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

    Neuronpedia

    INDEX
    Explanations

    JSON object closures and structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     back
    -0.66
     of
    -0.64
    fleisch
    -0.59
    しら
    -0.58
    𝙜
    -0.57
    ρή
    -0.57
    々
    -0.56
    CR
    -0.55
    𝙙
    -0.54
     GenerationType
    -0.54
    POSITIVE LOGITS
    ()),
    1.39
    %),
    1.38
    ,:),
    1.36
     %),
    1.35
    ']),
    1.35
    ,",
    1.35
    $),
    1.31
    ]),
    1.31
    ),),
    1.30
    ]),
    1.29
    Act Density 0.101%

    No Known Activations