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

    Neuronpedia

    INDEX
    Explanations

    capital letters inside a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'Y' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.81
    ities
    -0.77
     Painter
    -0.64
    ĸļ
    -0.63
     Cortana
    -0.61
    felt
    -0.61
     laps
    -0.61
    icable
    -0.59
     divid
    -0.59
    ĵĺ
    -0.57
    POSITIVE LOGITS
    outube
    1.20
    orkshire
    1.11
    ORK
    1.09
    outh
    1.08
    ield
    1.08
    OUR
    1.04
    EAR
    1.03
    ahoo
    1.00
    ielding
    1.00
    oga
    0.99
    Act Density 0.038%

    No Known Activations