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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical significance and comparisons in research

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

    Followed by words indicating positive change

    np_acts-logits-general · gemini-2.0-flash

    measure of significant change or effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APIView
    -0.57
    ReusableCell
    -0.49
     encarga
    -0.49
    au
    -0.47
     seres
    -0.46
    klo
    -0.46
    ıyors
    -0.46
    óz
    -0.44
     متعلقه
    -0.41
    wal
    -0.41
    POSITIVE LOGITS
     improvement
    0.88
     Improvement
    0.83
     increase
    0.82
     improvements
    0.79
     increased
    0.77
    improvement
    0.76
     reduction
    0.76
    increase
    0.74
    فایل‌لار
    0.73
    ificantly
    0.73
    Act Density 0.303%

    No Known Activations