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

    Neuronpedia

    INDEX
    Explanations

    terms related to interrogation and torture in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argon
    -0.15
     Griff
    -0.15
    hasOne
    -0.15
    ères
    -0.14
    лиÑĨ
    -0.14
    eru
    -0.14
    ervas
    -0.14
    arness
    -0.14
     intrig
    -0.14
    èĥİ
    -0.14
    POSITIVE LOGITS
     torture
    0.43
     Tort
    0.42
     TORT
    0.39
     tort
    0.34
     interrogation
    0.32
     interrog
    0.31
     tortured
    0.28
     techniques
    0.21
     detainees
    0.20
     CIA
    0.20
    Act Density 0.016%

    No Known Activations