Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .
    1.59
    ↵
    1.31
    top
    1.15
    1
    1.10
    ta
    1.08
     (
    1.05
    ts
    1.03
    1.02
    2
    1.01
    t
    0.97
    POSITIVE LOGITS
     ayatan
    2.08
    kprop
    2.05
     pptn
    1.99
     vehement
    1.98
    EnglishMarks
    1.97
     anisot
    1.96
     Quels
    1.95
    쾺
    1.95
    Hitpoint
    1.94
     vitth
    1.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.