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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pendapat
    0.51
     arbet
    0.50
     ungg
    0.48
     deference
    0.47
     workbench
    0.47
     exist
    0.47
     pueblos
    0.47
     húmed
    0.47
    :
    0.47
     fungi
    0.47
    POSITIVE LOGITS
    ੭
    0.48
    Influ
    0.46
    ❱
    0.46
    illi
    0.45
     یا
    0.45
    גד
    0.45
     SISO
    0.45
    وي
    0.44
    Pf
    0.44
    気分
    0.44
    Act Density 0.001%

    No Known Activations