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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases indicating falsehood or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.63
    Tembelea
    -0.61
    Inhalation
    -0.58
    plor
    -0.53
    MLLoader
    -0.52
    GIH
    -0.52
     mobilité
    -0.51
    NamedQueries
    -0.50
     Beine
    -0.50
    tamment
    -0.50
    POSITIVE LOGITS
     false
    4.54
    false
    3.83
     False
    3.77
    False
    3.45
     FALSE
    3.07
     falso
    2.77
    FALSE
    2.70
     falsa
    2.61
     falsely
    2.57
     falsos
    2.51
    Act Density 0.108%

    No Known Activations