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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ifter
    -0.85
    eele
    -0.84
    ÅĤ
    -0.83
    vous
    -0.83
    tu
    -0.80
    abwe
    -0.76
    onne
    -0.76
    ever
    -0.72
    ipel
    -0.69
    ocker
    -0.69
    POSITIVE LOGITS
     John
    0.95
    John
    0.77
     suit
    0.70
     Hancock
    0.69
     suits
    0.68
    ":[{"
    0.65
     Reeves
    0.65
     Nost
    0.64
     Apostles
    0.63
     Marvin
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.