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

    Neuronpedia

    INDEX
    Explanations

    mentions of torture in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to torture and related abuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.80
    ership
    -0.75
    ijk
    -0.65
    soDeliveryDate
    -0.65
    arger
    -0.65
    ovember
    -0.63
    nect
    -0.63
     explan
    -0.63
    utsch
    -0.63
    Merit
    -0.62
    POSITIVE LOGITS
     torture
    0.98
     tortured
    0.77
     captives
    0.75
     tactics
    0.73
    imony
    0.73
     detainees
    0.72
     confinement
    0.72
    apons
    0.70
     torment
    0.70
    rs
    0.69
    Act Density 0.021%

    No Known Activations