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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal pronouns and their interactions in sentences

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

    Preceding pronouns or names

    np_acts-logits-general · gemini-2.0-flash

    attributing things to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reasoning
    -0.58
     Reasoning
    -0.54
     собі
    -0.50
    を受けた
    -0.49
    を受けて
    -0.48
     JpaRepository
    -0.46
     betrokken
    -0.46
     mukana
    -0.46
    得到了
    -0.45
     sobie
    -0.44
    POSITIVE LOGITS
     owe
    0.65
     Paglinawan
    0.62
    ########.
    0.61
     assigned
    0.61
     belonged
    0.60
     belongs
    0.60
     belong
    0.59
     owes
    0.58
     dedicate
    0.58
     ascribed
    0.58
    Act Density 0.063%

    No Known Activations