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

    Neuronpedia

    INDEX
    Explanations

    references to control and compliance within societal or governmental structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ť
    -0.15
    stub
    -0.15
    ibold
    -0.15
    irq
    -0.15
     steward
    -0.14
    .problem
    -0.14
    oui
    -0.14
    _IRQ
    -0.13
    _typ
    -0.13
    ráf
    -0.13
    POSITIVE LOGITS
     submit
    0.19
     submission
    0.19
     bow
    0.19
    bow
    0.18
     toe
    0.18
     involuntary
    0.17
     compliance
    0.17
     Compliance
    0.17
    Submit
    0.17
     conform
    0.17
    Act Density 0.235%

    No Known Activations