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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    m
    1.16
    k
    1.07
    n
    1.06
    c
    0.95
    id
    0.92
    em
    0.91
    j
    0.91
    r
    0.90
    p
    0.90
    on
    0.89
    POSITIVE LOGITS
    Mutable
    0.80
    ような
    0.78
     pencils
    0.76
     believable
    0.76
    們
    0.75
     unwanted
    0.74
     அதிசயங்கள்
    0.74
     티
    0.74
    KeyValuePair
    0.74
     SIMPLE
    0.73
    Act Density 0.000%

    No Known Activations