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

    Neuronpedia

    INDEX
    Explanations

    words related to medical devices and procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ill."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -+-+
    -0.83
    Ħ¢
    -0.81
    ĸļ
    -0.79
    ©¶æ¥µ
    -0.78
    ĪĴ
    -0.75
    ij士
    -0.74
    ĵĺ
    -0.73
    reme
    -0.72
    resy
    -0.68
    eering
    -0.68
    POSITIVE LOGITS
    ted
    1.06
    uvian
    1.01
    ibrary
    0.98
    ibr
    0.97
    uminati
    0.96
    aments
    0.95
     Nadu
    0.94
    ocated
    0.91
    ogical
    0.91
    iberal
    0.88
    Act Density 0.035%

    No Known Activations