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

    Neuronpedia

    INDEX
    Explanations

    references to research or organizational centers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    🏻‍♀️
    -0.87
    UrlResolution
    -0.80
    hubarb
    -0.76
     Hogarth
    -0.74
    |
    -0.74
     McKinnon
    -0.72
    skiej
    -0.72
    soldier
    -0.71
    LEIA
    -0.70
    surgical
    -0.70
    POSITIVE LOGITS
     centers
    1.66
     Centers
    1.50
     center
    1.47
     Center
    1.47
     CENTER
    1.37
    center
    1.30
     centres
    1.30
    centers
    1.29
    Center
    1.26
    CENTER
    1.25
    Act Density 0.035%

    No Known Activations