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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ouf
    -0.75
    amen
    -0.73
    berman
    -0.71
    =-
    -0.68
     dummy
    -0.67
    llo
    -0.64
    ãģŁ
    -0.64
    iao
    -0.63
    ws
    -0.63
    talking
    -0.63
    POSITIVE LOGITS
    owship
    0.78
    renheit
    0.78
    mbuds
    0.71
     Leth
    0.71
     legends
    0.69
     Nightmares
    0.66
    lishes
    0.66
    vir
    0.65
     myths
    0.63
    renches
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.