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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a quantitative increase or upward movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.16
    ingt
    -0.16
    ace
    -0.15
    ecd
    -0.15
    ingly
    -0.15
    oral
    -0.15
    ystone
    -0.14
    tempts
    -0.14
    auer
    -0.14
     rej
    -0.14
    POSITIVE LOGITS
    otre
    0.23
     ward
    0.20
    -to
    0.20
     wards
    0.19
    rightness
    0.18
    ToDate
    0.17
    oload
    0.17
    holds
    0.16
    ozilla
    0.16
     Ward
    0.16
    Act Density 0.032%

    No Known Activations