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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     While
    -3.42
    </h2>
    -3.19
    ">
    -2.72
    ){
    -2.67
     With
    -2.64
     If
    -2.58
    外界
    -2.58
    熒
    -2.53
     for
    -2.53
     These
    -2.48
    POSITIVE LOGITS
    茈
    3.11
    ↵↵
    2.83
    戆
    2.78
    栳
    2.75
    蟶
    2.72
    ⟣
    2.70
     撮り
    2.69
    艄
    2.66
     einzige
    2.63
     captivating
    2.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.