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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <eos>
    1.91
    ↵↵↵↵
    1.72
    ↵↵↵↵↵
    1.69
    ↵↵↵
    1.60
    ↵↵↵↵↵↵
    1.49
    ↵↵
    1.47
    ↵↵↵↵↵↵↵↵↵
    1.45
    <start_of_image>
    1.44
    ↵↵↵↵↵↵↵↵
    1.44
    ].”
    1.41
    POSITIVE LOGITS
    ﹔
    0.68
    ikko
    0.67
    chae
    0.60
     دائو
    0.59
    tte
    0.59
     allocations
    0.59
    مارات
    0.58
     obviamente
    0.58
    뻤
    0.58
    늠
    0.57
    Act Density 2.115%

    No Known Activations