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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mellon
    -0.77
     MPG
    -0.72
    miah
    -0.69
    redit
    -0.66
     bottleneck
    -0.63
    itability
    -0.62
    anyon
    -0.61
    ullivan
    -0.60
     DAV
    -0.60
    lde
    -0.59
    POSITIVE LOGITS
    olson
    0.83
    iem
    0.75
    yers
    0.69
    }}}
    0.68
    天
    0.68
    ignant
    0.65
    tumblr
    0.65
    EMS
    0.64
     remedy
    0.64
    zai
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.