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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions and references to duration

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

    as long as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     letter
    -0.47
    -------
    -0.46
     Schumer
    -0.41
    ioutil
    -0.41
    PMailer
    -0.40
     letra
    -0.38
    áncer
    -0.37
     ferons
    -0.37
     äm
    -0.37
    letter
    -0.37
    POSITIVE LOGITS
     Пока
    1.03
     пока
    1.03
    Пока
    0.95
     solange
    0.83
     Enquanto
    0.69
     enquanto
    0.68
    Until
    0.67
     until
    0.67
     zatím
    0.65
     Until
    0.65
    Act Density 0.016%

    No Known Activations