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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and their associated possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashing
    -0.18
    ohn
    -0.16
    ãĥ³ãĤ¿
    -0.15
    onte
    -0.15
     Lah
    -0.14
    anki
    -0.14
    ALA
    -0.14
    .patch
    -0.14
    lect
    -0.14
    arine
    -0.14
    POSITIVE LOGITS
    éĢ¸
    0.16
    Animations
    0.16
    ãĤ¸ãĤª
    0.16
    /tos
    0.15
    allax
    0.15
    à¤Ĥदर
    0.14
    paque
    0.14
    pixels
    0.14
    /her
    0.14
    udic
    0.13
    Act Density 0.316%

    No Known Activations