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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating source attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \CMS
    -0.16
     Cyril
    -0.15
    arkin
    -0.15
    Uploaded
    -0.14
     Bunny
    -0.14
    arium
    -0.14
    izzo
    -0.14
    agra
    -0.14
    妹
    -0.14
    aria
    -0.14
    POSITIVE LOGITS
    ÃĹ↵↵
    0.18
    hti
    0.16
    ıs
    0.16
    ANTED
    0.16
    ihan
    0.15
     vict
    0.14
    Å¡Å¥
    0.14
    æĸ¯çī¹
    0.14
    adow
    0.14
    sse
    0.14
    Act Density 0.000%

    No Known Activations