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

    Neuronpedia

    INDEX
    Explanations

    references to specific legal or bureaucratic 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
    -0.69
    azo
    -0.67
    birds
    -0.59
    lar
    -0.58
    mson
    -0.58
    keley
    -0.57
    aez
    -0.56
     earnest
    -0.55
     jeans
    -0.55
    vation
    -0.55
    POSITIVE LOGITS
    ional
    1.25
    ions
    0.88
    wright
    0.79
    ioned
    0.77
    isans
    0.75
     process
    0.71
    DragonMagazine
    0.71
     Procedure
    0.70
    imony
    0.68
    hene
    0.67
    Act Density 0.039%

    No Known Activations