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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "false" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.98
     énergé
    -0.84
     referenties
    -0.83
    +#+#
    -0.83
     aufnehmen
    -0.82
     chré
    -0.80
     essenciais
    -0.79
     Hecht
    -0.77
    ynki
    -0.76
    spricht
    -0.76
    POSITIVE LOGITS
     false
    1.32
     False
    1.19
    false
    1.15
    False
    1.09
     FALSE
    0.99
     fals
    0.97
    FALSE
    0.96
     falsely
    0.95
     falsehood
    0.77
    GraphicsUnit
    0.72
    Act Density 0.064%

    No Known Activations