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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    opter
    -0.77
    ĸļ
    -0.75
    iler
    -0.72
    hari
    -0.71
    ovies
    -0.71
    ilers
    -0.70
    enforcement
    -0.68
    eki
    -0.67
    emer
    -0.67
    rake
    -0.65
    POSITIVE LOGITS
     lia
    0.75
     aides
    0.65
     remem
    0.65
     plea
    0.64
     impunity
    0.63
     links
    0.63
    stre
    0.63
     mood
    0.62
     closest
    0.61
     hints
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.