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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "skip" and its variations, which suggest omitted actions or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bì
    -0.16
    uur
    -0.15
    .UnitTesting
    -0.15
    avou
    -0.15
    leh
    -0.15
    ayd
    -0.14
    +Sans
    -0.14
    laps
    -0.14
    hiba
    -0.14
    coma
    -0.14
    POSITIVE LOGITS
    ting
    0.17
     altogether
    0.17
    رÛĮÙĩ
    0.17
    olin
    0.16
    pered
    0.14
    ırı
    0.14
    itz
    0.14
     Exact
    0.14
    ag
    0.13
     skip
    0.13
    Act Density 0.021%

    No Known Activations