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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causes, justifications, and beliefs in legal or argumentative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    cause point justify warrant consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.59
    principalColumn
    -0.54
    ValueStyle
    -0.50
     للاسماء
    -0.49
    MessageTagHelper
    -0.44
    UnitTesting
    -0.43
    ыгана
    -0.41
    LookAnd
    -0.40
    angeran
    -0.40
    AsUp
    -0.39
    POSITIVE LOGITS
    rungsseite
    0.53
     loud
    0.47
    complexType
    0.43
    didSet
    0.43
     Loud
    0.40
     reason
    0.40
    createServer
    0.38
     surla
    0.38
    homonymie
    0.38
    0.38
    Act Density 0.188%

    No Known Activations