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

    Neuronpedia

    INDEX
    Explanations

    the presence of asterisks and associated formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colette
    -0.72
    lito
    -0.72
     Blak
    -0.71
     MTA
    -0.71
    albert
    -0.70
     Sally
    -0.70
     Nava
    -0.70
    mina
    -0.70
     Peres
    -0.69
     Raton
    -0.69
    POSITIVE LOGITS
     ¡¡
    1.09
    )**
    1.01
    (**
    0.99
     wikipagina
    0.99
    /****
    0.94
    ]**
    0.92
    ●●
    0.90
    kwargs
    0.89
    ¡¡
    0.87
    .**
    0.87
    Act Density 0.297%

    No Known Activations