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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ALL
    -0.67
    mission
    -0.66
     impeachment
    -0.66
    Reviewer
    -0.65
    flags
    -0.64
    lag
    -0.64
    nil
    -0.63
     ))
    -0.63
    mbuds
    -0.62
    gress
    -0.62
    POSITIVE LOGITS
     Painter
    0.78
    teenth
    0.76
     Nou
    0.75
    hner
    0.75
    hower
    0.73
    ascript
    0.71
    eson
    0.71
     charism
    0.68
    Cra
    0.68
     Winc
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.