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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     phosphate
    1.04
     Coke
    1.02
     proble
    1.02
    :
    1.01
    ：%
    1.00
     Mackey
    0.98
     drinks
    0.98
     free
    0.97
     liberty
    0.96
     cutt
    0.96
    POSITIVE LOGITS
     Focusing
    0.86
     Aiden
    0.85
    Han
    0.83
     approfond
    0.83
     هات
    0.82
    Throughout
    0.81
     THOR
    0.80
     destacado
    0.75
     categorize
    0.74
    郝
    0.74
    Act Density 0.843%

    No Known Activations