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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     melted
    1.05
     melatonin
    1.05
     truncation
    1.03
    🌓
    1.02
     desorption
    1.02
    ǫ
    1.01
     gratification
    1.01
    🌒
    1.01
    <0x8C>
    1.01
    🌘
    1.00
    POSITIVE LOGITS
    ts
    1.05
    な
    1.02
    ters
    0.97
    ting
    0.93
    the
    0.91
    to
    0.88
    ну
    0.83
    tsi
    0.83
    a
    0.82
     اللهم
    0.79
    Act Density 0.012%

    No Known Activations