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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies or research citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.31
    Xna
    -0.30
     незавершена
    -0.29
    ondissement
    -0.29
    })$}
    -0.29
    ]}>
    -0.27
    })));
    -0.27
     Италијани
    -0.26
    >{@
    -0.26
    })*/
    -0.25
    POSITIVE LOGITS
    <unused52>
    0.79
    <unused79>
    0.78
    <unused21>
    0.77
    <unused16>
    0.77
    [@BOS@]
    0.77
    <unused68>
    0.77
    <unused14>
    0.77
    <unused28>
    0.77
    <unused8>
    0.77
    <unused3>
    0.77
    Act Density 0.215%

    No Known Activations