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

    Neuronpedia

    INDEX
    Explanations

    capitalized words with the letter "D"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific designations or codes starting with the letter 'D'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¡
    -0.78
     Bulg
    -0.77
     Isles
    -0.71
    terday
    -0.70
     lett
    -0.63
     Pose
    -0.62
     friction
    -0.62
     Canaver
    -0.62
     Remem
    -0.61
     slurs
    -0.61
    POSITIVE LOGITS
    etermination
    1.29
    etermin
    1.29
    etermined
    1.22
    ownt
    1.21
    aughters
    1.17
    imensional
    1.16
    wayne
    1.13
    izzy
    1.12
    REAM
    1.11
    ynam
    1.10
    Act Density 0.049%

    No Known Activations