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

    Neuronpedia

    INDEX
    Explanations

    technical terms, instructions, or code syntax

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.65
    haired
    -0.65
    ivals
    -0.65
    tarian
    -0.62
    regon
    -0.62
    sonian
    -0.61
    kefeller
    -0.61
     Mellon
    -0.60
    erest
    -0.59
     thro
    -0.58
    POSITIVE LOGITS
    ynchron
    1.11
    semb
    1.09
    phalt
    1.04
     shown
    1.03
     mentioned
    1.03
    ynchronous
    1.02
    semble
    1.02
    bestos
    1.00
    pects
    0.99
     opposed
    0.99
    Act Density 0.134%

    No Known Activations