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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "skip" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ejs
    -0.15
    हन
    -0.15
    ega
    -0.15
    /legal
    -0.14
    eÅŁ
    -0.14
    indsight
    -0.14
    imately
    -0.14
    iyat
    -0.14
    á»Ļ
    -0.14
    eing
    -0.14
    POSITIVE LOGITS
     ahead
    0.32
    pered
    0.30
    per
    0.29
    ahead
    0.28
     Ahead
    0.25
    cq
    0.25
    jack
    0.24
    pering
    0.24
     past
    0.23
    Ahead
    0.22
    Act Density 0.020%

    No Known Activations