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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quality and rankings among options or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    μά
    -0.15
    VICES
    -0.14
     Favorite
    -0.14
    ÙĪÙĩ
    -0.14
    ady
    -0.14
    682
    -0.14
    hiro
    -0.13
    unes
    -0.13
    adem
    -0.13
     stdClass
    -0.13
    POSITIVE LOGITS
    èle
    0.15
    Lite
    0.14
    ÑĢÑĥ
    0.14
    ulos
    0.14
    uml
    0.14
    IDs
    0.14
    AndWait
    0.14
    IDS
    0.14
    404
    0.14
     Kirk
    0.13
    Act Density 0.032%

    No Known Activations