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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating equality or balance between subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Triple
    -0.14
     Kenn
    -0.14
     lục
    -0.13
    ulace
    -0.13
     Pu
    -0.13
    jar
    -0.13
    å¼Ĥ
    -0.13
     sandwich
    -0.13
    ERRUPT
    -0.13
    ople
    -0.13
    POSITIVE LOGITS
     equally
    0.29
    ocha
    0.17
    uela
    0.16
    rong
    0.15
    ůr
    0.15
    lage
    0.14
    ÑĢалÑĮ
    0.14
    losion
    0.14
    ily
    0.14
    wel
    0.14
    Act Density 0.019%

    No Known Activations