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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    zb
    -0.70
    STAR
    -0.68
    gas
    -0.64
     nep
    -0.64
    word
    -0.62
    ''.
    -0.61
    Democrats
    -0.61
    '>
    -0.61
    gui
    -0.60
     Corpor
    -0.60
    POSITIVE LOGITS
    emouth
    0.76
     Levant
    0.69
    ç«
    0.69
    lus
    0.66
     BDS
    0.66
    ulent
    0.65
     Beetle
    0.65
    FAULT
    0.65
     impunity
    0.64
     Raf
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.