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

    Neuronpedia

    INDEX
    Explanations

    a wide variety of punctuation and coordinating conjunctions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jadx
    -0.65
     noDo
    -0.65
    adaptiveStyles
    -0.63
     defaultstate
    -0.62
     propOrder
    -0.61
    arangay
    -0.57
    mpagne
    -0.56
     GenerationType
    -0.56
    Jereo
    -0.54
    complexContent
    -0.54
    POSITIVE LOGITS
     Enix
    0.50
    werkers
    0.44
     Judah
    0.42
     nemlig
    0.42
    Teraz
    0.41
    ⍟
    0.39
    )‏
    0.39
     keuangan
    0.39
     Teraz
    0.39
    baz
    0.38
    Act Density 0.061%

    No Known Activations