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

    Neuronpedia

    INDEX
    Explanations

    social and political issues or statements related to them, especially surrounding controversial topics like racism, infrastructure spending, legislation, and administration decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gradient
    -0.57
    estern
    -0.57
     Schedule
    -0.57
    NOT
    -0.56
    FI
    -0.56
    ãĥĻ
    -0.55
    oval
    -0.55
    DragonMagazine
    -0.54
    ãĤ³
    -0.54
     unfinished
    -0.53
    POSITIVE LOGITS
     ever
    1.01
     combined
    0.98
     existed
    0.89
    pees
    0.81
    erest
    0.78
     implies
    0.78
    ().
    0.74
     could
    0.74
     deserves
    0.74
     realizes
    0.73
    Act Density 0.342%

    No Known Activations