logit contributions
 lifestyles-6.330
 personalities-6.121
 voices-5.792
 techn-5.784
 behaviour-5.783
Token 19
Token ID678
Feature activation-7.25e+00

Pos logit contributions
 lifestyles+0.754
 personalities+0.726
 behaviour+0.694
 techn+0.691
 voices+0.690
Neg logit contributions
 semester-0.827
Feb-0.735
EMBER-0.680
 weeks-0.679
imeo-0.664
Token°
Token ID7200
Feature activation-6.04e+00

Pos logit contributions
 semester+5.677
Feb+5.035
 weeks+4.706
 hrs+4.624
EMBER+4.602
Neg logit contributions
 lifestyles-6.258
 personalities-6.017
 techn-5.744
 behaviour-5.732
 Responsibility-5.680
Token30
Token ID1270
Feature activation-3.14e+00

Pos logit contributions
 semester+4.707
Feb+4.233
EMBER+3.888
 weeks+3.878
 hrs+3.830
Neg logit contributions
 lifestyles-5.227
 personalities-5.032
 techn-4.819
 behaviour-4.767
 voices-4.761
Token N
Token ID399
Feature activation-4.96e+00

Pos logit contributions
 semester+2.276
Feb+1.976
 weeks+1.804
EMBER+1.796
 hrs+1.763
Neg logit contributions
 lifestyles-2.959
 personalities-2.865
 techn-2.747
 behaviour-2.743
 voices-2.734
Token)
Token ID8
Feature activation-2.52e+00

Pos logit contributions
 semester+3.171
Feb+2.729
EMBER+2.458
 weeks+2.441
 hrs+2.381
Neg logit contributions
 lifestyles-5.061
 personalities-4.913
 voices-4.694
 techn-4.694
 behaviour-4.689
Token
Token ID198
Feature activation-5.90e+00

Pos logit contributions
 semester+2.141
Feb+1.907
 weeks+1.770
EMBER+1.759
 hrs+1.722
Neg logit contributions
 lifestyles-2.050
 personalities-1.975
 techn-1.873
 voices-1.870
 behaviour-1.869
Token,
Token ID11
Feature activation+4.15e+00

Pos logit contributions
 lifestyles+1.397
 personalities+1.365
 behaviour+1.325
 voices+1.319
 techn+1.317
Neg logit contributions
 semester-0.613
Feb-0.503
EMBER-0.433
imeo-0.419
 weeks-0.411
Token honestly
Token ID12698
Feature activation-4.66e+00

Pos logit contributions
 lifestyles+3.238
 personalities+3.119
 behaviour+2.977
 techn+2.972
 voices+2.959
Neg logit contributions
 semester-3.679
Feb-3.283
EMBER-3.049
 weeks-3.019
imeo-2.984
Token.
Token ID13
Feature activation+3.46e+00

Pos logit contributions
 semester+2.357
Feb+1.876
 weeks+1.678
EMBER+1.621
 hrs+1.536
Neg logit contributions
 lifestyles-5.367
 personalities-5.214
 techn-5.043
 behaviour-5.043
 voices-5.030
Token We
Token ID775
Feature activation-2.72e+00

Pos logit contributions
 lifestyles+2.215
 personalities+2.111
 behaviour+1.995
 techn+1.989
 voices+1.983
Neg logit contributions
 semester-3.564
Feb-3.222
EMBER-3.023
 weeks-3.014
imeo-2.973
Token did
Token ID750
Feature activation-5.45e+00

Pos logit contributions
 semester+2.048
Feb+1.775
 weeks+1.637
EMBER+1.613
 hrs+1.579
Neg logit contributions
 lifestyles-2.508
 personalities-2.415
 behaviour-2.320
 techn-2.309
 voices-2.307
Token many
Token ID867
Feature activation-7.30e+00

Pos logit contributions
 semester+4.633
Feb+4.087
 weeks+3.913
EMBER+3.782
 hrs+3.733
Neg logit contributions
 lifestyles-4.370
 personalities-4.158
 behaviour-3.957
 voices-3.949
 techn-3.946
Token things
Token ID1243
Feature activation-7.45e+00

Pos logit contributions
 semester+7.178
 weeks+6.329
Feb+6.321
 hrs+5.967
.+5.882
Neg logit contributions
 lifestyles-4.644
 personalities-4.364
 Responsibility-4.184
 masculinity-4.178
 Flavoring-4.141
Token right
Token ID826
Feature activation-9.04e+00

Pos logit contributions
 semester+5.699
Feb+4.871
 weeks+4.737
.+4.485
EMBER+4.438
Neg logit contributions
 lifestyles-6.460
 personalities-6.199
 Flavoring-5.995
 voices-5.939
 Responsibility-5.926
Token.
Token ID13
Feature activation+3.94e+00

Pos logit contributions
 semester+6.856
Feb+5.756
 weeks+5.669
.+5.449
EMBER+5.220
Neg logit contributions
 lifestyles-7.845
 personalities-7.566
 Responsibility-7.223
 Resistance-7.200
 techn-7.198
Token But
Token ID887
Feature activation+6.94e-01

Pos logit contributions
 lifestyles+2.495
 personalities+2.379
 behaviour+2.246
 techn+2.240
 voices+2.233
Neg logit contributions
 semester-4.077
Feb-3.685
EMBER-3.461
 weeks-3.447
imeo-3.407
Token that
Token ID326
Feature activation-2.00e+00

Pos logit contributions
 lifestyles+0.560
 personalities+0.538
 behaviour+0.514
 techn+0.513
 voices+0.512
Neg logit contributions
 semester-0.600
Feb-0.532
 weeks-0.494
EMBER-0.492
 hrs-0.480
TokenLa
Token ID14772
Feature activation+6.67e-01

Pos logit contributions
 semester+1.987
Feb+1.773
EMBER+1.582
 weeks+1.565
 hrs+1.520
Neg logit contributions
 lifestyles-2.630
 personalities-2.537
 techn-2.446
 behaviour-2.439
 voices-2.422
TokenFeb
Token ID15146
Feature activation-1.12e-01

Pos logit contributions
 lifestyles+1.020
 personalities+1.000
 behaviour+0.977
 techn+0.976
 voices+0.975
Neg logit contributions
 semester-0.093
Feb-0.020
EMBER+0.009
 weeks+0.011
 hrs+0.021
Tokenre
Token ID260
Feature activation+2.49e+00

Pos logit contributions
 semester+0.099
Feb+0.088
EMBER+0.082
 weeks+0.082
imeo+0.080
Neg logit contributions
 lifestyles-0.087
 personalities-0.084
 behaviour-0.080
 techn-0.080
 voices-0.080
Token says
Token ID1139
Feature activation+1.93e+00

Pos logit contributions
 lifestyles+1.956
 personalities+1.884
 voices+1.799
 behaviour+1.796
 techn+1.790
Neg logit contributions
 semester-2.197
Feb-1.966
EMBER-1.830
 weeks-1.806
imeo-1.790
Token five
Token ID1936
Feature activation-5.68e+00

Pos logit contributions
 lifestyles+1.637
 personalities+1.581
 behaviour+1.515
 techn+1.510
 voices+1.508
Neg logit contributions
 semester-1.589
Feb-1.403
EMBER-1.292
 weeks-1.286
imeo-1.259
Token months
Token ID1933
Feature activation-1.18e+01

Pos logit contributions
 semester+5.467
Feb+4.809
 weeks+4.722
 hrs+4.470
EMBER+4.461
Neg logit contributions
 lifestyles-3.959
 personalities-3.705
 techn-3.595
 behaviour-3.552
 Responsibility-3.491
Token after
Token ID706
Feature activation-4.88e+00

Pos logit contributions
 semester+6.924
Feb+5.562
 weeks+5.533
.+4.989
 hrs+4.940
Neg logit contributions
 lifestyles-11.821
 personalities-11.356
 techn-10.998
 Responsibility-10.815
 behaviour-10.783
Token Price
Token ID7886
Feature activation-3.00e+00

Pos logit contributions
 semester+4.689
Feb+4.188
 weeks+3.994
EMBER+3.867
 hrs+3.842
Neg logit contributions
 lifestyles-3.446
 personalities-3.231
 behaviour-3.067
 techn-3.050
 voices-3.001
Token
Token ID447
Feature activation-5.99e+00

Pos logit contributions
 semester+2.070
Feb+1.785
 weeks+1.615
EMBER+1.585
 hrs+1.536
Neg logit contributions
 lifestyles-2.940
 personalities-2.819
 behaviour-2.720
 techn-2.711
 voices-2.691
Token
Token ID247
Feature activation+1.05e+01

Pos logit contributions
 semester+4.427
Feb+3.904
EMBER+3.521
 weeks+3.498
 hrs+3.403
Neg logit contributions
 lifestyles-5.500
 personalities-5.255
 behaviour-5.132
 techn-5.071
 voices-5.010
Tokens
Token ID82
Feature activation+6.54e-01

Pos logit contributions
 lifestyles+5.924
 personalities+5.805
 voices+5.559
 behaviour+5.498
 techn+5.347
Neg logit contributions
 semester-10.493
Feb-9.352
EMBER-9.094
imeo-8.887
 weeks-8.814
Token which
Token ID543
Feature activation-4.09e+00

Pos logit contributions
 lifestyles+1.616
 personalities+1.554
 behaviour+1.485
 techn+1.480
 voices+1.477
Neg logit contributions
 semester-1.770
Feb-1.572
 weeks-1.458
EMBER-1.452
 hrs-1.418
Token begins
Token ID6140
Feature activation-7.32e+00

Pos logit contributions
 semester+3.357
Feb+2.930
 weeks+2.750
EMBER+2.636
 hrs+2.616
Neg logit contributions
 lifestyles-3.464
 personalities-3.330
 behaviour-3.214
 techn-3.175
 voices-3.169
Token in
Token ID287
Feature activation-8.24e+00

Pos logit contributions
 semester+4.998
Feb+4.366
 weeks+4.089
EMBER+3.790
 hrs+3.680
Neg logit contributions
 lifestyles-7.052
 personalities-6.820
 behaviour-6.556
 Responsibility-6.510
 techn-6.483
Token the
Token ID262
Feature activation-6.82e+00

Pos logit contributions
 semester+6.830
Feb+5.968
 weeks+5.848
EMBER+5.355
 hrs+5.310
Neg logit contributions
 lifestyles-6.664
 personalities-6.423
 behaviour-6.101
 Flavoring-6.072
 voices-6.002
Token final
Token ID2457
Feature activation-1.46e+01

Pos logit contributions
 semester+5.290
Feb+4.408
 weeks+4.391
EMBER+4.017
 afternoon+4.011
Neg logit contributions
 lifestyles-6.026
 personalities-5.805
 behaviour-5.593
 techn-5.504
 voices-5.499
Token week
Token ID1285
Feature activation-2.08e+01

Pos logit contributions
 semester+10.583
 weeks+9.257
Feb+8.204
 months+7.876
 hrs+7.758
Neg logit contributions
 lifestyles-12.529
 personalities-12.088
 Responsibility-11.837
 Controls-11.675
 Flavoring-11.629
Token of
Token ID286
Feature activation-9.32e+00

Pos logit contributions
 semester+14.338
 weeks+12.528
Feb+12.501
.+12.459
 apiece+11.378
Neg logit contributions
 lifestyles-15.860
 personalities-15.281
 Responsibility-14.651
 Behavior-14.452
 techn-14.426
Token July
Token ID2901
Feature activation-1.75e+01

Pos logit contributions
 semester+7.604
Feb+6.523
 weeks+6.309
EMBER+5.748
 hrs+5.627
Neg logit contributions
 lifestyles-7.572
 personalities-7.355
 Responsibility-6.949
 voices-6.939
 behaviour-6.910
Token.
Token ID13
Feature activation+2.09e+00

Pos logit contributions
 semester+12.212
.+10.437
Feb+10.369
 weeks+10.039
EMBER+9.453
Neg logit contributions
 lifestyles-14.259
 personalities-14.008
 Responsibility-13.348
 techn-13.217
 behaviour-13.087
Token
Token ID198
Feature activation-4.15e+00

Pos logit contributions
 lifestyles+1.591
 personalities+1.528
 behaviour+1.456
 techn+1.451
 voices+1.447
Neg logit contributions
 semester-1.905
Feb-1.702
EMBER-1.581
 weeks-1.579
 hrs-1.545
Token
Token ID198
Feature activation-1.84e+00

Pos logit contributions
 semester+3.082
Feb+2.750
 weeks+2.501
EMBER+2.453
 hrs+2.401
Neg logit contributions
 lifestyles-3.852
 personalities-3.730
 techn-3.559
 behaviour-3.523
 voices-3.484
Token list
Token ID1351
Feature activation-3.19e+00

Pos logit contributions
 lifestyles+2.002
 personalities+1.921
 behaviour+1.828
 techn+1.822
 voices+1.818
Neg logit contributions
 semester-2.504
Feb-2.242
EMBER-2.086
 weeks-2.083
imeo-2.040
Token management
Token ID4542
Feature activation+3.93e+00

Pos logit contributions
 semester+3.202
Feb+2.875
 weeks+2.725
EMBER+2.684
 hrs+2.635
Neg logit contributions
 lifestyles-2.096
 personalities-1.984
 behaviour-1.857
 voices-1.837
 masculinity-1.831
Token system
Token ID1080
Feature activation-1.91e+00

Pos logit contributions
 lifestyles+3.228
 personalities+3.121
 techn+3.012
 behaviour+3.000
 voices+2.982
Neg logit contributions
 semester-3.292
Feb-2.929
EMBER-2.716
 weeks-2.675
imeo-2.663
Token (
Token ID357
Feature activation-4.94e+00

Pos logit contributions
 semester+1.528
Feb+1.342
 weeks+1.237
EMBER+1.229
 hrs+1.193
Neg logit contributions
 lifestyles-1.663
 personalities-1.598
 behaviour-1.527
 voices-1.517
 techn-1.512
TokenMay
Token ID6747
Feature activation-1.49e+01

Pos logit contributions
 semester+2.792
Feb+2.512
EMBER+2.143
 weeks+2.038
imeo+1.972
Neg logit contributions
 lifestyles-5.437
 personalities-5.259
 techn-5.077
 behaviour-5.055
 voices-5.046
Token 2013
Token ID2211
Feature activation-1.63e+01

Pos logit contributions
 semester+9.667
Feb+8.143
EMBER+7.502
 weeks+7.497
.+7.417
Neg logit contributions
 lifestyles-12.980
 personalities-12.720
 Flavoring-11.864
 voices-11.794
 nationalism-11.733
Token),
Token ID828
Feature activation+3.91e+00

Pos logit contributions
 semester+9.544
Feb+7.778
 weeks+7.201
.+7.190
 hrs+6.787
Neg logit contributions
 lifestyles-15.376
 personalities-14.769
 techn-13.928
 masculinity-13.887
 personality-13.751
Token S
Token ID311
Feature activation-1.51e+00

Pos logit contributions
 lifestyles+2.368
 personalities+2.252
 behaviour+2.121
 techn+2.120
 voices+2.107
Neg logit contributions
 semester-4.153
Feb-3.780
EMBER-3.561
 weeks-3.543
imeo-3.489
Tokenout
Token ID448
Feature activation-5.55e-01

Pos logit contributions
 semester+1.231
Feb+1.094
EMBER+1.011
 weeks+0.997
imeo+0.989
Neg logit contributions
 lifestyles-1.290
 personalities-1.244
 behaviour-1.191
 voices-1.183
 techn-1.179
Tokenron
Token ID1313
Feature activation+1.88e+00

Pos logit contributions
 semester+0.418
Feb+0.369
 weeks+0.334
EMBER+0.333
imeo+0.325
Neg logit contributions
 lifestyles-0.507
 personalities-0.489
 behaviour-0.469
 techn-0.467
 voices-0.466
Token Global
Token ID8060
Feature activation+3.87e+00

Pos logit contributions
 lifestyles+1.385
 personalities+1.329
 behaviour+1.265
 techn+1.262
 voices+1.257
Neg logit contributions
 semester-1.757
Feb-1.574
EMBER-1.466
 weeks-1.463
imeo-1.434
Token cases
Token ID2663
Feature activation-4.33e+00

Pos logit contributions
 semester+5.510
Feb+4.972
 weeks+4.774
EMBER+4.639
 hrs+4.612
Neg logit contributions
 lifestyles-2.941
 personalities-2.766
 behaviour-2.658
 techn-2.584
 voices-2.570
Token of
Token ID286
Feature activation+2.90e+00

Pos logit contributions
 semester+2.416
Feb+1.975
 weeks+1.778
EMBER+1.699
 apiece+1.661
Neg logit contributions
 lifestyles-4.838
 personalities-4.669
 behaviour-4.526
 voices-4.502
 techn-4.501
Token firearm
Token ID13988
Feature activation+4.51e+00

Pos logit contributions
 lifestyles+1.743
 personalities+1.656
 behaviour+1.556
 techn+1.550
 voices+1.545
Neg logit contributions
 semester-3.109
Feb-2.828
EMBER-2.661
 weeks-2.656
imeo-2.612
Token shootings
Token ID17690
Feature activation-6.43e-02

Pos logit contributions
 lifestyles+3.642
 personalities+3.531
 behaviour+3.383
 techn+3.364
 voices+3.347
Neg logit contributions
 semester-3.839
Feb-3.428
EMBER-3.178
imeo-3.148
 weeks-3.122
Token in
Token ID287
Feature activation-2.50e+00

Pos logit contributions
 semester+0.048
Feb+0.041
EMBER+0.038
 weeks+0.037
imeo+0.037
Neg logit contributions
 lifestyles-0.060
 personalities-0.058
 behaviour-0.056
 techn-0.056
 voices-0.056
Token 2010
Token ID3050
Feature activation-1.69e+01

Pos logit contributions
 semester+1.954
Feb+1.692
 weeks+1.586
EMBER+1.526
 hrs+1.483
Neg logit contributions
 lifestyles-2.220
 personalities-2.151
 voices-2.052
 behaviour-2.045
 techn-2.040
Token,
Token ID11
Feature activation-2.53e+00

Pos logit contributions
 semester+12.059
.+10.074
Feb+9.963
 weeks+9.653
 apiece+9.353
Neg logit contributions
 lifestyles-13.629
 personalities-13.077
 Responsibility-12.641
 techn-12.593
 voices-12.585
Token according
Token ID1864
Feature activation-6.17e+00

Pos logit contributions
 semester+2.096
Feb+1.829
 weeks+1.736
EMBER+1.667
 hrs+1.626
Neg logit contributions
 lifestyles-2.110
 personalities-2.038
 behaviour-1.939
 voices-1.928
 techn-1.924
Token to
Token ID284
Feature activation-1.76e+00

Pos logit contributions
 semester+3.614
Feb+3.079
 weeks+2.780
EMBER+2.650
 hrs+2.563
Neg logit contributions
 lifestyles-6.555
 personalities-6.378
 techn-6.145
 behaviour-6.082
 voices-6.015
Token the
Token ID262
Feature activation-1.73e+00

Pos logit contributions
 semester+1.895
Feb+1.714
 weeks+1.641
EMBER+1.595
 hrs+1.582
Neg logit contributions
 lifestyles-1.027
 personalities-0.979
 behaviour-0.908
 voices-0.902
 techn-0.891
Token most
Token ID749
Feature activation-8.82e+00

Pos logit contributions
 semester+1.910
Feb+1.724
 weeks+1.650
EMBER+1.613
 hrs+1.589
Neg logit contributions
 lifestyles-0.971
 personalities-0.932
 behaviour-0.866
 voices-0.863
 techn-0.853
Token were
Token ID547
Feature activation-1.18e+00

Pos logit contributions
 lifestyles+5.773
 personalities+5.566
 behaviour+5.411
 techn+5.406
 voices+5.400
Neg logit contributions
 semester-5.021
Feb-4.471
imeo-4.135
EMBER-4.119
 hrs-4.011
Token introduced
Token ID5495
Feature activation-1.00e+00

Pos logit contributions
 semester+0.972
Feb+0.851
 weeks+0.789
EMBER+0.778
imeo+0.760
Neg logit contributions
 lifestyles-1.013
 personalities-0.976
 behaviour-0.935
 techn-0.927
 voices-0.926
Token in
Token ID287
Feature activation-3.60e+00

Pos logit contributions
 semester+0.753
Feb+0.656
EMBER+0.600
 weeks+0.593
imeo+0.585
Neg logit contributions
 lifestyles-0.925
 personalities-0.895
 behaviour-0.860
 techn-0.860
 voices-0.859
Token Milwaukee
Token ID16629
Feature activation-7.37e+00

Pos logit contributions
 semester+2.873
Feb+2.496
 weeks+2.343
EMBER+2.271
 hrs+2.196
Neg logit contributions
 lifestyles-3.121
 personalities-3.025
 behaviour-2.883
 voices-2.861
 techn-2.857
Token in
Token ID287
Feature activation-7.47e+00

Pos logit contributions
 semester+5.692
Feb+4.971
 weeks+4.718
EMBER+4.469
.+4.412
Neg logit contributions
 lifestyles-6.365
 personalities-6.165
 behaviour-5.902
 techn-5.863
 Responsibility-5.802
Token 1990
Token ID6303
Feature activation-1.87e+01

Pos logit contributions
 semester+5.576
Feb+4.731
 weeks+4.511
EMBER+4.253
 hrs+4.089
Neg logit contributions
 lifestyles-6.681
 personalities-6.493
 behaviour-6.165
 voices-6.121
 techn-6.108
Token.
Token ID13
Feature activation+1.62e+00

Pos logit contributions
 semester+13.415
.+11.932
Feb+11.408
 weeks+11.006
 apiece+10.430
Neg logit contributions
 lifestyles-14.286
 personalities-13.607
 behaviour-13.355
 Behavior-13.135
 masculinity-13.081
Token
Token ID198
Feature activation-6.07e+00

Pos logit contributions
 lifestyles+1.288
 personalities+1.240
 behaviour+1.184
 techn+1.177
 voices+1.174
Neg logit contributions
 semester-1.425
Feb-1.271
EMBER-1.175
 weeks-1.174
 hrs-1.148
Token
Token ID198
Feature activation-3.80e+00

Pos logit contributions
 semester+4.251
Feb+3.861
 weeks+3.462
EMBER+3.388
.+3.315
Neg logit contributions
 lifestyles-5.819
 personalities-5.638
 techn-5.371
 behaviour-5.300
 opinions-5.243
Token"
Token ID1
Feature activation+1.04e+00

Pos logit contributions
 semester+2.733
Feb+2.482
EMBER+2.206
 weeks+2.148
imeo+2.110
Neg logit contributions
 lifestyles-3.613
 personalities-3.488
 behaviour-3.356
 techn-3.343
 voices-3.321
TokenFund
Token ID24553
Feature activation+1.01e+01

Pos logit contributions
 lifestyles+0.968
 personalities+0.936
 behaviour+0.901
 techn+0.898
 voices+0.897
Neg logit contributions
 semester-0.764
Feb-0.660
EMBER-0.602
 weeks-0.601
imeo-0.586
Token ranking
Token ID12759
Feature activation-3.82e+00

Pos logit contributions
 semester+7.464
Feb+6.395
 weeks+6.176
 apiece+6.129
EMBER+6.075
Neg logit contributions
 lifestyles-6.231
 personalities-5.961
 behaviour-5.683
 techn-5.625
 voices-5.597
Token within
Token ID1626
Feature activation-3.59e+00

Pos logit contributions
 semester+2.736
Feb+2.320
 weeks+2.160
EMBER+2.108
 apiece+2.049
Neg logit contributions
 lifestyles-3.653
 personalities-3.534
 behaviour-3.394
 techn-3.389
 voices-3.367
Token the
Token ID262
Feature activation-2.39e+00

Pos logit contributions
 semester+3.674
Feb+3.244
 weeks+3.193
EMBER+3.062
 hrs+3.018
Neg logit contributions
 lifestyles-2.324
 personalities-2.207
 behaviour-2.108
 techn-2.078
 voices-2.051
Token last
Token ID938
Feature activation-1.75e+01

Pos logit contributions
 semester+2.102
Feb+1.819
 weeks+1.744
EMBER+1.697
 hrs+1.647
Neg logit contributions
 lifestyles-1.912
 personalities-1.831
 behaviour-1.754
 techn-1.740
 voices-1.723
Token 12
Token ID1105
Feature activation-1.77e+01

Pos logit contributions
 semester+12.257
 weeks+9.900
 months+8.842
Feb+8.827
.+8.444
Neg logit contributions
 lifestyles-14.731
 personalities-14.151
 Responsibility-13.785
 voices-13.660
 Flavoring-13.615
Token months
Token ID1933
Feature activation-2.23e+01

Pos logit contributions
 semester+12.836
 weeks+11.559
 months+10.757
Feb+10.311
 hrs+10.005
Neg logit contributions
 lifestyles-13.906
 personalities-13.245
 Responsibility-13.031
 techn-12.935
 Controls-12.809
Token),
Token ID828
Feature activation+5.89e+00

Pos logit contributions
 semester+14.076
 weeks+11.985
.+11.877
 apiece+11.849
Feb+11.405
Neg logit contributions
 lifestyles-16.314
 personalities-15.872
 Responsibility-15.337
 Behavior-15.245
 Policies-15.165
Token a
Token ID257
Feature activation+2.52e+00

Pos logit contributions
 lifestyles+4.604
 personalities+4.430
 voices+4.226
 techn+4.222
 behaviour+4.215
Neg logit contributions
 semester-5.162
Feb-4.631
EMBER-4.316
 weeks-4.228
imeo-4.224
Token 3
Token ID513
Feature activation-5.86e+00

Pos logit contributions
 lifestyles+1.977
 personalities+1.902
 behaviour+1.815
 techn+1.813
 voices+1.807
Neg logit contributions
 semester-2.219
Feb-1.984
EMBER-1.842
 weeks-1.828
imeo-1.801
Token-
Token ID12
Feature activation+2.75e-01

Pos logit contributions
 semester+3.461
Feb+2.863
 weeks+2.565
EMBER+2.504
 hrs+2.425
Neg logit contributions
 lifestyles-6.331
 personalities-6.133
 behaviour-5.959
 voices-5.920
 techn-5.917
Token0
Token ID15
Feature activation-1.05e+00

Pos logit contributions
 lifestyles+0.271
 personalities+0.262
 behaviour+0.253
 techn+0.252
 voices+0.252
Neg logit contributions
 semester-0.190
Feb-0.163
EMBER-0.147
 weeks-0.147
imeo-0.142