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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    obyl
    -0.74
    KNOWN
    -0.67
    yk
    -0.66
    atform
    -0.65
     Yam
    -0.63
    Pear
    -0.63
    zn
    -0.62
     Kore
    -0.62
     Kats
    -0.61
    Kal
    -0.60
    POSITIVE LOGITS
    xual
    0.82
    ongevity
    0.74
    rule
    0.72
     Clement
    0.69
    oire
    0.69
    theless
    0.68
    udic
    0.66
    ample
    0.66
    ETHOD
    0.65
    wart
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.