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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    certain proper nouns and specific identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reilly
    -0.70
     pestic
    -0.67
     confidentiality
    -0.67
    issance
    -0.66
    SourceFile
    -0.66
     parachute
    -0.65
     Scully
    -0.65
    Downloadha
    -0.64
     duct
    -0.63
     ours
    -0.63
    POSITIVE LOGITS
    culosis
    0.85
    awk
    0.83
    henko
    0.80
    gur
    0.78
    allery
    0.77
    vic
    0.76
    oshi
    0.75
    chuk
    0.75
    orrow
    0.75
    agi
    0.74
    Act Density 0.226%

    No Known Activations