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

    Neuronpedia

    INDEX
    Explanations

    words related to the formatting and coding conventions used for programming

    oai_token-act-pair · gpt-3.5-turbo

    references to specific formatting and capitalization rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overhe
    -0.75
    netflix
    -0.72
    Kin
    -0.72
     apparel
    -0.71
    odynam
    -0.70
    Blu
    -0.70
     assum
    -0.69
    geries
    -0.67
    Temperature
    -0.64
    atcher
    -0.64
    POSITIVE LOGITS
     aster
    1.18
     suffix
    1.14
     denotes
    1.13
     prefix
    1.11
     denote
    1.10
     notation
    1.05
     vowel
    1.04
     "+
    1.04
     comma
    1.03
     subscript
    1.02
    Act Density 0.408%

    No Known Activations