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

    Neuronpedia

    INDEX
    Explanations

    verbs related to accomplishments or achievements

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs that indicate actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.66
    PU
    -0.58
     DRAGON
    -0.58
    adan
    -0.57
    PI
    -0.56
    arger
    -0.55
    aging
    -0.55
    itte
    -0.54
    dimension
    -0.53
    issue
    -0.52
    POSITIVE LOGITS
    nesday
    0.72
    Ĥİ
    0.72
     theirs
    0.67
    eals
    0.66
    onite
    0.64
    rums
    0.62
    monton
    0.62
    raints
    0.61
    DeliveryDate
    0.59
     by
    0.59
    Act Density 0.622%

    No Known Activations