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

    Neuronpedia

    INDEX
    Explanations

    references to groups or subgroups of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to various types or categories of groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Adv
    -0.79
    Accessory
    -0.78
     Latest
    -0.76
    wards
    -0.75
    LV
    -0.75
    Marginal
    -0.69
    shire
    -0.69
    TN
    -0.66
     DEC
    -0.64
     Advocate
    -0.64
    POSITIVE LOGITS
    roups
    1.02
     affili
    0.91
    anguage
    0.87
    rats
    0.86
     groups
    0.86
    groups
    0.86
    ativity
    0.84
    istical
    0.83
    group
    0.79
     group
    0.78
    Act Density 0.040%

    No Known Activations