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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ospons
    -0.75
    \/\/
    -0.74
    enf
    -0.73
    ammy
    -0.73
    hair
    -0.72
    picking
    -0.70
    oval
    -0.70
    enh
    -0.70
    urous
    -0.68
    offer
    -0.68
    POSITIVE LOGITS
     dividing
    0.69
     divides
    0.69
     separates
    0.66
     divide
    0.63
     LEVEL
    0.61
    nown
    0.59
     multiplied
    0.59
    ITH
    0.58
     Calls
    0.57
     Rowling
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.