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

    Neuronpedia

    INDEX
    Explanations

    themes related to questioning authority and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itag
    -0.15
    707
    -0.14
    lá
    -0.14
    ungs
    -0.14
    UMP
    -0.14
    edback
    -0.14
    eya
    -0.14
    ductor
    -0.14
    inan
    -0.14
    ston
    -0.13
    POSITIVE LOGITS
     convention
    0.25
     conventional
    0.25
     authority
    0.25
     establishment
    0.21
     established
    0.21
     traditional
    0.20
     establishments
    0.20
     Establishment
    0.20
     conventions
    0.19
    /question
    0.19
    Act Density 0.244%

    No Known Activations