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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cade
    -0.74
    ables
    -0.71
    nec
    -0.70
     Velvet
    -0.66
    vel
    -0.65
     catalogue
    -0.65
    ults
    -0.65
    ele
    -0.64
    arth
    -0.62
     curtain
    -0.61
    POSITIVE LOGITS
    ľ
    1.14
    ĸ
    0.87
    ħ
    0.83
    ongyang
    0.82
    ¤
    0.79
    Reviewer
    0.78
    ãĤ´ãĥ³
    0.75
    ļ
    0.74
    ŃĶ
    0.74
    backer
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.