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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     atta
    0.75
    창
    0.71
     창
    0.70
    지의
    0.70
     கூட
    0.69
    atea
    0.68
    Add
    0.68
     hånd
    0.68
     huj
    0.66
     advertisements
    0.66
    POSITIVE LOGITS
    }:$
    0.89
    以下の
    0.88
     three
    0.88
    }$:
    0.85
    以下
    0.85
    :”
    0.83
     stepwise
    0.82
     continuación
    0.81
    如下
    0.80
     以下
    0.80
    Act Density 4.341%

    No Known Activations