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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Presumably
    1.02
     Importantly
    0.99
     presumably
    0.96
     Somehow
    0.95
     (~
    0.93
     Typically
    0.92
     모습
    0.92
     상당히
    0.89
    だけでなく
    0.89
     뿐
    0.89
    POSITIVE LOGITS
    delayed
    0.87
    split
    0.81
     ghost
    0.80
     estoppel
    0.79
     delayed
    0.78
     rebound
    0.77
    saturation
    0.75
     vampire
    0.75
    environmental
    0.74
     falsa
    0.74
    Act Density 1.731%

    No Known Activations