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

    Neuronpedia

    INDEX
    Explanations

    negation terms commonly used in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ARAB
    -0.78
    fwd
    -0.77
    ódz
    -0.74
    pezi
    -0.73
     Eisenberg
    -0.71
    SAX
    -0.71
     pleaf
    -0.69
     SAX
    -0.69
     Arab
    -0.68
     fwd
    -0.68
    POSITIVE LOGITS
    neither
    1.18
     neither
    1.10
    Nor
    1.10
     NOR
    1.05
     nor
    1.04
    nor
    1.02
     Nor
    1.01
     Norris
    0.98
    Neither
    0.97
    (!__
    0.97
    Act Density 0.074%

    No Known Activations