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

    Neuronpedia

    INDEX
    Explanations

    statistics and numbers related to various subjects

    oai_token-act-pair · gpt-3.5-turbo

    data and statistics related to population and health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comrades
    -0.74
    ĪĴ
    -0.66
     fences
    -0.64
     superiors
    -0.61
    henko
    -0.61
     colleagues
    -0.60
     realism
    -0.60
    asty
    -0.59
     recons
    -0.58
     Honour
    -0.58
    POSITIVE LOGITS
     worldwide
    1.06
     globally
    0.94
     annually
    0.91
     yearly
    0.84
     relies
    0.73
     livest
    0.72
     nowadays
    0.71
    0.68
     revolves
    0.68
     (£
    0.68
    Act Density 0.574%

    No Known Activations