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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant named entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TaÅŁ
    -0.15
    ê³Ħ
    -0.14
    FFE
    -0.14
     Ba
    -0.14
     Heat
    -0.14
     bridges
    -0.14
    Ba
    -0.14
     Tale
    -0.13
    pon
    -0.13
    MLE
    -0.13
    POSITIVE LOGITS
     bro
    0.17
    idenav
    0.17
    gue
    0.16
    eto
    0.16
    kker
    0.16
    ucht
    0.15
    ÑĸлÑĮ
    0.15
     Bro
    0.15
    stry
    0.15
     Bros
    0.14
    Act Density 0.037%

    No Known Activations