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

    Neuronpedia

    INDEX
    Explanations

    references to secrecy and hidden information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.62
    astéroïdes
    -0.46
     beginnetje
    -0.46
    ArgsConstructor
    -0.46
    المكان
    -0.44
    ConstraintMaker
    -0.42
    MockBean
    -0.42
    पया
    -0.42
    yntaxException
    -0.41
     Photocase
    -0.41
    POSITIVE LOGITS
     secret
    3.27
     secrets
    2.88
    secret
    2.88
    Secret
    2.59
     Secret
    2.55
     SECRET
    2.50
    secrets
    2.39
     secreto
    2.36
     secretos
    2.33
    SECRET
    2.27
    Act Density 0.325%

    No Known Activations