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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and third-person perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    canf
    -0.16
    viar
    -0.15
     Lad
    -0.15
    IDS
    -0.14
    ÑijÑĢ
    -0.14
    GS
    -0.14
    _firestore
    -0.13
    emas
    -0.13
    valor
    -0.13
    æĬľ
    -0.13
    POSITIVE LOGITS
    pedia
    0.16
    adoo
    0.16
    ajan
    0.16
    ering
    0.15
    entity
    0.14
    ered
    0.14
    _endpoint
    0.14
    plete
    0.14
    .RunWith
    0.14
    beck
    0.13
    Act Density 0.342%

    No Known Activations