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

    Neuronpedia

    INDEX
    Explanations

    mentions of division and divisiveness in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.16
    riba
    -0.15
    ãģıãĤī
    -0.15
    entai
    -0.14
     nghiá»ĩp
    -0.14
    awning
    -0.14
    hiba
    -0.14
    ulis
    -0.14
    .Companion
    -0.14
    idth
    -0.14
    POSITIVE LOGITS
     polar
    0.20
     polarization
    0.20
    pel
    0.15
    between
    0.15
     Between
    0.15
     overhe
    0.14
     differences
    0.14
     between
    0.14
     BETWEEN
    0.14
     cert
    0.14
    Act Density 0.133%

    No Known Activations