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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    RP
    -0.71
    ._
    -0.68
    imum
    -0.68
    Overall
    -0.66
    Increased
    -0.66
    (_
    -0.66
    Sen
    -0.63
    CAR
    -0.62
    GV
    -0.62
    ï¸ı
    -0.61
    POSITIVE LOGITS
    etooth
    0.75
    itri
    0.72
     eleph
    0.69
     wom
    0.68
    cms
    0.67
    ipel
    0.67
     ropes
    0.65
     bom
    0.63
    tainment
    0.63
    mouth
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.