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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Accessory
    -0.78
    TPPStreamerBot
    -0.78
    ALS
    -0.74
     perish
    -0.72
    usual
    -0.71
    CHQ
    -0.69
    orks
    -0.67
    ichick
    -0.67
    ...]
    -0.67
     scrut
    -0.66
    POSITIVE LOGITS
     Franch
    0.65
     wrapper
    0.63
     Directions
    0.62
     reven
    0.62
     himself
    0.61
    marks
    0.60
     Himself
    0.58
     Fri
    0.57
     Counsel
    0.57
     knowing
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.