INDEX
Explanations
phrases related to Johns Hopkins University
repeated mentions of the name "Johns."
New Auto-Interp
Negative Logits
mble
-0.90
BOOK
-0.75
Examples
-0.67
deleting
-0.66
deletion
-0.66
eq
-0.66
REP
-0.65
Spread
-0.64
gered
-0.63
atchewan
-0.62
POSITIVE LOGITS
Hopkins
1.23
Johns
1.04
kins
1.00
sonian
0.88
istry
0.84
ston
0.83
ons
0.83
stone
0.79
acre
0.79
son
0.79
Activations Density 0.006%