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

    Neuronpedia

    INDEX
    Explanations

    words related to darkness and negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    references to darkness and themes of despair or evil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ª
    -0.79
    ãĥ£
    -0.71
    visors
    -0.70
    ī
    -0.70
    ducers
    -0.67
    İ
    -0.66
    tein
    -0.65
    Ĺ
    -0.64
    arel
    -0.64
    ħ
    -0.64
    POSITIVE LOGITS
     Incarn
    1.02
     reckoning
    0.91
     awaits
    0.90
     incarn
    0.86
     doom
    0.85
    mares
    0.85
     inflicted
    0.85
    bringer
    0.82
     Hades
    0.81
     abyss
    0.76
    Act Density 0.109%

    No Known Activations