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

    Neuronpedia

    INDEX
    Explanations

    mentions of blood

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amend
    -0.86
    awaru
    -0.75
    IX
    -0.71
     Spac
    -0.71
     Lank
    -0.70
     VIDEOS
    -0.69
    ECH
    -0.67
    VICE
    -0.64
    acle
    -0.62
    cffffcc
    -0.62
    POSITIVE LOGITS
    thirst
    1.52
    bath
    1.31
    hound
    1.28
    stained
    1.27
    lust
    1.20
    shed
    1.14
    lines
    1.12
     thirsty
    0.97
    shot
    0.97
    spl
    0.96
    Act Density 0.044%

    No Known Activations