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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating someone's actions or decisions in various contexts

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

    past habitual actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagHelper
    -0.45
    ))=\
    -0.42
     souten
    -0.41
    <?
    -0.41
     aapt
    -0.40
    ")));
    -0.40
     remains
    -0.39
     считает
    -0.37
    httphttps
    -0.37
     consideran
    -0.36
    POSITIVE LOGITS
     occasional
    0.65
    Occasionally
    0.60
    Whenever
    0.60
     whenever
    0.60
     periodic
    0.58
     oftentimes
    0.57
    whenever
    0.56
     Whenever
    0.55
     sometimes
    0.54
     Occasionally
    0.54
    Act Density 0.035%

    No Known Activations