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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

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

    which followed by a descriptive clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насеље
    -0.35
     pierdas
    -0.35
    nito
    -0.34
    SEGUIR
    -0.34
    tale
    -0.34
     suivante
    -0.34
    พวก
    -0.33
     cuesta
    -0.33
     współ
    -0.33
     dovrebbero
    -0.32
    POSITIVE LOGITS
    homonymie
    0.55
    getWriter
    0.55
    InInspector
    0.47
    farwyddwr
    0.46
    umerable
    0.46
     kasarigan
    0.46
    Who
    0.44
     بيها
    0.43
    MENAFN
    0.43
     endforeach
    0.43
    Act Density 0.070%

    No Known Activations