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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authorship or attribution in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    used
    -0.16
     cá
    -0.15
    adj
    -0.14
     Patron
    -0.14
    htags
    -0.13
     excess
    -0.13
     patron
    -0.13
    má
    -0.13
    anders
    -0.13
     Esper
    -0.13
    POSITIVE LOGITS
     admin
    0.25
    	admin
    0.25
     Admin
    0.21
    Admin
    0.20
     admins
    0.19
    _admin
    0.17
    admin
    0.17
     rodi
    0.17
    Administrator
    0.17
    interop
    0.16
    Act Density 0.012%

    No Known Activations