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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anyone
    1.15
    ма
    1.08
    ה
    1.03
    er
    1.03
    <
    1.03
    im
    0.97
    do
    0.95
     pu
    0.94
     Anyone
    0.94
    なります
    0.93
    POSITIVE LOGITS
    ционными
    1.40
    ционных
    1.39
     inextricably
    1.37
     leisurely
    1.36
     lâu
    1.36
     degassing
    1.33
    ytocin
    1.33
    arently
    1.32
    lications
    1.30
     $(`.
    1.30
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.