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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "death"

    oai_token-act-pair · gpt-3.5-turbo

    references to death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CN
    -0.85
    Cola
    -0.82
    ECA
    -0.82
    Avg
    -0.79
    ĸļ
    -0.78
    EEK
    -0.78
    OPER
    -0.74
    atters
    -0.74
    soType
    -0.74
     CLIENT
    -0.72
    POSITIVE LOGITS
    blow
    1.06
     toll
    0.98
    stroke
    0.97
    guard
    0.90
    match
    0.89
    touch
    0.88
    fish
    0.87
    adder
    0.85
    guards
    0.83
    hound
    0.83
    Act Density 0.039%

    No Known Activations