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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating change or transformation

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

    making and looking at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.66
    expandindo
    -0.65
    EDEFAULT
    -0.62
    Tembelea
    -0.60
    RTEE
    -0.59
    Rhestr
    -0.57
    Hauptartikel
    -0.57
     بيها
    -0.57
    ScopeManager
    -0.56
    principalTable
    -0.56
    POSITIVE LOGITS
    werth
    0.36
     assumption
    0.34
     resemble
    0.33
     firm
    0.33
     essentially
    0.32
     catching
    0.32
     virtually
    0.32
     truly
    0.31
     ground
    0.31
     instead
    0.31
    Act Density 0.047%

    No Known Activations