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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𩾃
    -0.08
     fais
    -0.07
     coff
    -0.07
    ="<?=$
    -0.07
    ㈎
    -0.07
     Perry
    -0.07
    🐂
    -0.07
    `"]↵
    -0.07
     soft
    -0.07
    abyrinth
    -0.07
    POSITIVE LOGITS
     것이다
    0.08
     것입니다
    0.08
    cribes
    0.08
     שכבר
    0.08
     그것
    0.07
     đó
    0.07
     때문이다
    0.07
     высоко
    0.07
     inferred
    0.07
     analysed
    0.07
    Act Density 0.003%

    No Known Activations