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

    Neuronpedia

    INDEX
    Explanations

    indicators of strong emphasis or importance in a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ting
    -0.57
     parties
    -0.54
    isinstance
    -0.53
     block
    -0.52
    mati
    -0.51
     kem
    -0.51
     inc
    -0.50
     parti
    -0.49
    부
    -0.49
     下午
    -0.49
    POSITIVE LOGITS
     ↑
    0.93
    __(/*!
    0.89
    <bos>
    0.80
    uride
    0.77
    //
    0.73
    ])).
    0.72
    ]));
    0.68
     AppColors
    0.67
    ]))
    0.67
    WebVitals
    0.67
    Act Density 0.059%

    No Known Activations