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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝒔
    0.83
     世界
    0.82
     Всё
    0.81
    ियस
    0.76
    𝐬
    0.76
    bbing
    0.75
     Bigger
    0.75
     indoctr
    0.74
    ২২
    0.74
    頪
    0.73
    POSITIVE LOGITS
     rasa
    0.76
    arcs
    0.71
    id
    0.69
     затвер
    0.69
     cerca
    0.68
     mrs
    0.68
    permissionid
    0.68
    il
    0.68
    ackel
    0.68
    ниць
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.