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

    Neuronpedia

    INDEX
    Explanations

    themes related to power dynamics and the influence of ruling classes in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tick
    -0.16
    isson
    -0.16
    onica
    -0.15
     tick
    -0.15
     Bour
    -0.15
     Tick
    -0.14
    ERRU
    -0.14
    uzzi
    -0.14
    icus
    -0.14
    лиÑĨ
    -0.14
    POSITIVE LOGITS
    /power
    0.19
     control
    0.18
    (power
    0.18
    (control
    0.17
     power
    0.17
    control
    0.17
    power
    0.16
     influence
    0.15
    -control
    0.15
     Influence
    0.15
    Act Density 0.183%

    No Known Activations