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

    Neuronpedia

    INDEX
    Explanations

    well-defined, regulated, crafted, made, written, understood, informed, lit, constructed, paid, implemented, administered, maintained, appointed, managed words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with definitions, regulations, and evaluations of quality or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.71
    ĪĴ
    -0.69
    kay
    -0.68
    İĭ
    -0.65
    alos
    -0.65
    manent
    -0.63
    idge
    -0.63
    chwitz
    -0.63
    emb
    -0.62
    arth
    -0.62
    POSITIVE LOGITS
    paren
    0.75
    entious
    0.75
     (>
    0.72
     (<
    0.69
     geographically
    0.67
    ÃŁ
    0.63
     indeed
    0.58
    .–
    0.57
     (~
    0.56
     considering
    0.56
    Act Density 0.167%

    No Known Activations