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

    Neuronpedia

    INDEX
    Explanations

    references to interrogation and torture in a governmental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aar
    -0.14
    andom
    -0.14
    icros
    -0.13
    ãĥ³ãĥĹ
    -0.13
    oupon
    -0.13
    паÑĤ
    -0.13
     Consumers
    -0.13
     borough
    -0.13
    umer
    -0.13
    ommen
    -0.13
    POSITIVE LOGITS
     interrogation
    0.39
     torture
    0.39
     interrog
    0.37
     water
    0.31
     Tort
    0.30
     TORT
    0.30
     tort
    0.29
     CIA
    0.28
     techniques
    0.28
     tortured
    0.25
    Act Density 0.017%

    No Known Activations