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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ּוֹ
    -1.17
    ؘ
    -1.09
    וֹ
    -1.06
     concerning
    -1.04
     system
    -1.03
     strategy
    -1.03
     bonitas
    -1.02
    =$_
    -1.02
     prevention
    -1.02
     reliability
    -1.01
    POSITIVE LOGITS
     الى
    1.00
     μεγαλ
    0.94
    瞠
    0.92
    や
    0.91
    ceral
    0.91
     Generous
    0.90
     сахара
    0.90
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.90
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.88
     Kue
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.