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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    qy
    0.42
    ence
    0.40
    employment
    0.37
    ルール
    0.37
     employment
    0.37
    ère
    0.36
     something
    0.36
    ார
    0.36
    q
    0.36
    Acceler
    0.36
    POSITIVE LOGITS
     TikTok
    0.44
     Witcher
    0.44
    TikTok
    0.44
     alcoved
    0.42
     homes
    0.40
     filede
    0.40
     sofá
    0.40
    Instagram
    0.39
    boxed
    0.39
    boxplot
    0.39
    Act Density 0.002%

    No Known Activations