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

    Neuronpedia

    INDEX
    Explanations

    references to typical characteristics or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hands
    -0.75
     Injectable
    -0.74
     JsonObject
    -0.73
     plais
    -0.73
     Sundance
    -0.70
    ра
    -0.69
    人
    -0.68
     šķ
    -0.68
     Sura
    -0.66
     juos
    -0.66
    POSITIVE LOGITS
    typical
    1.02
     ujednoznacz
    0.89
    %");
    0.88
    )');
    0.86
    ')):
    0.85
     typique
    0.82
    %</
    0.81
     =",
    0.79
     typ
    0.77
    "]);
    0.76
    Act Density 0.133%

    No Known Activations