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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Monte
    -0.76
     Loren
    -0.73
     Slim
    -0.72
    ofi
    -0.69
     Logic
    -0.68
     Mahjong
    -0.68
     Commando
    -0.68
     SAR
    -0.67
     Bret
    -0.66
    FG
    -0.66
    POSITIVE LOGITS
    ottesville
    0.77
    unte
    0.77
    wage
    0.76
    âĢ¦]
    0.75
    âĢ¦)
    0.75
    bugs
    0.73
    bleacher
    0.68
    office
    0.67
    upt
    0.66
    undo
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.