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

    Neuronpedia

    INDEX
    Explanations

    references to a specific fictional or mythical entity, likely named "Death Star."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Death" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.82
    ij
    -0.81
    Ń·
    -0.78
    Ģ
    -0.74
    ================================
    -0.74
    æ°
    -0.73
    EEK
    -0.73
    OPER
    -0.73
    Ĥ
    -0.71
    Ĥİ
    -0.69
    POSITIVE LOGITS
    hound
    0.90
     Death
    0.88
    claw
    0.84
    death
    0.84
    fighters
    0.83
     incarn
    0.83
    blow
    0.82
    fighter
    0.81
    guards
    0.79
    flies
    0.79
    Act Density 0.013%

    No Known Activations