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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and coordinating phrases

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

    conjunction followed by participial clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     depends
    -0.48
     can
    -0.47
     makes
    -0.45
    KommentareTeilen
    -0.45
     happens
    -0.45
    depends
    -0.45
     ensures
    -0.44
     helps
    -0.44
     might
    -0.43
    transQ
    -0.43
    POSITIVE LOGITS
     requiring
    1.27
     needing
    1.18
     featuring
    1.18
     containing
    1.16
     consisting
    1.11
     representing
    1.09
     possessing
    1.09
     having
    1.06
     lacking
    1.02
     offering
    1.02
    Act Density 0.105%

    No Known Activations