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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and contrastive conjunctions indicating challenges or obstacles

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

    contrasting conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.57
     poveznice
    -0.56
    verwijspagina
    -0.52
    Демографія
    -0.52
    ьаж
    -0.49
     يتيمه
    -0.48
    hyrchwyd
    -0.47
    出版年
    -0.46
    تقاوى
    -0.45
    WebServlet
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.41
     reaſon
    0.40
    FormatException
    0.38
     easy
    0.37
    EndContext
    0.35
     Determin
    0.35
     evid
    0.35
    Gesch
    0.34
    Errorf
    0.34
     lö
    0.34
    Act Density 0.036%

    No Known Activations