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

    Neuronpedia

    INDEX
    Explanations

    programming-related headers and sections in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arl
    -0.17
    ype
    -0.16
    unn
    -0.16
    legg
    -0.15
    ег
    -0.14
    rig
    -0.14
    amilia
    -0.14
    ế
    -0.14
    ce
    -0.13
    ÌĢ
    -0.13
    POSITIVE LOGITS
    LOT
    0.17
    æĸĻ
    0.15
    oks
    0.15
    ediator
    0.15
    696
    0.15
    oki
    0.15
    REAM
    0.15
    fir
    0.15
    oku
    0.14
    tat
    0.14
    Act Density 0.025%

    No Known Activations