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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.82
     DI
    -0.73
    ãĥ£
    -0.73
    ↵Âł
    -0.69
    æ©
    -0.68
     AX
    -0.68
     MUST
    -0.67
     Marion
    -0.66
     ILCS
    -0.66
    STON
    -0.65
    POSITIVE LOGITS
    opian
    1.01
    onymous
    0.94
    hemer
    0.89
    wich
    0.86
    ighth
    0.83
    ucle
    0.80
    verend
    0.78
    oub
    0.75
    rompt
    0.75
    chid
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.