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

    Neuronpedia

    INDEX
    Explanations

    specific structural elements and formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.73
     itſelf
    -0.70
     виправивши
    -0.69
     chré
    -0.68
     quelcon
    -0.68
     humaines
    -0.68
     firſt
    -0.67
     Monfieur
    -0.67
     sexuales
    -0.67
     GoogleFonts
    -0.66
    POSITIVE LOGITS
    hirt
    0.58
    '))
    0.52
    virons
    0.50
     core
    0.49
     Kam
    0.49
     Core
    0.48
    asiness
    0.48
    ))));
    0.47
    )))
    0.47
     Fe
    0.47
    Act Density 1.489%

    No Known Activations