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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the past action of using something or occurring events

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

    "used to" or "happen to"

    np_acts-logits-general · gemini-2.0-flash

    used to / happen to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.68
     щоб
    -0.63
    endsection
    -0.60
    üyada
    -0.59
    //
    -0.59
    yml
    -0.57
     để
    -0.56
     чтобы
    -0.53
     CanadaChoose
    -0.53
    зулта
    -0.53
    POSITIVE LOGITS
     be
    0.70
    tobe
    0.64
    styleType
    0.61
    ToBe
    0.60
     Gorg
    0.57
    verifyException
    0.57
     '\\;'
    0.57
     být
    0.55
    antly
    0.55
     happen
    0.53
    Act Density 0.112%

    No Known Activations