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

    Neuronpedia

    INDEX
    Explanations

    occurrences of programming keywords and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cker
    -0.17
    она
    -0.17
    pher
    -0.15
    urf
    -0.15
    iveness
    -0.15
    ara
    -0.14
    era
    -0.14
     Pride
    -0.14
    Object
    -0.14
     throttle
    -0.14
    POSITIVE LOGITS
    ãĤ¿ãĥ³
    0.16
    elem
    0.16
    nodoc
    0.15
    yar
    0.15
    -↵↵
    0.15
    eor
    0.15
     ëĦ¤ìĿ´íĬ¸
    0.15
    tor
    0.14
    adr
    0.14
    ELLOW
    0.14
    Act Density 0.190%

    No Known Activations