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

    Neuronpedia

    INDEX
    Explanations

    personal names, particularly of politicians

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and titles related to government positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gins
    -0.89
    estones
    -0.89
    keyes
    -0.83
    vana
    -0.78
    jas
    -0.75
    ttes
    -0.72
    acea
    -0.69
    ties
    -0.69
    wich
    -0.68
    crew
    -0.68
    POSITIVE LOGITS
     Bers
    0.89
     Rog
    0.79
     Bald
    0.79
     Mech
    0.78
     Priebus
    0.78
     Ban
    0.76
     Kik
    0.76
     Trog
    0.75
     Lis
    0.75
     Herz
    0.75
    Act Density 0.122%

    No Known Activations