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

    Neuronpedia

    INDEX
    Explanations

    words related to torture and suffering

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hitman
    -0.70
     donor
    -0.67
    ··
    -0.64
    itably
    -0.64
    lihood
    -0.62
    ity
    -0.62
     Hung
    -0.59
     Conservative
    -0.57
     Leone
    -0.57
     assumption
    -0.57
    POSITIVE LOGITS
    urous
    1.64
    urers
    1.46
    uring
    1.46
    ures
    1.44
    ured
    1.38
    orial
    1.32
    oise
    1.21
    urable
    1.21
    urer
    1.19
    eur
    1.09
    Act Density 0.162%

    No Known Activations