INDEX
Explanations
references to a specific person named Stan
the name "Stan" in various contexts
New Auto-Interp
Negative Logits
edIn
-0.70
minors
-0.68
sensitive
-0.67
classified
-0.66
gearing
-0.65
preferential
-0.63
heightened
-0.62
underage
-0.62
Gemini
-0.61
anwhile
-0.61
POSITIVE LOGITS
isl
1.07
brook
0.93
isle
0.92
izo
0.92
geon
0.91
ning
0.87
lins
0.84
Stan
0.83
oya
0.83
ford
0.83
Activations Density 0.017%