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

    Neuronpedia

    INDEX
    Explanations

    phrases related to education and skill development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annt
    -0.17
    orna
    -0.16
    utton
    -0.16
    leys
    -0.15
    orex
    -0.15
    ORITY
    -0.14
    odate
    -0.14
    oxy
    -0.14
    каз
    -0.14
    anter
    -0.14
    POSITIVE LOGITS
    eda
    0.17
     Garrison
    0.15
    YYY
    0.14
    rio
    0.14
    XX
    0.14
    iffin
    0.14
     Ú©ÙĨ
    0.14
    798
    0.13
     Gad
    0.13
    INAL
    0.13
    Act Density 0.139%

    No Known Activations