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

    Neuronpedia

    INDEX
    Explanations

    file paths or references to files in a program

    oai_token-act-pair · gpt-3.5-turbo

    special characters or operators used in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertodd
    -0.70
     reluct
    -0.70
     millenn
    -0.66
     htt
    -0.64
     widest
    -0.64
     nodd
    -0.64
     Auditor
    -0.63
     dece
    -0.62
     rall
    -0.61
     Redd
    -0.61
    POSITIVE LOGITS
    meta
    0.91
    CONT
    0.89
    400
    0.88
    DATA
    0.86
    apply
    0.86
    pol
    0.85
    300
    0.84
    #$
    0.84
    empty
    0.84
    50
    0.82
    Act Density 0.115%

    No Known Activations