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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     teori
    1.32
     requires
    1.16
     hydrox
    1.15
     distinguishes
    1.14
     fluctuates
    1.12
     recommends
    1.11
     restricts
    1.10
     but
    1.09
     prefers
    1.09
     trink
    1.09
    POSITIVE LOGITS
    d
    1.14
    ટ
    1.00
    力
    0.95
    l
    0.93
    ر
    0.93
    b
    0.90
    rà
    0.89
    èrement
    0.88
    Capacity
    0.88
    ας
    0.86
    Act Density 0.718%

    No Known Activations