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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal procedures or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.73
     earnest
    -0.64
    hiro
    -0.62
    undai
    -0.61
    mson
    -0.60
    azo
    -0.60
    akening
    -0.60
    lar
    -0.60
    IGHTS
    -0.59
     Hots
    -0.59
    POSITIVE LOGITS
    ional
    1.10
    DragonMagazine
    0.85
    ions
    0.76
     process
    0.76
    ioned
    0.75
    utics
    0.73
    wright
    0.69
     processes
    0.69
    hene
    0.67
     Process
    0.67
    Act Density 0.027%

    No Known Activations