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

    Neuronpedia

    INDEX
    Explanations

    references to faith and its associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ETT
    -0.77
    rrr
    -0.69
    ette
    -0.69
     Mullins
    -0.69
    Eugen
    -0.69
     huwa
    -0.68
    </b>
    -0.67
     Clarke
    -0.65
     mence
    -0.65
     Dov
    -0.63
    POSITIVE LOGITS
     FAITH
    1.65
     faith
    1.52
     Faith
    1.50
    faith
    1.50
    Faith
    1.45
     faiths
    1.14
     Faithful
    0.98
     faithfulness
    0.95
    faithful
    0.93
     ویکی‌پدیا
    0.90
    Act Density 0.115%

    No Known Activations