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

    Neuronpedia

    INDEX
    Explanations

    commands or executables stored in directories marked with "bin"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "bin" associated with file paths or directories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.75
     Jagu
    -0.71
    ammy
    -0.71
     entrants
    -0.64
    pter
    -0.63
     advant
    -0.62
    theless
    -0.61
    plays
    -0.60
    gypt
    -0.60
    IRE
    -0.60
    POSITIVE LOGITS
    ocular
    1.57
    omial
    1.41
     Laden
    1.19
    ned
    1.08
    ning
    0.98
    nington
    0.96
    thood
    0.94
    stocks
    0.93
    jamin
    0.93
    utils
    0.86
    Act Density 0.019%

    No Known Activations