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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Household
    0.55
     Private
    0.47
     investigate
    0.46
     Martha
    0.46
    *;
    0.46
     Whitley
    0.45
     vice
    0.45
    hold
    0.45
     household
    0.43
     P
    0.42
    POSITIVE LOGITS
     outflows
    0.50
    eraient
    0.50
     appare
    0.48
    凪
    0.48
    teau
    0.45
    ลูกค้า
    0.45
    istiche
    0.44
    잉
    0.44
    ขาย
    0.44
     paradigms
    0.44
    Act Density 0.001%

    No Known Activations