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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ſicht
    -1.00
    ſſung
    -0.96
    iſchen
    -0.95
    <unused74>
    -0.95
    <unused41>
    -0.94
    <unused51>
    -0.94
    <unused52>
    -0.94
    <unused23>
    -0.94
    <unused8>
    -0.94
    <unused14>
    -0.94
    POSITIVE LOGITS
    I
    0.36
    0
    0.32
    But
    0.30
    ，
    0.29
    SP
    0.29
    TP
    0.29
    My
    0.29
    Por
    0.28
    Will
    0.28
    Do
    0.28
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.