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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and conditions involving variables or parameters in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Buffered
    -0.14
    (prog
    -0.14
     Trace
    -0.14
    eries
    -0.14
    Hel
    -0.14
    ery
    -0.14
    .crm
    -0.13
     AA
    -0.13
    xm
    -0.13
    icari
    -0.13
    POSITIVE LOGITS
    aylor
    0.16
    kea
    0.16
    vern
    0.15
    anja
    0.15
    istrovstvÃŃ
    0.14
    иÑĩа
    0.14
    ield
    0.14
    zx
    0.14
    ç
    0.14
    Ìī
    0.14
    Act Density 0.067%

    No Known Activations