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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    resultado
    -0.07
    ：“
    -0.07
    ้
    -0.07
    裉
    -0.06
    润
    -0.06
    ?option
    -0.06
    )'),↵
    -0.06
    ❒
    -0.06
    无助
    -0.06
    ℰ
    -0.06
    POSITIVE LOGITS
    .fragment
    0.09
     Forms
    0.08
    ungeons
    0.07
    _posts
    0.07
    ungalow
    0.07
     perf
    0.07
    垭
    0.07
     הראשונה
    0.07
    .sn
    0.07
    加拿
    0.07
    Act Density 0.001%

    No Known Activations