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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pard
    -0.70
    \/\/
    -0.69
    avascript
    -0.65
    SPONSORED
    -0.65
     mentors
    -0.65
    Ü
    -0.64
     Hamm
    -0.64
     indo
    -0.63
     Rudd
    -0.63
     bonded
    -0.61
    POSITIVE LOGITS
    ¥µ
    0.85
     FANTASY
    0.73
    usual
    0.72
    uch
    0.70
    £ı
    0.70
     Idol
    0.69
     agency
    0.69
    ijk
    0.68
     LTD
    0.68
    iterator
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.