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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the name "Kos" or "Kumar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ees
    -0.79
    ible
    -0.73
    ee
    -0.72
    ault
    -0.72
    ership
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    rees
    -0.67
     Carrie
    -0.66
    ISTER
    -0.66
    ists
    -0.65
    POSITIVE LOGITS
    ovan
    0.80
    ugi
    0.78
    balls
    0.75
    ukemia
    0.75
    sei
    0.75
    iky
    0.73
    ball
    0.71
    posium
    0.69
    nikov
    0.68
    jac
    0.67
    Act Density 0.050%

    No Known Activations