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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oppers
    -0.78
    ptions
    -0.73
    akeru
    -0.71
    thia
    -0.71
    illance
    -0.70
    uddenly
    -0.70
    gregation
    -0.69
    lly
    -0.68
    ancial
    -0.68
    lication
    -0.68
    POSITIVE LOGITS
     Burk
    0.70
    -)
    0.68
    ãĤ´ãĥ³
    0.67
     Panc
    0.66
     Brooke
    0.64
     Rings
    0.64
     Elev
    0.63
     Oscar
    0.62
    MY
    0.62
     Herb
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.