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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific trademarks or brands related to "Instinct."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal designations or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     published
    -0.67
     Timber
    -0.66
     Wat
    -0.66
     Nets
    -0.64
     Dear
    -0.62
     targets
    -0.62
     blackmail
    -0.61
     flies
    -0.61
     Goodman
    -0.61
     Wa
    -0.61
    POSITIVE LOGITS
    inct
    4.84
    inction
    1.92
    ingu
    1.48
    inctions
    1.48
    inguished
    1.32
    inguishable
    1.23
    antly
    1.05
    iple
    0.98
    ract
    0.97
    icent
    0.97
    Act Density 0.009%

    No Known Activations