INDEX
Explanations
proper names, specifically individuals named "Steve"
mentions of the name "Steve."
New Auto-Interp
Negative Logits
teen
-0.74
ktop
-0.74
bound
-0.73
exempt
-0.73
sovere
-0.70
Spoiler
-0.69
appropriately
-0.69
unres
-0.67
runtime
-0.66
interrupted
-0.66
POSITIVE LOGITS
Bannon
1.00
Irwin
0.98
Jobs
0.95
Ange
0.91
McInt
0.90
Rogers
0.89
otle
0.85
Trevor
0.85
Schmidt
0.84
Martin
0.83
Activations Density 0.011%