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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flix
    -0.17
    utra
    -0.17
    dum
    -0.15
    udeau
    -0.15
    idot
    -0.15
    /or
    -0.15
    ilation
    -0.15
    ubern
    -0.15
    iyah
    -0.15
    ICODE
    -0.15
    POSITIVE LOGITS
     else
    0.17
    anges
    0.17
    chest
    0.15
     же
    0.15
    naments
    0.14
     Or
    0.14
    ξε
    0.14
     simply
    0.14
     ELSE
    0.14
    ania
    0.13
    Act Density 0.069%

    No Known Activations