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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roj
    -0.16
    Äįi
    -0.16
    uyo
    -0.15
    roje
    -0.15
    779
    -0.14
    rvé
    -0.14
    ALCHEMY
    -0.14
    ivid
    -0.14
    è«ĸ
    -0.14
     RuntimeObject
    -0.14
    POSITIVE LOGITS
    WH
    0.42
    wh
    0.32
     wh
    0.32
     whe
    0.28
    hen
    0.27
    _WH
    0.27
    “When
    0.26
    "When
    0.26
     Wh
    0.25
     Whe
    0.25
    Act Density 0.088%

    No Known Activations