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

    Neuronpedia

    INDEX
    Explanations

    references to secrets and hidden truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    もしろ
    -0.57
     AspNetCore
    -0.56
     GenerationType
    -0.54
    Rider
    -0.54
    ########.
    -0.52
    izace
    -0.52
     Welding
    -0.51
    harusnya
    -0.51
     Pferd
    -0.50
     Whelan
    -0.50
    POSITIVE LOGITS
     secret
    2.17
     Secret
    2.05
    Secret
    2.03
    secret
    1.99
     SECRET
    1.92
    SECRET
    1.70
     secrets
    1.70
     secreto
    1.52
     Secrets
    1.50
    Secrets
    1.47
    Act Density 0.188%

    No Known Activations