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

    Neuronpedia

    INDEX
    Explanations

    names and expressions of gratitude or sign-off phrases in correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.63
    MigrationBuilder
    -0.62
     للاسماء
    -0.61
     stockbild
    -0.61
    الحياه
    -0.61
     ModelExpression
    -0.60
     Мексичка
    -0.60
     queſta
    -0.59
    Personensuche
    -0.59
    gdx
    -0.58
    POSITIVE LOGITS
    sin
    0.36
    calaure
    0.35
     Grund
    0.30
    <eos>
    0.30
    ∃
    0.30
    nach
    0.29
    .
    0.29
    DropTable
    0.29
    Respectfully
    0.29
     TC
    0.28
    Act Density 0.233%

    No Known Activations