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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atoria
    -0.29
    ered
    -0.29
    ABCDEFGHI
    -0.28
    amat
    -0.27
     fortified
    -0.27
    ABCDEFG
    -0.26
     squirt
    -0.26
     tart
    -0.25
    ETY
    -0.25
    ickey
    -0.25
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.27
     Launcher
    0.27
    witter
    0.25
    åīIJ
    0.25
    ä¸Ģ个éĹ®é¢ĺ
    0.25
    lv
    0.24
    ruc
    0.24
    å·¡èĪª
    0.24
     Gros
    0.24
    ä¸ĢåĪĢ
    0.24
    Act Density 0.005%

    No Known Activations

    This feature has no known activations.