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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive terms

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

    possessive pronouns indicating ownership or belonging

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

    find a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scel
    -0.52
    Spec
    -0.47
     发表于
    -0.46
     Frage
    -0.44
     designed
    -0.44
     fetched
    -0.44
    kuu
    -0.43
     choosing
    -0.43
     Cochin
    -0.42
     choose
    -0.42
    POSITIVE LOGITS
     solace
    0.92
     heraus
    0.74
     answers
    0.74
    بوابة
    0.72
     собі
    0.72
     Finds
    0.71
     ways
    0.71
     balans
    0.70
     balance
    0.69
     hidden
    0.69
    Act Density 0.035%

    No Known Activations