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

    Neuronpedia

    INDEX
    Explanations

    phrases denoting effects or relationships related to causal influences or impacts

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

    effects of X on Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.66
    ########.
    -0.61
    saraba
    -0.59
    +#+
    -0.59
     mijne
    -0.57
     zijne
    -0.56
    AddTagHelper
    -0.55
    ChildScrollView
    -0.55
     geschiedenis
    -0.55
     AssemblyCompany
    -0.54
    POSITIVE LOGITS
     affects
    0.39
    chartInstance
    0.38
    における
    0.38
    影响
    0.36
     decreases
    0.36
    holdet
    0.35
    導致
    0.35
    AutoModerator
    0.35
     khiến
    0.34
    会导致
    0.34
    Act Density 0.131%

    No Known Activations