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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "old" or "aged" entities

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

    Following "old" or similar words ("Old", "Alte")

    np_acts-logits-general · gemini-2.0-flash

    old and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSprite
    -0.80
     Ressources
    -0.75
    Personensuche
    -0.73
    esgue
    -0.72
     سكانية
    -0.72
    UserScript
    -0.71
    OGND
    -0.69
    amaño
    -0.69
    Билгалдахарш
    -0.68
    ViewFeatures
    -0.68
    POSITIVE LOGITS
     fashioned
    1.17
    fashioned
    0.93
    school
    0.72
     Old
    0.69
     OLD
    0.65
    Old
    0.64
     доб
    0.63
     adage
    0.63
     age
    0.61
     skool
    0.60
    Act Density 0.145%

    No Known Activations