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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    {
    0.99
    gimento
    0.90
     inductor
    0.89
     resentment
    0.86
    ^\
    0.85
    ν
    0.84
     vinegar
    0.83
    ἠ
    0.81
    ünüz
    0.81
    檛
    0.79
    POSITIVE LOGITS
    Bene
    1.03
     Blo
    1.01
    щих
    1.00
    Cal
    1.00
    ચારી
    0.98
    Doors
    0.97
    volle
    0.96
    Defining
    0.95
     Architect
    0.95
     disposto
    0.94
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.