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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or questions directed at the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alli
    -0.15
    оÑģп
    -0.14
     Gram
    -0.14
    memberOf
    -0.14
    rist
    -0.13
     appetite
    -0.13
    ег
    -0.13
     aqu
    -0.13
    inand
    -0.13
    éĿ
    -0.13
    POSITIVE LOGITS
     cul
    0.16
    isel
    0.15
    urdy
    0.15
    977
    0.14
    oni
    0.14
    finity
    0.14
    REW
    0.14
    277
    0.14
    aign
    0.14
    zie
    0.14
    Act Density 0.030%

    No Known Activations