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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     yeast
    -0.08
    inear
    -0.08
    两边
    -0.08
    文案
    -0.07
    דיו
    -0.07
    Hang
    -0.07
     liner
    -0.07
    density
    -0.07
    (':',
    -0.07
     cheesy
    -0.07
    POSITIVE LOGITS
     iPhone
    0.10
     aku
    0.07
    iPhone
    0.07
    برج
    0.07
     שקיבל
    0.07
     Eins
    0.07
    igt
    0.07
     October
    0.07
    小时候
    0.06
    درجة
    0.06
    Act Density 0.005%

    No Known Activations