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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     brid
    -0.66
     bet
    -0.64
     Coul
    -0.62
    jud
    -0.62
     groundwater
    -0.61
     reckon
    -0.60
    vers
    -0.60
     cohesion
    -0.60
     guild
    -0.59
     reper
    -0.58
    POSITIVE LOGITS
    ModLoader
    0.85
    rero
    0.75
     Alto
    0.75
    hetical
    0.71
     Moroc
    0.68
    heses
    0.68
     Soup
    0.67
    irez
    0.66
     Aires
    0.65
    ------------------------------------------------
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.