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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief or faith, particularly belief in specific entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to belief or faith in various concepts, particularly in God or similar ideals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.94
    DragonMagazine
    -0.76
    irable
    -0.71
    в
    -0.71
    MAP
    -0.68
    hai
    -0.68
    wl
    -0.67
    luent
    -0.67
    iae
    -0.67
    Dispatch
    -0.66
    POSITIVE LOGITS
     miracles
    1.23
    clus
    1.08
     fairness
    0.94
     preserving
    0.94
     ghosts
    0.93
     God
    0.91
     equality
    0.85
     reincarn
    0.85
     independence
    0.84
     immortality
    0.84
    Act Density 0.071%

    No Known Activations