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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.16
    peon
    -0.15
    moth
    -0.15
    sWith
    -0.14
    lsa
    -0.14
     Ness
    -0.14
    imiz
    -0.14
    izing
    -0.14
    ise
    -0.14
    ron
    -0.14
    POSITIVE LOGITS
    quo
    0.15
    olvable
    0.14
    ofs
    0.14
    essian
    0.14
    AGEMENT
    0.14
    oenix
    0.14
    ayo
    0.14
    ÑģÑĤеÑĢ
    0.14
    erras
    0.14
    _TH
    0.13
    Act Density 0.036%

    No Known Activations