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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and their variations in the context of relationships and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.15
    ãĥ¼ãĥ³
    -0.14
    елик
    -0.14
    ILE
    -0.14
    nat
    -0.14
    HAL
    -0.14
    kowski
    -0.14
    iven
    -0.13
    ILES
    -0.13
    iesen
    -0.13
    POSITIVE LOGITS
    lash
    0.15
    ëĵł
    0.14
    sembl
    0.14
    ůl
    0.13
    elo
    0.13
    eding
    0.13
    eti
    0.13
    sei
    0.13
    ataka
    0.13
    DT
    0.13
    Act Density 0.097%

    No Known Activations