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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal rulings and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chân
    -0.16
    furt
    -0.15
    ึ
    -0.15
    elyn
    -0.14
    ilyn
    -0.14
    SizePolicy
    -0.14
    AGMA
    -0.14
     //================================================================
    -0.14
    enton
    -0.14
    onec
    -0.14
    POSITIVE LOGITS
     favor
    0.90
     favour
    0.84
     Favor
    0.81
    favor
    0.74
     favors
    0.73
     fav
    0.67
     favorable
    0.52
     favored
    0.47
     favourable
    0.47
     Fav
    0.46
    Act Density 0.252%

    No Known Activations