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

    Neuronpedia

    INDEX
    Explanations

    instructions related to user account management and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arde
    -0.18
    emailer
    -0.15
     hete
    -0.15
    UnderTest
    -0.15
     stuff
    -0.14
    iffe
    -0.13
    öy
    -0.13
     Indexed
    -0.13
     Viv
    -0.13
    IMAL
    -0.13
    POSITIVE LOGITS
     admin
    0.17
     admins
    0.16
    Admin
    0.14
     stew
    0.14
     doÄŁru
    0.14
    erro
    0.14
     Admin
    0.14
     Tin
    0.14
     org
    0.13
     Administr
    0.13
    Act Density 0.031%

    No Known Activations