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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    뮌
    -0.08
    嘶
    -0.07
    aleigh
    -0.07
    메
    -0.07
    傑
    -0.07
    吞
    -0.07
    换来
    -0.07
     Return
    -0.07
    Prince
    -0.06
     lif
    -0.06
    POSITIVE LOGITS
     ROOT
    0.07
     missions
    0.07
     blat
    0.07
     biting
    0.07
     coating
    0.07
     crystal
    0.06
     riding
    0.06
     request
    0.06
    藻
    0.06
     trig
    0.06
    Act Density 0.026%

    No Known Activations