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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    at
    1.36
    as
    1.22
    andang
    1.11
    en
    1.11
     caring
    1.04
     wasted
    1.03
    antaranya
    1.00
    ynn
    0.98
    ியின்
    0.98
    aqs
    0.97
    POSITIVE LOGITS
    𝐖
    1.23
    源代码
    1.20
    越大
    1.15
     ребята
    1.10
    감을
    1.09
    Ĉ
    1.08
     சித்த
    1.07
     hexadecimal
    1.07
    Л
    1.05
    1.05
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.