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

    Neuronpedia

    INDEX
    Explanations

    the word "only" and its variations, indicating exclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Macedonia
    -0.71
     Wakefield
    -0.71
     Marge
    -0.70
     Wadsworth
    -0.69
     zah
    -0.69
     urma
    -0.69
    ViewFeatures
    -0.68
    $($
    -0.67
     Bulldogs
    -0.67
    Zah
    -0.66
    POSITIVE LOGITS
     only
    1.28
     Only
    1.12
     ONLY
    1.08
    ONLY
    1.05
    Only
    1.04
    only
    0.99
    Sólo
    0.95
    nly
    0.95
     seulement
    0.91
    \}_{
    0.85
    Act Density 0.108%

    No Known Activations