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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to storytelling and narrative elements

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

    Prepositions, conjunctions, or question marks

    np_acts-logits-general · gemini-2.0-flash

    linking clauses or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    していますが
    -0.63
     sanoo
    -0.63
    をしています
    -0.62
    chyma
    -0.61
    tualmente
    -0.60
     currently
    -0.59
    いますが
    -0.59
    美味しいです
    -0.58
    ține
    -0.58
    ಿದೆ
    -0.57
    POSITIVE LOGITS
     was
    1.84
     had
    1.77
     wasn
    1.64
     were
    1.62
     hadn
    1.61
    was
    1.55
     weren
    1.52
    wasn
    1.45
    had
    1.44
    were
    1.44
    Act Density 1.232%

    No Known Activations