INDEX
Explanations
references to specific electronic devices or technology
specific names, terms, and references related to popular gaming devices and political figures
New Auto-Interp
Negative Logits
sburg
-0.91
tes
-0.88
inguished
-0.74
tan
-0.72
teen
-0.69
ãĤ¨ãĥ«
-0.69
´
-0.69
een
-0.68
ley
-0.66
ffee
-0.66
POSITIVE LOGITS
itism
0.82
ites
0.81
iting
0.78
itent
0.77
emonic
0.77
ickr
0.73
agine
0.72
hao
0.71
ALD
0.70
Du
0.67
Activations Density 0.050%