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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     indo
    -0.96
     Frankenstein
    -0.70
    ible
    -0.69
     membr
    -0.66
    ),"
    -0.65
     Frem
    -0.65
     fossil
    -0.65
     acad
    -0.65
    ——
    -0.64
     Trojan
    -0.63
    POSITIVE LOGITS
    lication
    0.83
    externalActionCode
    0.79
    miah
    0.79
    wcs
    0.78
    ipes
    0.74
     CoC
    0.73
    netflix
    0.73
    meg
    0.72
    Exit
    0.72
    andise
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.