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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of a deity or god

    oai_token-act-pair · gpt-3.5-turbo

    references to deities and gods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carb
    -0.79
     Diabetes
    -0.72
    phrine
    -0.71
     Retirement
    -0.70
     Lans
    -0.68
     Hyde
    -0.68
    NK
    -0.68
     Flint
    -0.66
     Prospect
    -0.65
    DonaldTrump
    -0.64
    POSITIVE LOGITS
    mother
    1.20
    father
    1.20
    frey
    1.05
     god
    1.04
    parents
    1.01
    god
    0.99
    zilla
    0.95
    liness
    0.91
    gling
    0.90
    sword
    0.88
    Act Density 0.009%

    No Known Activations