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

    Neuronpedia

    INDEX
    Explanations

    references to secretive concepts, entities, or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     становника
    -0.96
    PyExc
    -0.77
    MigrationBuilder
    -0.73
    +"/"+
    -0.68
    addPreferredGap
    -0.68
    wapV
    -0.67
    migiano
    -0.66
    timbangkan
    -0.65
    Fuckin
    -0.65
    contributor
    -0.64
    POSITIVE LOGITS
     Secret
    1.80
     secret
    1.78
     secrets
    1.77
    Secret
    1.75
     Secrets
    1.71
     SECRET
    1.69
    secret
    1.67
    Secrets
    1.52
    secrets
    1.43
    SECRET
    1.36
    Act Density 0.084%

    No Known Activations