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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ources
    -0.73
    olars
    -0.65
    fal
    -0.65
    auga
    -0.64
     disbanded
    -0.62
     Stard
    -0.61
    plex
    -0.61
     accur
    -0.60
     torch
    -0.60
     BST
    -0.59
    POSITIVE LOGITS
    Sanders
    0.87
     Pref
    0.74
     Mubarak
    0.71
    é¾į
    0.71
    Democratic
    0.70
    Connector
    0.68
    wear
    0.66
    ãĥ¼ãĥĨ
    0.65
     Teach
    0.65
    vana
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.