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

    Neuronpedia

    INDEX
    Explanations

    references to the Oscar awards and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.77
    __':
    -0.71
    caux
    -0.70
    AddTagHelper
    -0.64
    voix
    -0.63
    "],
    -0.61
    )=>{
    -0.61
    endar
    -0.60
    entity
    -0.60
     Kuznets
    -0.59
    POSITIVE LOGITS
     Moore
    1.36
     MOORE
    1.16
    Moore
    1.12
     Amy
    1.07
     moore
    1.04
    Amy
    1.00
     Moor
    0.95
     lid
    0.85
     Emma
    0.83
     Oscar
    0.82
    Act Density 0.061%

    No Known Activations