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

    Neuronpedia

    INDEX
    Explanations

    phrases related to themes of loss and transformations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.55
    IntoConstraints
    -0.54
    HtmlAttribute
    -0.45
     OMITBAD
    -0.45
     snippetHide
    -0.44
    ScopeManager
    -0.42
     intStringLen
    -0.41
    ftagPool
    -0.41
    MessageState
    -0.41
     defaultstate
    -0.40
    POSITIVE LOGITS
     game
    3.58
     games
    2.95
    game
    2.88
     Game
    2.55
    Game
    2.50
     GAME
    2.50
     게임
    2.31
    games
    2.30
     Games
    2.28
    游戏
    2.28
    Act Density 0.680%

    No Known Activations