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

    Neuronpedia

    INDEX
    Explanations

    words that convey authenticity or sincerity

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

    authenticity and sincerity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     courts
    -0.39
    standes
    -0.36
    bní
    -0.35
    fromCharCode
    -0.34
     symbole
    -0.34
     retir
    -0.34
     desertcart
    -0.33
     tịch
    -0.33
     book
    -0.33
     herein
    -0.33
    POSITIVE LOGITS
     genuinely
    1.77
    genu
    1.34
     Genu
    1.11
     sincerely
    0.99
     legitimately
    0.96
    honestly
    0.92
     honestly
    0.91
    Genuine
    0.90
     genu
    0.89
     genuine
    0.89
    Act Density 0.006%

    No Known Activations