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

    Neuronpedia

    INDEX
    Explanations

    concepts related to deep philosophical ideas and emotions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to emotions, wisdom, and philosophical beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uran
    -0.74
    addons
    -0.74
    mx
    -0.70
    era
    -0.67
    ZI
    -0.67
     Late
    -0.65
    bern
    -0.62
    gran
    -0.61
    arnaev
    -0.60
    pict
    -0.59
    POSITIVE LOGITS
     arises
    0.84
     encompasses
    0.84
     exists
    0.84
     itself
    0.82
     threshold
    0.79
    worthiness
    0.79
    lessness
    0.78
     arising
    0.77
     arose
    0.74
     multiplier
    0.74
    Act Density 0.446%

    No Known Activations