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

    Neuronpedia

    INDEX
    Explanations

    phrases that assert or emphasize the concept of truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stating truth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sonrası
    -0.51
    harapkan
    -0.47
     abgesch
    -0.45
     waarbij
    -0.42
     inaugural
    -0.42
     årene
    -0.41
     katanya
    -0.41
     fuese
    -0.41
    出版年
    -0.40
    ayos
    -0.40
    POSITIVE LOGITS
     truth
    1.24
    truth
    1.03
     TRUTH
    0.97
     reality
    0.90
     Wahrheit
    0.89
     Truth
    0.88
    Truth
    0.85
     vérité
    0.82
    reality
    0.82
    真相
    0.72
    Act Density 0.010%

    No Known Activations