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

    Neuronpedia

    INDEX
    Explanations

    references to shadowy concepts or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anto
    -0.18
    587
    -0.16
    SCRI
    -0.15
    볨
    -0.15
    หมà¸Ķ
    -0.15
    zione
    -0.15
    viÄį
    -0.15
    رÙĪÙħ
    -0.14
    ouch
    -0.14
    Ń
    -0.14
    POSITIVE LOGITS
     cast
    0.21
     shadow
    0.20
    sock
    0.20
     Shadow
    0.18
    .shadow
    0.17
    y
    0.17
     Cast
    0.17
     thrown
    0.17
    ing
    0.17
    lands
    0.17
    Act Density 0.019%

    No Known Activations