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

    Neuronpedia

    INDEX
    Explanations

    instances of name changes or references to naming conventions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemLayout
    -0.55
    ElementException
    -0.52
     estekak
    -0.46
     Италијани
    -0.45
    GEBURTSDATUM
    -0.41
    SetBool
    -0.40
    PreferredItem
    -0.40
     dostar
    -0.39
    enable
    -0.39
     ProtoMessage
    -0.38
    POSITIVE LOGITS
     naming
    1.55
     renaming
    1.50
     nickname
    1.47
     rename
    1.44
     nicknames
    1.42
     moniker
    1.35
     Naming
    1.31
     renamed
    1.30
    Naming
    1.25
    naming
    1.21
    Act Density 0.321%

    No Known Activations