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

    Neuronpedia

    INDEX
    Explanations

    options and alternatives in discussions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <typeof
    -0.17
    ANGLES
    -0.17
    zburg
    -0.17
     度
    -0.17
    isphere
    -0.16
    drv
    -0.15
    ستÙĩ
    -0.15
    ÙĪاج
    -0.15
    apl
    -0.15
     示
    -0.15
    POSITIVE LOGITS
     else
    0.19
    else
    0.15
     directly
    0.15
    _else
    0.15
     Supplement
    0.14
    láda
    0.14
     Rare
    0.14
    ator
    0.14
    pora
    0.14
    ubber
    0.14
    Act Density 0.297%

    No Known Activations