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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    idlo
    -0.17
    haf
    -0.17
    edom
    -0.16
    idth
    -0.15
    605
    -0.15
    riers
    -0.15
    upert
    -0.14
    ajÄħ
    -0.14
    achat
    -0.14
    itespace
    -0.14
    POSITIVE LOGITS
     Wire
    0.23
     wire
    0.22
    wire
    0.21
    Wire
    0.21
     toe
    0.21
     coast
    0.17
     yard
    0.17
     deep
    0.15
    osed
    0.15
     Toe
    0.15
    Act Density 0.017%

    No Known Activations