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

    Neuronpedia

    INDEX
    Explanations

    themes related to trust and credibility in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íĹĮ
    -0.15
    fleet
    -0.14
    PropertyDescriptor
    -0.14
    oplay
    -0.14
     STATS
    -0.14
    à¸ģรรม
    -0.14
     Templates
    -0.14
    affe
    -0.14
     Talent
    -0.14
    TEMPLATE
    -0.14
    POSITIVE LOGITS
     trust
    0.67
    trust
    0.57
     Trust
    0.56
    Trust
    0.54
     trusted
    0.50
     trustworthy
    0.48
     trusts
    0.48
    trusted
    0.45
     trusting
    0.43
    ä¿¡
    0.42
    Act Density 0.269%

    No Known Activations