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

    Neuronpedia

    INDEX
    Explanations

    personal experiences or stories shared by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals mentioning their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tu
    -0.69
    isoft
    -0.68
    ģĸ
    -0.67
    mite
    -0.67
    emort
    -0.63
    ez
    -0.62
    Released
    -0.61
    isons
    -0.61
    ption
    -0.59
    irements
    -0.57
    POSITIVE LOGITS
     privately
    1.02
     bluntly
    1.01
     beforehand
    0.88
     anecd
    0.87
     repeatedly
    0.86
     plainly
    0.85
     personally
    0.84
     emphatically
    0.83
     afterward
    0.81
     afterwards
    0.79
    Act Density 0.037%

    No Known Activations