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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations, particularly those related to equations and expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    indd
    -0.97
    RegressionTest
    -0.86
    MLLoader
    -0.79
     Magdalene
    -0.78
    KommentareTeilen
    -0.73
    Personendaten
    -0.73
    coroutines
    -0.70
     Савезне
    -0.70
    ertale
    -0.70
    Dowell
    -0.70
    POSITIVE LOGITS
    obraz
    0.71
     thérape
    0.60
     Cond
    0.60
     servici
    0.60
    τογραφ
    0.59
     Quig
    0.59
     hjelp
    0.58
     nuages
    0.58
    鋭
    0.57
     compét
    0.57
    Act Density 0.027%

    No Known Activations