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

    Neuronpedia

    INDEX
    Explanations

    terms related to fire and firefighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢı
    -0.16
    anism
    -0.16
    ities
    -0.15
    endir
    -0.14
    weis
    -0.14
    âĢı
    -0.14
    rades
    -0.14
    riz
    -0.14
    ota
    -0.14
    aires
    -0.14
    POSITIVE LOGITS
    nze
    0.24
    places
    0.22
    proof
    0.21
    brand
    0.20
    ball
    0.20
    bird
    0.19
    /fire
    0.19
    brands
    0.19
    works
    0.18
    ighter
    0.18
    Act Density 0.037%

    No Known Activations