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

    Neuronpedia

    INDEX
    Explanations

    sections of code and programming-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    programming-related output functions and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mods
    -0.76
    chool
    -0.69
    orship
    -0.67
    abase
    -0.66
    OTS
    -0.65
    anth
    -0.64
    urat
    -0.64
    Flickr
    -0.64
    omal
    -0.64
     pilgrimage
    -0.63
    POSITIVE LOGITS
     "\
    0.80
     Reports
    0.78
     ERROR
    0.78
    ;;;;;;;;;;;;
    0.74
     "%
    0.74
     "{
    0.72
     Statements
    0.72
    EO
    0.72
    andum
    0.69
     Already
    0.69
    Act Density 0.101%

    No Known Activations