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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and numeric values within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cola
    -0.80
    È
    -0.73
    ophen
    -0.70
    ucci
    -0.67
     compan
    -0.66
    iar
    -0.65
    natureconservancy
    -0.65
    Increases
    -0.64
    ulhu
    -0.64
     fung
    -0.63
    POSITIVE LOGITS
    dal
    0.68
     Sabha
    0.68
    xual
    0.66
    monton
    0.66
    schild
    0.65
    ogle
    0.64
    amus
    0.63
    ceptor
    0.62
    3333
    0.61
    actic
    0.61
    Act Density 0.240%

    No Known Activations