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

    Neuronpedia

    INDEX
    Explanations

    positive indicators of success or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maal
    -0.17
    ToBounds
    -0.16
    liga
    -0.15
    ashtra
    -0.15
     flips
    -0.15
    unal
    -0.14
    qli
    -0.14
    913
    -0.14
     Aux
    -0.14
    ways
    -0.14
    POSITIVE LOGITS
    oe
    0.17
    rieve
    0.15
    -extension
    0.14
     {{↵
    0.14
    isers
    0.14
    utt
    0.14
    ilen
    0.14
     ÄĮes
    0.14
    pest
    0.14
    ieces
    0.13
    Act Density 0.437%

    No Known Activations