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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal issues and consequences

    oai_token-act-pair · gpt-3.5-turbo

    the article "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ontent
    -0.73
    berman
    -0.70
    ratulations
    -0.69
    ecided
    -0.67
    scape
    -0.66
    utan
    -0.65
    lly
    -0.65
    heit
    -0.64
    gans
    -0.64
    kson
    -0.64
    POSITIVE LOGITS
     outset
    1.36
     behest
    1.24
     same
    1.16
     forefront
    1.06
     periphery
    1.01
     slightest
    1.01
     expense
    1.00
     intersections
    0.96
     conclusion
    0.96
     earliest
    0.96
    Act Density 0.179%

    No Known Activations