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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to legal terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal criteria or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.64
    nce
    -0.63
     Volunteers
    -0.62
     Rouge
    -0.62
    film
    -0.61
     Empress
    -0.61
     Bake
    -0.61
     Leilan
    -0.61
     Riders
    -0.60
    haw
    -0.60
    POSITIVE LOGITS
     kinds
    1.24
     aspects
    1.15
     factors
    1.12
     types
    1.12
     tasks
    1.03
     traits
    0.99
     sorts
    0.98
     tenets
    0.98
     variables
    0.97
     characteristic
    0.96
    Act Density 0.490%

    No Known Activations