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

    Neuronpedia

    INDEX
    Explanations

    names and terms containing the sequence "dup"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Dup" or related variations within different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.93
    aceous
    -0.91
    ¯¯¯¯
    -0.75
     Marketable
    -0.73
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    ware
    -0.67
    AMA
    -0.66
     Johann
    -0.65
    izen
    -0.65
    ONEY
    -0.65
    POSITIVE LOGITS
     Dup
    1.38
     dup
    1.27
    lex
    1.11
    olicy
    0.89
    rites
    0.87
    rint
    0.84
     confir
    0.84
    inx
    0.83
    cffff
    0.81
     predec
    0.79
    Act Density 0.012%

    No Known Activations