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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    dbl
    -0.07
    ,dim
    -0.07
    ,last
    -0.06
    耐磨
    -0.06
    _RADIUS
    -0.06
    领导小组
    -0.06
     fantasy
    -0.06
    firstname
    -0.06
     Senator
    -0.06
     threaten
    -0.06
    POSITIVE LOGITS
     Hyderabad
    0.08
    !</
    0.08
     Crypt
    0.07
    ערכת
    0.07
    yling
    0.07
     Roku
    0.07
     synchron
    0.06
     disco
    0.06
     sourcing
    0.06
     wys
    0.06
    Act Density 0.119%

    No Known Activations