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

    Neuronpedia

    INDEX
    Explanations

    terms related to suitability and appropriateness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç²
    -0.16
    hed
    -0.16
    hti
    -0.15
    quis
    -0.15
    neau
    -0.14
    hausen
    -0.14
    ãģĦãĤĭ
    -0.14
     Insight
    -0.14
    apsed
    -0.14
    gin
    -0.14
    POSITIVE LOGITS
    ably
    0.28
    cases
    0.20
    ively
    0.17
    eldo
    0.16
    arel
    0.16
    artz
    0.16
    inct
    0.15
    dol
    0.15
    cased
    0.15
    uations
    0.15
    Act Density 0.029%

    No Known Activations