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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    راء
    -0.27
    picker
    -0.26
    èĵĿ
    -0.26
    hawks
    -0.25
    outs
    -0.25
    bite
    -0.25
    éģĤ
    -0.25
    åħīæĺİ
    -0.25
    rooms
    -0.24
    cast
    -0.24
    POSITIVE LOGITS
    æĵį
    0.28
    hma
    0.27
    .perform
    0.27
    èı½
    0.27
    çĹķ
    0.26
    ará
    0.25
    太é«ĺ
    0.24
    贯穿
    0.24
    xbd
    0.23
    forma
    0.23
    Act Density 0.006%

    No Known Activations

    This feature has no known activations.