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

    Neuronpedia

    INDEX
    Explanations

    Latin characters followed by digits starting with the letter 'g'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gleaming
    -0.70
     Puzzles
    -0.63
    aram
    -0.63
     Archdemon
    -0.62
    gel
    -0.61
    ortium
    -0.58
    eteria
    -0.56
    bage
    -0.56
     Dele
    -0.56
    collar
    -0.55
    POSITIVE LOGITS
    vous
    0.81
    ukong
    0.66
    gotten
    0.63
    schild
    0.61
    aunts
    0.61
    ãĤ¤ãĥĪ
    0.61
    ¨
    0.61
    èª
    0.60
    WARE
    0.60
    roth
    0.60
    Act Density 0.348%

    No Known Activations