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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ⾨
    -0.08
     Daniel
    -0.08
    して
    -0.07
    	address
    -0.07
     Reno
    -0.07
     describes
    -0.07
     touched
    -0.07
     japanese
    -0.06
     הנאשם
    -0.06
     Después
    -0.06
    POSITIVE LOGITS
    _attention
    0.07
     singular
    0.07
     pls
    0.07
    _ROLE
    0.07
    _UUID
    0.07
    关口
    0.07
    _WH
    0.07
    Ù
    0.07
    Merge
    0.06
    hop
    0.06
    Act Density 0.000%

    No Known Activations