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

    Neuronpedia

    INDEX
    Explanations

    references to proprietary information or copyrighted material

    oai_token-act-pair · gpt-3.5-turbo

    terms related to proprietary and copyrighted content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPA
    -0.88
    othy
    -0.79
    immer
    -0.76
    SEE
    -0.75
    asin
    -0.73
    alys
    -0.70
    annis
    -0.70
    apers
    -0.69
    ulhu
    -0.69
    ttp
    -0.69
    POSITIVE LOGITS
     proprietary
    1.00
     secrets
    0.88
     interests
    0.83
     materials
    0.83
    ĨĴ
    0.81
     formulas
    0.81
     jargon
    0.77
     identities
    0.75
     positioning
    0.75
    ignty
    0.75
    Act Density 0.009%

    No Known Activations