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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sax
    -0.15
     Pistol
    -0.15
    odor
    -0.14
    anger
    -0.14
     rede
    -0.14
    forge
    -0.14
     Ott
    -0.14
    LETTE
    -0.13
     Guns
    -0.13
    .y
    -0.13
    POSITIVE LOGITS
    xico
    0.16
    gfx
    0.15
     addCriterion
    0.15
    encent
    0.15
    allah
    0.15
    =%.
    0.14
    ätz
    0.14
    erras
    0.14
    uko
    0.14
    ujet
    0.14
    Act Density 0.065%

    No Known Activations