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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olla
    -0.71
    adal
    -0.71
     fri
    -0.67
     merry
    -0.65
     derog
    -0.65
    rog
    -0.64
     GMT
    -0.63
     decom
    -0.63
     provisional
    -0.62
     Reno
    -0.62
    POSITIVE LOGITS
    ube
    0.69
     VIDEOS
    0.66
    nergy
    0.64
    ACTED
    0.63
    APS
    0.62
    System
    0.62
     Tuls
    0.61
    metics
    0.61
    ATS
    0.61
    cht
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.