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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "center" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.91
     Мексичка
    -0.79
    hyrchwyd
    -0.77
    хьтан
    -0.77
     FetchType
    -0.73
    rrggbb
    -0.70
    CreateMap
    -0.70
    ########.
    -0.69
     transfieras
    -0.68
     виправивши
    -0.67
    POSITIVE LOGITS
    center
    1.59
     center
    1.16
    Center
    1.05
    centers
    0.96
    CENTER
    0.96
     centers
    0.92
    centre
    0.88
     CENTER
    0.86
     centre
    0.79
     Centers
    0.77
    Act Density 0.017%

    No Known Activations