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

    Neuronpedia

    INDEX
    Explanations

    phrases related to people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Accessory
    -0.79
    enthal
    -0.68
    Brexit
    -0.67
    Phill
    -0.65
     McDonnell
    -0.64
     Boss
    -0.64
     podium
    -0.62
    Adds
    -0.62
    Front
    -0.60
     recess
    -0.60
    POSITIVE LOGITS
     persons
    1.06
     Persons
    0.97
    chwitz
    0.88
    folk
    0.85
    hood
    0.81
    laughter
    0.79
    puter
    0.77
    cript
    0.77
    everal
    0.77
     "$:/
    0.76
    Act Density 0.008%

    No Known Activations