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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating differences or variations

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

    differ in specified ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wayback
    -0.56
    蚪
    -0.54
    maxSize
    -0.54
     Schmitz
    -0.54
     Greenberg
    -0.54
    urna
    -0.53
    Nucle
    -0.53
     Laird
    -0.53
     Schulz
    -0.53
     nucleus
    -0.53
    POSITIVE LOGITS
     differ
    1.63
     differed
    1.46
     differs
    1.45
    differ
    1.30
     Differ
    1.27
     differing
    1.25
    Differ
    1.15
     DIFFER
    1.08
     diffé
    1.04
     verschillen
    0.90
    Act Density 0.013%

    No Known Activations