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

    Neuronpedia

    INDEX
    Explanations

    mentions of torture and interrogation practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intrig
    -0.16
    _blocking
    -0.15
    .blocks
    -0.15
    alker
    -0.15
    åĩĿ
    -0.14
    ois
    -0.14
     stalking
    -0.14
     Griff
    -0.14
    Traversal
    -0.14
    Cli
    -0.14
    POSITIVE LOGITS
     torture
    0.44
     Tort
    0.41
     TORT
    0.38
     tort
    0.34
     interrogation
    0.28
     tortured
    0.28
     interrog
    0.27
     detainees
    0.20
     detain
    0.20
     techniques
    0.19
    Act Density 0.021%

    No Known Activations