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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize negation or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     qualquer
    -0.50
    morphism
    -0.50
    IInterface
    -0.48
     formules
    -0.48
     vías
    -0.47
    şti
    -0.47
    Doi
    -0.47
    rapie
    -0.45
    surate
    -0.45
     trasparente
    -0.45
    POSITIVE LOGITS
    owohl
    1.00
     kasarigan
    0.81
     both
    0.81
     både
    0.77
    neither
    0.74
    tagHelperRunner
    0.74
     Roskov
    0.74
    AddTagHelper
    0.74
    первых
    0.74
    both
    0.74
    Act Density 0.339%

    No Known Activations