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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the end of a turn or segment in a conversation

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

    programming and technical code

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens marking the end of a user turn (end-of-turn/conversation-boundary markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     card
    -0.41
    ↵↵
    -0.40
    FDRE
    -0.39
     or
    -0.38
    io
    -0.37
    card
    -0.36
    OrCreate
    -0.35
     of
    -0.35
     be
    -0.35
     and
    -0.35
    POSITIVE LOGITS
     ExecuteAsync
    0.79
    transQ
    0.71
     NSCoder
    0.67
    tvguidetime
    0.65
    ambién
    0.65
    enumii
    0.64
     JpaRepository
    0.64
    setVerticalGroup
    0.64
    ftagPool
    0.62
     HasFactory
    0.61
    Act Density 0.016%

    No Known Activations