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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     warships
    1.00
     surveyed
    1.00
     averse
    0.98
     estrogens
    0.98
     despise
    0.94
    ри
    0.94
     headwinds
    0.94
     huddled
    0.93
     refute
    0.92
    들이
    0.91
    POSITIVE LOGITS
    i
    1.69
    e
    1.57
    f
    1.30
    n
    1.27
    iš
    1.26
    s
    1.22
    ド
    1.20
    es
    1.15
    ে
    1.15
    er
    1.13
    Act Density 0.001%

    No Known Activations