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

    Neuronpedia

    INDEX
    Explanations

    the brand name "Pro"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Pro" brand or series in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     straw
    -0.77
    ãĤ¼ãĤ¦ãĤ¹
    -0.77
    owship
    -0.76
     halls
    -0.75
    assetsadobe
    -0.73
    DERR
    -0.66
    ibrary
    -0.63
    gow
    -0.63
     needles
    -0.63
     Dise
    -0.63
    POSITIVE LOGITS
    digy
    1.48
    secution
    1.22
    gression
    1.22
    posal
    1.22
    verbs
    1.21
    clamation
    1.12
    blems
    1.09
    ceed
    1.07
    poses
    1.05
    hibited
    1.03
    Act Density 0.018%

    No Known Activations