INDEX
Explanations
mentions of the institution Stanford University
mentions of "Stanford" in various contexts
New Auto-Interp
Negative Logits
alez
-0.85
usting
-0.72
livest
-0.71
hops
-0.71
substant
-0.70
informative
-0.68
usher
-0.68
ocre
-0.65
ombo
-0.64
odic
-0.63
POSITIVE LOGITS
University
0.94
Institution
0.94
Cardinal
0.85
Hills
0.81
Encyclopedia
0.78
Libraries
0.78
Laboratories
0.77
Prison
0.77
Alto
0.75
Swim
0.74
Activations Density 0.011%