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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or personal identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .TestCase
    -0.17
    icast
    -0.16
    uther
    -0.16
     Nun
    -0.16
     Brass
    -0.16
    alse
    -0.16
    erp
    -0.15
    BuilderFactory
    -0.14
    oya
    -0.14
    anner
    -0.14
    POSITIVE LOGITS
    ule
    0.18
    unks
    0.17
    unk
    0.16
     Mand
    0.15
     åĭ
    0.15
    amel
    0.15
    δε
    0.15
    ãĥ³ãĥIJãĥ¼
    0.15
    estr
    0.15
    steen
    0.15
    Act Density 0.025%

    No Known Activations