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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -=
    -0.07
     Iceland
    -0.07
     Failed
    -0.07
     Rooney
    -0.07
     tv
    -0.06
    罶
    -0.06
     lends
    -0.06
    (.
    -0.06
     loses
    -0.06
     substitutions
    -0.06
    POSITIVE LOGITS
     ráp
    0.07
     shemale
    0.07
    keletal
    0.07
    킵
    0.07
    מאה
    0.07
     packaged
    0.07
    Scaler
    0.07
     questa
    0.07
    .callback
    0.06
     Global
    0.06
    Act Density 0.005%

    No Known Activations