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

    Neuronpedia

    INDEX
    Explanations

    references to death and the death penalty

    oai_token-act-pair · gpt-3.5-turbo

    references to the death penalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CN
    -0.78
    umar
    -0.75
    Cola
    -0.75
    MN
    -0.73
    ECA
    -0.72
    Americ
    -0.72
    EEK
    -0.71
    ĸļ
    -0.69
    Avg
    -0.67
    æ©Ł
    -0.65
    POSITIVE LOGITS
    blow
    1.04
     toll
    0.97
    guard
    0.95
    adder
    0.94
    stroke
    0.94
    locked
    0.93
    match
    0.93
    trap
    0.91
     thro
    0.88
    bed
    0.88
    Act Density 0.049%

    No Known Activations