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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding social and political beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indr
    -0.16
    æľĭ
    -0.15
     favored
    -0.15
     дол
    -0.15
     anymore
    -0.15
     barely
    -0.15
     favors
    -0.14
     theater
    -0.14
     referencing
    -0.14
    Regardless
    -0.14
    POSITIVE LOGITS
     nexus
    0.16
    æ
    0.15
    èIJ
    0.15
    ague
    0.14
     Tribal
    0.13
    semi
    0.13
     passionately
    0.13
    egot
    0.13
    -Clause
    0.13
     suburban
    0.13
    Act Density 0.014%

    No Known Activations