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

    Neuronpedia

    INDEX
    Explanations

    references to academic or research centers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    |
    -0.84
     Hogarth
    -0.83
    🏻‍♀️
    -0.83
     Eilish
    -0.81
    氓
    -0.80
    hubarb
    -0.78
    UrlResolution
    -0.75
    soldier
    -0.74
    gemä
    -0.73
    Photoshop
    -0.73
    POSITIVE LOGITS
     centers
    1.54
     Centers
    1.39
     Center
    1.34
     centres
    1.31
     center
    1.30
     CENTER
    1.24
     Centre
    1.24
     Centres
    1.18
    center
    1.17
     centre
    1.16
    Act Density 0.033%

    No Known Activations