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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to scientific research citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abal
    -0.17
    gings
    -0.16
    laÄį
    -0.15
    GS
    -0.14
    PTS
    -0.14
    cef
    -0.13
    essor
    -0.13
    408
    -0.13
    abez
    -0.13
    ÃŃky
    -0.13
    POSITIVE LOGITS
    oro
    0.14
     Tent
    0.14
    _callable
    0.14
    strand
    0.14
    anela
    0.14
    agma
    0.14
    tres
    0.14
    دÙĩ
    0.14
     Heller
    0.13
    ł
    0.13
    Act Density 0.047%

    No Known Activations