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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional words that contrast or introduce an exception

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     InputDecoration
    -1.02
    ftagPool
    -0.96
     nakalista
    -0.91
    CppCodeGen
    -0.90
    ViewFeatures
    -0.90
    帖最后由
    -0.80
    expandindo
    -0.79
    UnsafeEnabled
    -0.79
     JpaRepository
    -0.77
     Roskov
    -0.77
    POSITIVE LOGITS
     But
    0.63
    But
    0.61
     Butler
    0.54
    confirmButton
    0.52
    ut
    0.52
    but
    0.51
     BUTLER
    0.49
    もありますが
    0.48
    di
    0.47
    "${
    0.45
    Act Density 0.026%

    No Known Activations