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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ochet
    -0.76
     brakes
    -0.66
    UGE
    -0.63
     ton
    -0.63
    ENG
    -0.62
    ULAR
    -0.62
     canv
    -0.62
    abouts
    -0.62
     quizz
    -0.61
     whipping
    -0.60
    POSITIVE LOGITS
    td
    0.72
    ipedia
    0.72
    chio
    0.71
    uthor
    0.69
     Dino
    0.69
     Afgh
    0.68
    ccording
    0.65
     Default
    0.63
     Ares
    0.63
    merce
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.