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

    Neuronpedia

    INDEX
    Explanations

    words related to the spread, development, or origination of various phenomena or issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the spread and prevention of diseases or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.67
    DCS
    -0.67
    ãĤ¦ãĤ¹
    -0.62
    ĪĴ
    -0.61
    Ĥ¬
    -0.60
    ãĤ·ãĥ£
    -0.60
    ãĤ¡
    -0.60
     refres
    -0.60
    ãĥª
    -0.59
    staff
    -0.59
    POSITIVE LOGITS
     elsewhere
    1.11
     underground
    0.98
     unchecked
    0.95
     anywhere
    0.95
     explos
    0.94
     everywhere
    0.94
     spontaneously
    0.93
     outside
    0.92
     peacefully
    0.90
     around
    0.90
    Act Density 0.265%

    No Known Activations