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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orah
    -0.86
    ysis
    -0.75
     Alive
    -0.71
    resp
    -0.66
    ather
    -0.66
    thro
    -0.65
    ilon
    -0.65
     Sham
    -0.64
    bon
    -0.64
    ona
    -0.63
    POSITIVE LOGITS
    iets
    0.82
     pesky
    0.73
     fateful
    0.72
     culminated
    0.70
    milo
    0.70
     arose
    0.69
     carbohyd
    0.69
     destro
    0.69
     settles
    0.68
    minecraft
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.