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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ocally
    -0.87
    çİĭ
    -0.71
    imb
    -0.70
     Kitt
    -0.70
    actic
    -0.69
    WT
    -0.68
    BF
    -0.66
    MJ
    -0.65
    ĸļ
    -0.65
     Offer
    -0.64
    POSITIVE LOGITS
    rig
    0.73
    alon
    0.69
    ritz
    0.69
    riad
    0.68
    serv
    0.65
    igator
    0.63
    pan
    0.63
     warnings
    0.62
     Razor
    0.61
    eers
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.