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

    Neuronpedia

    INDEX
    Explanations

    concepts related to faith, belief, and trust

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

    Virtues, religious concepts, or capitalized words

    np_acts-logits-general · gemini-2.0-flash

    virtue names and abstract qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.64
    WindowConstants
    -0.62
    publicPath
    -0.59
    notic
    -0.59
    ltk
    -0.58
    arası
    -0.55
    GTCX
    -0.54
    rasco
    -0.54
    Novel
    -0.54
    StateException
    -0.54
    POSITIVE LOGITS
     Reſ
    0.81
     Majefty
    0.81
    fulness
    0.80
    fully
    0.80
     perſon
    0.79
     pleaſure
    0.79
     Chriftian
    0.78
     Diſ
    0.78
     ſtate
    0.78
     itſelf
    0.76
    Act Density 0.513%

    No Known Activations