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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    表达
    0.48
    OCITY
    0.47
     트
    0.46
     прида
    0.44
     좋은
    0.43
     Oceania
    0.43
     AppBsky
    0.43
    vout
    0.42
     극한
    0.42
     hexa
    0.41
    POSITIVE LOGITS
    Insurance
    0.45
     Medicare
    0.42
    стра
    0.42
    Champions
    0.41
    ابه
    0.40
    師
    0.40
    Medicare
    0.40
    بر
    0.39
     learned
    0.39
    Bay
    0.39
    Act Density 0.001%

    No Known Activations