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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation, particularly periods and bullet points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KE
    -0.15
    uish
    -0.15
    άλÏħ
    -0.15
    aley
    -0.14
    ategory
    -0.14
    ãĤ
    -0.14
     SE
    -0.14
    Integrated
    -0.14
    ormal
    -0.13
    ivers
    -0.13
    POSITIVE LOGITS
    406
    0.17
    lander
    0.16
    æīĺ
    0.15
    tin
    0.15
    435
    0.14
    λι
    0.14
    Æ°á»Ŀng
    0.14
    £
    0.14
    ίκ
    0.14
    479
    0.13
    Act Density 0.003%

    No Known Activations