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

    Neuronpedia

    INDEX
    Explanations

    concepts pertaining to truth and dishonesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jstor
    -0.70
    addPreferredGap
    -0.68
    ⓧ
    -0.67
    ╚
    -0.63
     وتسجيلات
    -0.63
    Архівовано
    -0.61
    Tembelea
    -0.61
    naires
    -0.60
    canActivate
    -0.60
    :+:
    -0.59
    POSITIVE LOGITS
     truth
    3.88
     Truth
    3.44
    truth
    3.44
    Truth
    3.25
     TRUTH
    3.14
     truths
    2.72
     Wahrheit
    2.40
     Truths
    2.39
     verità
    2.11
     vérité
    2.04
    Act Density 0.039%

    No Known Activations