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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    eeper
    -0.67
    kered
    -0.67
    wcsstore
    -0.66
    ayette
    -0.64
    ertodd
    -0.63
    rower
    -0.62
    «ĺ
    -0.62
    emale
    -0.62
    INTON
    -0.62
    ccording
    -0.62
    POSITIVE LOGITS
     Arena
    0.70
    fit
    0.67
     vac
    0.64
    fits
    0.61
    eval
    0.60
     ignorant
    0.59
     idle
    0.58
    Aren
    0.58
     Zig
    0.57
    nor
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.