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

    Neuronpedia

    INDEX
    Explanations

    the words associated with the term "Dead" with varying degrees of intensity in activation

    oai_token-act-pair · gpt-3.5-turbo

    references to "Dead" associated with various contexts, particularly in titles and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.90
    anwhile
    -0.81
    orney
    -0.78
    ickr
    -0.76
    efully
    -0.73
    uration
    -0.68
    unity
    -0.66
     REPL
    -0.66
    FFFF
    -0.65
    aunder
    -0.65
    POSITIVE LOGITS
     Dead
    1.24
    Dead
    1.00
     Alive
    0.91
     DEAD
    0.88
    dead
    0.87
    spin
    0.85
    pool
    0.85
    liest
    0.84
     Corpse
    0.82
    bag
    0.81
    Act Density 0.009%

    No Known Activations