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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.73
    ħĭ
    -0.67
    -+-+
    -0.63
    Cass
    -0.63
    Minor
    -0.62
     witches
    -0.62
     Pilgrim
    -0.61
     Shepard
    -0.61
     cradle
    -0.61
     Pear
    -0.60
    POSITIVE LOGITS
    ogan
    0.69
    verty
    0.66
    igor
    0.66
    ps
    0.64
    ayers
    0.64
    itated
    0.63
    fu
    0.63
    ca
    0.62
    itation
    0.62
    pps
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.