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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "then" in various contexts

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

    indicating sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geiſt
    -0.80
     Geſch
    -0.70
    parsedMessage
    -0.69
    <unused52>
    -0.68
    <unused74>
    -0.68
    <unused23>
    -0.68
    <unused79>
    -0.68
     Waſſer
    -0.68
    <unused8>
    -0.68
    <unused14>
    -0.68
    POSITIVE LOGITS
     then
    0.55
     Then
    0.52
     затем
    0.49
     sitten
    0.48
     Kemudian
    0.48
     Luego
    0.45
    ępnie
    0.43
     luego
    0.42
    then
    0.42
    Then
    0.41
    Act Density 0.051%

    No Known Activations