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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hill
    0.49
     We
    0.48
     Begin
    0.48
     Tex
    0.46
     Grove
    0.45
     Grou
    0.43
     Save
    0.43
     Learn
    0.43
     Go
    0.42
     Third
    0.42
    POSITIVE LOGITS
     تامین
    0.55
    ді
    0.54
    ಒ
    0.52
    𝘱
    0.52
    ڈ
    0.52
    𝘸
    0.52
    government
    0.51
    ஒரு
    0.51
     nghĩ
    0.50
    bub
    0.50
    Act Density 0.000%

    No Known Activations