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

    Neuronpedia

    INDEX
    Explanations

    references to human behavior and its associated patterns

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

    "behavior" or "behaviour"

    np_acts-logits-general · gemini-2.0-flash

    behavior and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fairest
    -0.59
    бият
    -0.59
     Donne
    -0.59
     skar
    -0.57
     Milne
    -0.57
     losers
    -0.56
     jdbcTemplate
    -0.55
     geschlagen
    -0.55
     romántica
    -0.55
     Ráp
    -0.54
    POSITIVE LOGITS
     behavior
    1.35
     behaviors
    1.34
     behaviours
    1.32
     behaviour
    1.30
     Behavior
    1.22
     BEHAVIOR
    1.19
     BEHAV
    1.18
    behavior
    1.17
     Behaviour
    1.16
     Behaviors
    1.13
    Act Density 0.258%

    No Known Activations