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

    Neuronpedia

    INDEX
    Explanations

    phrases related to games or specific elements within a game

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming and various contexts in which games and their components are discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.81
    imon
    -0.79
    mercial
    -0.76
    oggles
    -0.73
    vantage
    -0.72
    azeera
    -0.71
    rencies
    -0.70
    ãĥŃ
    -0.69
    escription
    -0.68
    orsi
    -0.66
    POSITIVE LOGITS
     hierarchy
    0.93
    osphere
    0.85
     itself
    0.81
     realm
    0.80
     vicinity
    0.79
     area
    0.76
     periphery
    0.72
     sphere
    0.67
     nucleus
    0.65
     plaza
    0.65
    Act Density 0.343%

    No Known Activations