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

    Neuronpedia

    INDEX
    Explanations

    words related to coding and technical parameters like "Name" and "password"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of identifiers or names within a programming or data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romy
    -0.89
    yrinth
    -0.83
    awaru
    -0.79
    psey
    -0.71
    ilib
    -0.70
    tumblr
    -0.70
    yrus
    -0.68
    icult
    -0.67
     balcon
    -0.66
     Bulletin
    -0.65
    POSITIVE LOGITS
    plates
    1.09
    name
    1.06
    names
    1.02
    Name
    0.94
    plate
    0.94
    ames
    0.88
    NAME
    0.88
     names
    0.87
    paces
    0.86
     NAME
    0.86
    Act Density 0.025%

    No Known Activations