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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and actions they are associated with

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAGON
    -0.61
    adan
    -0.60
    isol
    -0.58
    PU
    -0.55
    itte
    -0.54
    cipled
    -0.54
    adier
    -0.54
    Trade
    -0.54
     Hier
    -0.54
    MAT
    -0.53
    POSITIVE LOGITS
    monton
    0.81
    nesday
    0.80
    DeliveryDate
    0.75
    Ĥİ
    0.72
    eals
    0.71
     pione
    0.69
     subur
    0.67
     aback
    0.65
    ocument
    0.64
    rums
    0.62
    Act Density 0.627%

    No Known Activations