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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shells
    -0.98
    sal
    -0.96
    skins
    -0.95
    swe
    -0.95
    scales
    -0.91
    smo
    -0.90
    shields
    -0.90
    Skins
    -0.89
    shel
    -0.89
    sent
    -0.89
    POSITIVE LOGITS
    principalColumn
    0.40
     số
    0.35
    AndView
    0.32
    ส
    0.31
    apeno
    0.28
     הס
    0.28
    исленность
    0.28
    ♎
    0.27
    Tazama
    0.27
     š
    0.25
    Act Density 4.200%

    No Known Activations