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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kefeller
    -0.73
     Bulg
    -0.73
    kernel
    -0.68
    owment
    -0.68
     Kissinger
    -0.68
    ospace
    -0.63
    oves
    -0.62
     Rockefeller
    -0.61
     TRUMP
    -0.61
     Slime
    -0.60
    POSITIVE LOGITS
    Pass
    0.75
    vertisements
    0.67
    Side
    0.64
    nant
    0.64
     elbows
    0.62
    Applic
    0.61
    én
    0.60
     unintention
    0.60
    Jet
    0.59
    raviolet
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.