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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    blocking
    -0.75
    limit
    -0.71
    lander
    -0.70
     dipping
    -0.69
     forgiving
    -0.65
     Emin
    -0.64
    ¯
    -0.64
    yip
    -0.63
     tagging
    -0.62
    ilee
    -0.61
    POSITIVE LOGITS
    MpServer
    0.73
    姫
    0.72
     Aerospace
    0.70
    OME
    0.69
    IRO
    0.69
    riott
    0.67
    ¬¼
    0.67
    mL
    0.66
    rawdownloadcloneembedreportprint
    0.64
    GAN
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.