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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Predict
    1.00
     Dedicated
    0.99
     Expensive
    0.98
     Unlike
    0.98
     Delicate
    0.96
     Domain
    0.95
     Discrimin
    0.93
     Keyboard
    0.93
     Limb
    0.92
     Within
    0.90
    POSITIVE LOGITS
    h
    0.94
    v
    0.85
    sa
    0.84
    стро
    0.84
    sø
    0.81
    tr
    0.80
    rze
    0.79
    Stephen
    0.79
    SK
    0.77
    س
    0.76
    Act Density 0.000%

    No Known Activations