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

    Neuronpedia

    INDEX
    Explanations

    identifiers, index values, or codes that categorize or label data entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %"),
    -0.93
    )");
    -0.88
    ')):
    -0.88
    >";
    -0.87
    )):
    -0.86
    "):
    -0.85
    ?}",
    -0.85
    )';
    -0.85
    %");
    -0.83
    '))
    -0.83
    POSITIVE LOGITS
    .
    0.94
    _
    0.71
    _.
    0.63
     Anſ
    0.56
     ſeveral
    0.55
     Chriſt
    0.55
    *.
    0.55
     Monfieur
    0.54
     Diſ
    0.54
     Theſe
    0.54
    Act Density 0.406%

    No Known Activations