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

    Neuronpedia

    INDEX
    Explanations

    mentions of different groups of people or communities

    oai_token-act-pair · gpt-3.5-turbo

    references to different groups or communities of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctors
    -0.71
    VM
    -0.70
    ous
    -0.68
    QL
    -0.67
    LV
    -0.67
    é¾
    -0.67
    Shot
    -0.65
    Charge
    -0.64
    GPU
    -0.64
    PM
    -0.64
    POSITIVE LOGITS
     peoples
    1.28
    oples
    0.99
     minds
    0.83
     nations
    0.81
     Peoples
    0.77
     inhab
    0.77
    wana
    0.76
    itaire
    0.74
    selves
    0.73
    folk
    0.73
    Act Density 0.006%

    No Known Activations