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

    Neuronpedia

    INDEX
    Explanations

    specific programming concepts and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    int
    -0.36
     
    -0.35
     are
    -0.34
    ma
    -0.32
    ing
    -0.31
    di
    -0.31
    <b>
    -0.30
    com
    -0.30
    va
    -0.29
    ↵
    -0.29
    POSITIVE LOGITS
    rungsseite
    1.20
    niſſe
    1.18
    verwijspagina
    1.15
    ſicht
    1.15
    featureID
    1.15
    ロウィン
    1.10
    ſchaft
    1.09
    parsedMessage
    1.09
     ſind
    1.09
    [@BOS@]
    1.08
    Act Density 0.167%

    No Known Activations