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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    enson
    -0.86
     confir
    -0.75
    dh
    -0.70
    auld
    -0.69
    iffe
    -0.68
    strom
    -0.67
    scl
    -0.65
    iazep
    -0.62
    ersen
    -0.62
    erson
    -0.62
    POSITIVE LOGITS
     Nose
    0.73
     Toad
    0.70
    76561
    0.67
     Springer
    0.66
     Rican
    0.66
     Banana
    0.65
     invis
    0.64
     Favor
    0.64
    oret
    0.62
     Toast
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.