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

    Neuronpedia

    INDEX
    Explanations

    references to political or social affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yı
    -0.67
    Logan
    -0.65
    odenal
    -0.62
    ote
    -0.61
    lote
    -0.61
    ฎ
    -0.60
    DeleteMapping
    -0.60
    ../../
    -0.60
    onte
    -0.59
    rarr
    -0.59
    POSITIVE LOGITS
     affairs
    3.31
     Affairs
    3.23
     AFFAIRS
    2.85
     Affair
    2.44
     affair
    2.43
    Aff
    1.76
     affaires
    1.74
     affaire
    1.67
    aff
    1.47
     Affaires
    1.46
    Act Density 0.075%

    No Known Activations