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

    Neuronpedia

    INDEX
    Explanations

    references to obedience and compliance with authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lomb
    -0.16
    .infinity
    -0.15
    olio
    -0.15
    elly
    -0.15
    Coal
    -0.15
    ãĤ
    -0.15
    /Table
    -0.15
     ÑĦÑĢан
    -0.14
     coal
    -0.14
    acob
    -0.14
    POSITIVE LOGITS
    inth
    0.16
    fully
    0.14
    .ls
    0.14
    ná
    0.14
     Kra
    0.14
    istra
    0.14
    amus
    0.13
    ť
    0.13
    arsers
    0.13
    ews
    0.13
    Act Density 0.061%

    No Known Activations