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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence-ending indicators

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

    Sentences that begin with coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    nevertheless, nonetheless, still

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Waray
    -0.66
    Autoritní
    -0.62
    setof
    -0.61
    HomeAsUpEnabled
    -0.58
    tonsoft
    -0.58
    SequentialGroup
    -0.57
    featureID
    -0.56
    __()
    -0.55
     Exactos
    -0.55
    ArgsConstructor
    -0.54
    POSITIVE LOGITS
     nevertheless
    2.77
     nonetheless
    2.67
    Nevertheless
    2.63
     Nevertheless
    2.60
    Nonetheless
    2.55
     Nonetheless
    2.53
    Still
    2.38
     Still
    2.33
     still
    2.23
     dennoch
    2.12
    Act Density 0.456%

    No Known Activations