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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rongh
    -0.73
    ioxid
    -0.72
    erves
    -0.70
    ãĤ¤ãĥĪ
    -0.68
    abouts
    -0.66
    ablishment
    -0.66
     Rosenthal
    -0.65
     Moss
    -0.65
     IRA
    -0.62
     estates
    -0.62
    POSITIVE LOGITS
    ama
    0.66
    urnal
    0.64
    maid
    0.63
    toe
    0.62
    lav
    0.62
    unction
    0.62
    aid
    0.62
    isively
    0.61
    adic
    0.61
    Äĩ
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.