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

    Neuronpedia

    INDEX
    Explanations

    references to coding structure and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (__('
    -0.68
     Weiss
    -0.64
     Appel
    -0.62
    getJSONObject
    -0.60
     Thacker
    -0.60
     FontWeight
    -0.59
     Zweiten
    -0.58
    lobo
    -0.58
    EMOS
    -0.57
    IALES
    -0.57
    POSITIVE LOGITS
    ↵
    1.27
    ↵↵
    1.18
    </tr>
    1.15
    <eos>
    1.15
    ())));
    0.95
    })).
    0.94
    ])));
    0.91
    ↵↵↵
    0.90
     }));
    0.88
    ())))
    0.87
    Act Density 0.373%

    No Known Activations