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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence of something or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.50
    __":
    -0.38
    tagHelper
    -0.37
     gardeners
    -0.36
    fxml
    -0.35
     ModelExpression
    -0.35
     че
    -0.35
     fören
    -0.35
     chefs
    -0.35
     a
    -0.34
    POSITIVE LOGITS
     nothing
    0.81
     NOTHING
    0.77
     никакого
    0.75
    nothing
    0.74
     Nothing
    0.74
    Nothing
    0.73
    Aucun
    0.72
    aucun
    0.71
     هیچ
    0.68
     nothin
    0.68
    Act Density 0.293%

    No Known Activations