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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or references in the document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Pro
    -0.62
    Pro
    -0.58
     pro
    -0.57
    osy
    -0.50
     z
    -0.49
     PRO
    -0.49
     доку
    -0.47
    {
    -0.47
     De
    -0.47
     -
    -0.46
    POSITIVE LOGITS
    rungsseite
    1.07
     referenties
    0.93
     ProtoMessage
    0.91
    antaranya
    0.89
    parsedMessage
    0.89
    rrggbb
    0.85
     pinulongan
    0.81
     Efq
    0.80
     Monfieur
    0.80
     Theſe
    0.78
    Act Density 0.001%

    No Known Activations