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

    Neuronpedia

    INDEX
    Explanations

    instances and variations of the word "full."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olik
    -0.16
    ebi
    -0.15
    jen
    -0.15
    jem
    -0.15
    اÙģت
    -0.15
    bai
    -0.15
    ennes
    -0.15
    utherford
    -0.14
    ISM
    -0.14
    avad
    -0.14
    POSITIVE LOGITS
     blown
    0.36
    ledged
    0.32
    -bl
    0.31
    -scale
    0.31
     fled
    0.31
    filled
    0.28
    erton
    0.28
    /full
    0.27
    fil
    0.27
    -length
    0.26
    Act Density 0.053%

    No Known Activations