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

    Neuronpedia

    INDEX
    Explanations

    instances of words or phrases indicating action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prostor
    -0.15
    agrams
    -0.15
    lanma
    -0.15
    -lnd
    -0.14
    elts
    -0.14
    imeType
    -0.14
    quire
    -0.14
    enek
    -0.14
    BuilderFactory
    -0.14
    inds
    -0.14
    POSITIVE LOGITS
    idable
    0.25
    able
    0.25
    ulous
    0.24
    izable
    0.24
    inous
    0.23
    ous
    0.23
    tractive
    0.23
    idious
    0.22
    eworthy
    0.22
    urious
    0.22
    Act Density 0.003%

    No Known Activations