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

    Neuronpedia

    INDEX
    Explanations

    code structure elements and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FontWeight
    -0.74
    ENEFITS
    -0.73
    ÁG
    -0.72
    VERTISEMENT
    -0.72
     SUDOC
    -0.71
    arino
    -0.71
    EMOS
    -0.70
    CHREIB
    -0.69
    USTOM
    -0.69
    Câ
    -0.69
    POSITIVE LOGITS
    ↵
    1.67
    ↵↵
    1.39
    </tr>
    1.38
    <eos>
    1.30
    ↵↵↵
    1.11
    ())));
    0.97
    ↵↵↵↵
    0.95
    }));
    0.94
    ])));
    0.94
    ↵↵↵↵↵
    0.93
    Act Density 1.167%

    No Known Activations