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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    \/\/
    -0.72
    Pierre
    -0.68
    oire
    -0.68
     []
    -0.68
    []
    -0.67
    letter
    -0.66
     Fernand
    -0.66
    Origin
    -0.63
    Chat
    -0.63
     Stam
    -0.62
    POSITIVE LOGITS
    ancial
    0.76
    iasco
    0.74
    */(
    0.68
    ¥ŀ
    0.67
    ancock
    0.67
     tablet
    0.66
    ruck
    0.65
     traged
    0.65
    agements
    0.64
     consec
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.