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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantifiable or measurable concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.15
    iddet
    -0.15
     ÑĢей
    -0.14
    iglia
    -0.14
    cott
    -0.14
    419
    -0.14
    folio
    -0.14
    769
    -0.14
    eka
    -0.13
    _unsigned
    -0.13
    POSITIVE LOGITS
    аÑĢÑı
    0.15
    vette
    0.15
    ÑĤеÑĢн
    0.14
    adder
    0.14
     奥
    0.14
    _tools
    0.14
    ÑĤоÑĩ
    0.13
    ÑĢиÑĦ
    0.13
    endif
    0.13
    rá
    0.13
    Act Density 0.002%

    No Known Activations