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

    Neuronpedia

    INDEX
    Explanations

    legal terms and statutes

    oai_token-act-pair · gpt-3.5-turbo

    references to legal statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idates
    -0.75
    agnar
    -0.67
    anqu
    -0.66
    rocal
    -0.65
     parachute
    -0.65
     plates
    -0.64
    iston
    -0.63
     sidel
    -0.63
    cffffcc
    -0.62
     anniversary
    -0.62
    POSITIVE LOGITS
    士
    0.81
    utes
    0.80
    vere
    0.79
    ute
    0.75
    shock
    0.73
    UTE
    0.70
     Eleven
    0.70
     Dollar
    0.69
    vich
    0.67
    ault
    0.66
    Act Density 0.015%

    No Known Activations