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

    Neuronpedia

    INDEX
    Explanations

    phrases related to design and function specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.61
     مشين
    -0.61
    WEBPACK
    -0.57
    ьаж
    -0.56
    Humble
    -0.55
     disponibilités
    -0.53
    cendental
    -0.52
    ⓧ
    -0.51
    creep
    -0.51
    arrings
    -0.51
    POSITIVE LOGITS
     designed
    1.12
     intended
    1.05
    designed
    0.98
    intended
    0.95
     Designed
    0.94
    Designed
    0.90
     destinés
    0.90
    Intended
    0.88
     предназна
    0.86
     Intended
    0.84
    Act Density 0.233%

    No Known Activations