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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _epochs
    -0.07
    .Go
    -0.07
     optimal
    -0.07
    人在
    -0.07
    .XPATH
    -0.07
     epid
    -0.07
     Machine
    -0.06
     ^=
    -0.06
    🅘
    -0.06
     Imper
    -0.06
    POSITIVE LOGITS
    畴
    0.08
    \"");↵
    0.07
    啪
    0.07
    	explicit
    0.07
    羧
    0.07
    lexport
    0.07
     Wroc
    0.07
    .`|`↵
    0.07
    屋里
    0.07
    nox
    0.07
    Act Density 0.040%

    No Known Activations