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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    四肢
    -0.07
     evil
    -0.07
    眦
    -0.07
    跪
    -0.07
    .trace
    -0.07
     hakk
    -0.06
    gf
    -0.06
     '--
    -0.06
     delt
    -0.06
    .BOLD
    -0.06
    POSITIVE LOGITS
    的进步
    0.07
     менее
    0.07
    sters
    0.06
    rition
    0.06
    Action
    0.06
     Expansion
    0.06
    mus
    0.06
    _rules
    0.06
    tection
    0.06
     Thompson
    0.06
    Act Density 0.000%

    No Known Activations