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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Pwr
    -0.77
     Moving
    -0.66
    Moving
    -0.66
    immune
    -0.65
    uf
    -0.65
    Russ
    -0.64
    ROR
    -0.63
    agher
    -0.63
    behind
    -0.63
    Balt
    -0.62
    POSITIVE LOGITS
    ties
    0.83
    izations
    0.73
    orate
    0.71
    ournal
    0.68
    merce
    0.67
    oshenko
    0.66
    tin
    0.66
    atem
    0.65
    chwitz
    0.64
    berra
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.