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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     asses
    -0.07
    ↵                    ↵
    -0.07
    -Israel
    -0.07
     train
    -0.07
    弟子
    -0.07
     entertain
    -0.06
    ima
    -0.06
    䲟
    -0.06
     Irene
    -0.06
    >J
    -0.06
    POSITIVE LOGITS
    parts
    0.07
    CHANNEL
    0.07
     autour
    0.07
    quel
    0.07
     CPI
    0.07
    vl
    0.07
    \\\
    0.07
    اخ
    0.07
    allel
    0.07
    üs
    0.07
    Act Density 0.023%

    No Known Activations