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

    Neuronpedia

    INDEX
    Explanations

    consistent references to specific identifiers or annotations within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ](#
    -1.18
     Tamp
    -0.76
    Emile
    -0.70
    mä
    -0.68
     шпа
    -0.66
     Bep
    -0.66
     Puoi
    -0.65
     equinox
    -0.65
     Pasquale
    -0.65
     TPE
    -0.65
    POSITIVE LOGITS
    aarrggbb
    0.75
     onOptions
    0.66
    awaiter
    0.66
    UnsafeEnabled
    0.65
    InputElement
    0.64
     belegt
    0.64
     ";
    0.63
    XmlAccessorType
    0.61
     ';
    0.61
    Kaynakça
    0.60
    Act Density 0.002%

    No Known Activations