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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    enegger
    -0.76
    illions
    -0.75
    ciating
    -0.72
    fortunately
    -0.71
     neglig
    -0.68
     releasing
    -0.66
    pressed
    -0.65
     outweigh
    -0.63
     hars
    -0.63
    rawdownloadcloneembedreportprint
    -0.62
    POSITIVE LOGITS
    itute
    0.73
     Pose
    0.72
     Weaver
    0.70
    meric
    0.67
     Rue
    0.67
     CG
    0.66
     Grain
    0.66
    izabeth
    0.65
    laus
    0.64
     Compass
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.