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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and bureaucratic processes

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or procedural processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.71
    vation
    -0.64
     Hots
    -0.63
     Haram
    -0.60
    hiro
    -0.60
    oft
    -0.59
     earnest
    -0.57
    mson
    -0.57
     Portug
    -0.57
     Wand
    -0.56
    POSITIVE LOGITS
    ional
    1.14
    ions
    0.79
    ioned
    0.79
     overseen
    0.74
    DragonMagazine
    0.74
     process
    0.73
    hene
    0.71
    anus
    0.69
    wright
    0.68
    matically
    0.66
    Act Density 0.032%

    No Known Activations