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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    osi
    -0.06
    a
    -0.06
     spell
    -0.06
     surprisingly
    -0.06
     corp
    -0.06
    anio
    -0.06
     patches
    -0.06
     something
    -0.05
     stealth
    -0.05
    [--
    -0.05
    POSITIVE LOGITS
    pek
    0.09
     gerekmektedir
    0.08
    esktop
    0.08
    á»Ļc
    0.08
    едак
    0.08
    iator
    0.08
    ocab
    0.08
    ocoder
    0.07
    ROUGH
    0.07
    ëī´
    0.07
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.