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

    Neuronpedia

    INDEX
    Explanations

    expressions related to completeness or entirety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.81
     altogether
    -0.73
    +#+
    -0.69
     vivement
    -0.67
     météo
    -0.61
     célèbres
    -0.60
     Wicidata
    -0.59
     blessures
    -0.58
     BorderSide
    -0.58
    zdo
    -0.57
    POSITIVE LOGITS
     blown
    1.04
     fled
    0.98
    fledged
    0.97
    blown
    0.93
     full
    0.89
     Full
    0.84
    Full
    0.81
    FULL
    0.80
     FULL
    0.79
    full
    0.76
    Act Density 0.093%

    No Known Activations