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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arch
    -0.07
     Og
    -0.07
    Berry
    -0.07
    有效的
    -0.07
     Oz
    -0.07
     books
    -0.07
    rock
    -0.07
    dj
    -0.07
     Ange
    -0.07
    alles
    -0.07
    POSITIVE LOGITS
     side
    0.07
     behaved
    0.07
    孩子
    0.07
    :white
    0.07
    侧
    0.07
    顺着
    0.07
     safer
    0.07
    洁白
    0.07
     thugs
    0.07
    _BIT
    0.07
    Act Density 0.047%

    No Known Activations