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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    usha
    -0.75
     DRAG
    -0.72
     ANG
    -0.72
     Dawkins
    -0.71
     Dw
    -0.70
     Feinstein
    -0.70
    icter
    -0.69
     Osw
    -0.69
     Mara
    -0.68
     Hezbollah
    -0.65
    POSITIVE LOGITS
    abit
    0.77
    rylic
    0.70
    Found
    0.68
    Liter
    0.67
    mallow
    0.66
    ilion
    0.65
    pei
    0.65
    System
    0.65
    obo
    0.62
    cade
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.