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

    Neuronpedia

    INDEX
    Explanations

    references to administrative or editorial content, particularly those mentioning authors or contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongan
    -0.15
    emer
    -0.14
    å¦
    -0.14
    jong
    -0.14
    .tar
    -0.13
    ÅĽmy
    -0.13
    argent
    -0.13
    .push
    -0.13
    ãģĶ
    -0.13
    able
    -0.13
    POSITIVE LOGITS
     admin
    0.33
     Admin
    0.33
    admin
    0.33
    Admin
    0.31
    _admin
    0.30
    _Admin
    0.29
     staff
    0.28
    -admin
    0.28
    .admin
    0.27
     admins
    0.27
    Act Density 0.043%

    No Known Activations