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

    Neuronpedia

    INDEX
    Explanations

    pronouns, particularly in reference to people and their interactions

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

    told him that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    moi
    -0.38
     MonoBehaviour
    -0.36
     tip
    -0.35
    クロス
    -0.35
     Moi
    -0.35
     moi
    -0.33
     Chia
    -0.32
    henswürdigkeiten
    -0.32
     va
    -0.32
    kup
    -0.32
    POSITIVE LOGITS
     Roskov
    0.66
     الرياضيه
    0.66
    :✨
    0.65
     queſta
    0.65
    ⓧ
    0.64
    Atsauces
    0.63
     оригіналу
    0.62
     jadx
    0.61
     houſe
    0.61
     Monfieur
    0.58
    Act Density 0.093%

    No Known Activations