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

    Neuronpedia

    INDEX
    Explanations

    terms related to invalidity or null values in a technical or legal context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nullification or cancellation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.80
     millenn
    -0.78
     livest
    -0.76
     exha
    -0.76
    DonaldTrump
    -0.74
    BOOK
    -0.73
     hemor
    -0.69
     toget
    -0.69
    ilitating
    -0.68
     ingred
    -0.67
    POSITIVE LOGITS
    ifying
    1.27
    ptr
    1.23
    ifies
    1.18
    ified
    1.16
    ification
    1.09
    ifier
    1.04
    ify
    1.00
    ifiers
    0.97
    ities
    0.94
    eenth
    0.91
    Act Density 0.023%

    No Known Activations