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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions related to nearest values and comparisons in a dataset

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ivelany
    -0.52
    ChildScrollView
    -0.47
    Tembelea
    -0.47
    rentiel
    -0.45
    olymer
    -0.45
    ]);
    -0.43
    metrist
    -0.43
    }]);
    -0.43
    </em>
    -0.42
    ]))
    -0.42
    POSITIVE LOGITS
    dafx
    0.75
    
    0.75
    ">//
    0.69
    intios
    0.66
     themſelves
    0.63
    الحياه
    0.63
    Tē
    0.62
     ſever
    0.61
     تضيفلها
    0.61
    олові
    0.60
    Act Density 0.015%

    No Known Activations