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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illow
    -0.17
     BITTE
    -0.16
    morph
    -0.16
    utsch
    -0.15
    xes
    -0.15
    $MESS
    -0.15
    lich
    -0.15
     iParam
    -0.14
    á»ĭch
    -0.14
    (EIF
    -0.14
    POSITIVE LOGITS
     Fold
    0.16
     Arms
    0.14
     Шев
    0.14
    ucc
    0.14
    vt
    0.14
    ucher
    0.13
    cer
    0.13
    amilia
    0.13
    uter
    0.13
    stream
    0.13
    Act Density 0.002%

    No Known Activations