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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news articles about specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly focusing on the name "Silva" and associated attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artment
    -1.08
    mallow
    -0.86
    ressed
    -0.85
    neys
    -0.83
    artments
    -0.83
    roma
    -0.83
    hea
    -0.82
    itone
    -0.81
    oleon
    -0.77
    ney
    -0.77
    POSITIVE LOGITS
    ous
    0.83
     vest
    0.70
    ggles
    0.69
     Pearce
    0.67
     torches
    0.67
    Film
    0.66
     welding
    0.63
     Gat
    0.62
     bargain
    0.61
     inference
    0.60
    Act Density 0.070%

    No Known Activations