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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     locals
    -0.70
     pse
    -0.68
     Chatt
    -0.67
     deleg
    -0.67
    代
    -0.65
     entitle
    -0.64
     idle
    -0.63
     lame
    -0.63
     Daisy
    -0.63
     secretaries
    -0.62
    POSITIVE LOGITS
    TOR
    0.89
    OSP
    0.81
    EMENT
    0.72
    ICE
    0.70
    cel
    0.70
    MpServer
    0.69
    ulla
    0.67
    UTF
    0.67
    ETF
    0.66
    EngineDebug
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.