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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erald
    -0.76
    bent
    -0.73
    ety
    -0.71
    phrine
    -0.71
    orically
    -0.64
     challeng
    -0.61
    awk
    -0.60
    Eye
    -0.59
    ird
    -0.58
    trace
    -0.58
    POSITIVE LOGITS
    ILLE
    0.81
     PRESS
    0.69
    usha
    0.69
     KR
    0.65
    atives
    0.65
    velt
    0.62
    ilater
    0.62
    nesday
    0.62
     Azerb
    0.61
    aos
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.