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

    Neuronpedia

    INDEX
    Explanations

    instances of actions and their outcomes

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

    starts sentences with personal pronouns and pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.52
    Дереккөздер
    -0.48
    RTSN
    -0.47
    Искәрмәләр
    -0.44
     propOrder
    -0.44
    Билгалдахарш
    -0.44
    وردار
    -0.44
    Šaltiniai
    -0.43
    Ծանոթ
    -0.43
    HeaderComponent
    -0.42
    POSITIVE LOGITS
    awtextra
    0.49
     myself
    0.43
     I
    0.39
     hice
    0.38
    Virgin
    0.36
     чтобы
    0.36
     ended
    0.35
    ZING
    0.35
     smartest
    0.35
    enjoy
    0.35
    Act Density 0.061%

    No Known Activations