INDEX
Explanations
mentions of universities, particularly highlighting the name "Cornell."
mentions of specific universities and individuals associated with them
New Auto-Interp
Negative Logits
roxy
-0.82
Ĥ¬
-0.77
sighted
-0.75
venants
-0.73
eport
-0.72
ened
-0.69
eer
-0.69
eln
-0.67
erer
-0.66
ening
-0.65
POSITIVE LOGITS
izabeth
0.84
vier
0.80
mson
0.79
Tire
0.79
itational
0.74
ANCE
0.73
ursion
0.71
vic
0.69
ãģĦ
0.69
Dame
0.68
Activations Density 0.036%