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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that indicate relationships between ideas

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

    conjunctions and phrases indicating addition or combination

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

    so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    middels
    -0.64
    存于互联网档案馆
    -0.61
    EnableWeb
    -0.60
     للاسماء
    -0.57
    PHPExcel
    -0.56
    buie
    -0.54
     NSCoder
    -0.54
     tartalomajánló
    -0.53
    LookAnd
    -0.52
    ждую
    -0.52
    POSITIVE LOGITS
     so
    3.80
    so
    2.85
    So
    2.38
     So
    2.19
     così
    2.01
     так
    1.95
     så
    1.94
     SO
    1.77
    那么
    1.55
     sooo
    1.51
    Act Density 0.168%

    No Known Activations