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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     explain
    0.40
     explains
    0.35
     clearly
    0.34
     proffered
    0.34
     Goldsmith
    0.34
    ynski
    0.33
     unint
    0.32
    হেল
    0.32
     actu
    0.32
     materialism
    0.31
    POSITIVE LOGITS
    au
    0.36
    ()}.
    0.35
    à
    0.34
    zte
    0.33
     arrivée
    0.33
    ato
    0.32
    克的
    0.32
    uria
    0.32
    uncur
    0.32
    atz
    0.31
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.