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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldur
    -0.15
     boz
    -0.15
    rani
    -0.14
    rdf
    -0.14
    radient
    -0.14
    ãģĵãĤį
    -0.14
    amient
    -0.13
    weeney
    -0.13
    _PRIVATE
    -0.13
    peria
    -0.13
    POSITIVE LOGITS
    ses
    0.16
     cont
    0.16
    reet
    0.15
    /how
    0.14
    s
    0.14
     tac
    0.14
     ê¸Īìķ¡
    0.13
    /Internal
    0.13
     Chip
    0.13
     sang
    0.13
    Act Density 0.075%

    No Known Activations