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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	txt
    -0.07
    POWER
    -0.07
     kep
    -0.07
    yum
    -0.07
     charming
    -0.07
     처
    -0.06
    .ship
    -0.06
    .Butter
    -0.06
    马刺
    -0.06
    又被
    -0.06
    POSITIVE LOGITS
    /D
    0.07
    agos
    0.07
    分别
    0.07
    Repair
    0.06
    column
    0.06
    ichael
    0.06
    pause
    0.06
    metadata
    0.06
    conomics
    0.06
    rogen
    0.06
    Act Density 0.023%

    No Known Activations