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

    Neuronpedia

    INDEX
    Explanations

    pronouns and specific nouns related to individuals and their identities

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

    whomever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.47
     lite
    -0.42
    twimg
    -0.42
    mpz
    -0.41
    DELL
    -0.40
     cam
    -0.40
    MLLoader
    -0.39
    delli
    -0.39
     Rigid
    -0.39
    詰
    -0.38
    POSITIVE LOGITS
     Monfieur
    0.62
     ſch
    0.60
     themſelves
    0.60
     itſelf
    0.56
     Inſ
    0.54
     Houſe
    0.51
    ſelf
    0.50
     myſelf
    0.50
    drawSprites
    0.50
    eseorang
    0.49
    Act Density 0.002%

    No Known Activations