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

    Neuronpedia

    INDEX
    Explanations

    the beginning and end markers of sequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -2.72
     reluct
    -2.56
     disgra
    -2.52
     unlaw
    -2.52
     shenan
    -2.40
     impractica
    -2.40
     impra
    -2.35
     ineffec
    -2.35
     horrend
    -2.34
     disagre
    -2.31
    POSITIVE LOGITS
    <bos>
    14.46
    GEBURTSDATUM
    2.54
    expandindo
    2.52
     betweenstory
    2.48
    Autoritní
    2.46
    تقاوى
    2.20
     Italijani
    2.16
     Administrativna
    2.16
     Paglinawan
    2.11
     kasarigan
    2.11
    Act Density 0.090%

    No Known Activations