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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of executions

    oai_token-act-pair · gpt-3.5-turbo

    references to execution or capital punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tire
    -0.68
    ijn
    -0.66
     Boh
    -0.66
     NR
    -0.64
    thora
    -0.64
    Fi
    -0.64
     Greater
    -0.63
     Tec
    -0.63
     Dew
    -0.63
     ECO
    -0.62
    POSITIVE LOGITS
     executions
    0.97
    eering
    0.93
    locks
    0.92
     execution
    0.91
     inmate
    0.88
    icts
    0.85
     execute
    0.83
    eers
    0.80
     executes
    0.79
     executed
    0.77
    Act Density 0.018%

    No Known Activations