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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    variance
    1.06
    mint
    0.99
    otive
    0.95
    ignor
    0.95
    puts
    0.94
     ActionMode
    0.94
    Hydrochloride
    0.94
    cookie
    0.93
    ousedown
    0.93
    unique
    0.93
    POSITIVE LOGITS
    8
    0.98
     ""),
    0.87
    5
    0.86
    …]
    0.85
     Tipps
    0.84
     impetus
    0.83
    )").
    0.83
    ЕР
    0.83
    9
    0.82
    ͒
    0.81
    Act Density 0.000%

    No Known Activations