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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts as well as the word "which."

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

    that followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.46
    NewUrlParser
    -0.40
     alcuna
    -0.40
     prochaines
    -0.38
    Personendaten
    -0.38
    重要的是
    -0.36
    Примі
    -0.35
     enfans
    -0.35
     vérit
    -0.35
    んじゃない
    -0.35
    POSITIVE LOGITS
     którzy
    0.88
     которые
    0.78
     kteří
    0.75
     ktorí
    0.75
     които
    0.75
     who
    0.73
     jotka
    0.71
     који
    0.67
    UIControlState
    0.67
     które
    0.67
    Act Density 0.312%

    No Known Activations