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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating existence or status

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

    past existence or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.51
     ainfi
    -0.48
     iParam
    -0.47
     ſte
    -0.45
    VYMaps
    -0.44
     ſa
    -0.44
     purpoſe
    -0.43
    zeiro
    -0.42
     Fon
    -0.41
     Inscrivez
    -0.40
    POSITIVE LOGITS
     was
    0.80
     היה
    0.79
    だった
    0.77
     geweest
    0.71
     הייתה
    0.71
     gewesen
    0.70
    なかった
    0.69
     doveva
    0.68
    وكان
    0.68
    しかった
    0.67
    Act Density 0.008%

    No Known Activations