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

    Neuronpedia

    INDEX
    Explanations

    references to favorability or support in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.59
     JpaRepository
    -0.51
     Públicas
    -0.48
     utafitiHapana
    -0.47
     diagnos
    -0.43
    celotti
    -0.42
    meuble
    -0.41
    Ilo
    -0.40
     Italij
    -0.39
    NPD
    -0.39
    POSITIVE LOGITS
     favoured
    0.80
     favour
    0.80
     favor
    0.78
    fav
    0.75
     favored
    0.75
     Slave
    0.74
     Favor
    0.73
     favours
    0.73
     favors
    0.69
    favor
    0.68
    Act Density 0.372%

    No Known Activations