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

    Neuronpedia

    INDEX
    Explanations

    mentions of proxies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.95
    findpost
    -0.79
    ❤❤
    -0.74
     Amar
    -0.73
    Amar
    -0.72
    Ҭ
    -0.70
    <<"
    -0.68
    ELIN
    -0.68
     amar
    -0.67
    setupUi
    -0.67
    POSITIVE LOGITS
     deer
    0.78
     hike
    0.77
     Wenger
    0.75
     scribe
    0.74
     Hike
    0.73
     commodity
    0.72
    Dave
    0.71
     Reporter
    0.71
     recorder
    0.70
     hiker
    0.70
    Act Density 0.058%

    No Known Activations