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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /OR
    -0.16
    /or
    -0.15
    ÅĻad
    -0.13
    álu
    -0.13
    ầu
    -0.13
    thus
    -0.13
    اع
    -0.13
    IENTATION
    -0.13
    ifferential
    -0.13
    ÅĽ
    -0.13
    POSITIVE LOGITS
    hen
    0.16
    asin
    0.15
     Kauf
    0.15
    addtogroup
    0.14
    ratulations
    0.13
    prech
    0.13
    ivent
    0.13
     Ders
    0.13
    lover
    0.13
    adol
    0.12
    Act Density 0.299%

    No Known Activations