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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or patterns involving the word "a" and related quantifiers

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

    "a" followed by quantity words

    np_acts-logits-general · gemini-2.0-flash

    a lot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الاطلاع
    -0.56
    rimp
    -0.56
    ]='\
    -0.53
    erval
    -0.51
    yeur
    -0.51
     unve
    -0.50
     QtCore
    -0.48
    unjungi
    -0.48
     MonoBehaviour
    -0.48
     seme
    -0.48
    POSITIVE LOGITS
     spits
    0.72
     estekak
    0.72
     crappy
    0.70
     termica
    0.66
     crazy
    0.65
     montón
    0.65
     bunch
    0.64
     anthropologists
    0.63
     wierd
    0.63
     little
    0.62
    Act Density 0.323%

    No Known Activations