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

    Neuronpedia

    INDEX
    Explanations

    references to secrets or hidden truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fst
    -0.14
    zy
    -0.14
     RemoteException
    -0.13
    ÙĪÙĨد
    -0.13
    lek
    -0.13
    าà¸į
    -0.13
    ÑĨ
    -0.13
    ICENSE
    -0.13
    æĪı
    -0.13
    693
    -0.13
    POSITIVE LOGITS
     secret
    0.62
     secrets
    0.60
     Secret
    0.50
     Secrets
    0.49
    secret
    0.49
    -secret
    0.46
    ç§ĺ
    0.46
     SECRET
    0.45
     secre
    0.44
    Secret
    0.44
    Act Density 0.089%

    No Known Activations