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

    Neuronpedia

    INDEX
    Explanations

    specific personal pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DropTable
    -0.54
    parsedMessage
    -0.52
    LayoutConstraint
    -0.49
     stripped
    -0.45
    Geografía
    -0.42
    TagMode
    -0.41
    ThroughAttribute
    -0.41
     baratas
    -0.40
     cash
    -0.39
    boutin
    -0.39
    POSITIVE LOGITS
    :✨
    0.65
     ferons
    0.53
    ifflin
    0.45
     <=",
    0.44
     ब्रेकडाउन
    0.42
    HXLINE
    0.41
    GTCX
    0.41
    $_['
    0.40
    ayam
    0.40
    NameInMap
    0.39
    Act Density 0.028%

    No Known Activations