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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical illness or negative health conditions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sick"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlaw
    -0.75
     unden
    -0.67
     compr
    -0.67
    ETHOD
    -0.65
     Unch
    -0.64
    inational
    -0.64
    merce
    -0.63
    anship
    -0.62
    AUT
    -0.62
    adr
    -0.61
    POSITIVE LOGITS
    ening
    1.20
    bay
    1.14
    ened
    1.06
    nesses
    0.94
    estro
    0.87
    le
    0.87
    ly
    0.86
    est
    0.85
    ert
    0.85
    ness
    0.82
    Act Density 0.016%

    No Known Activations