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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data usage and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aikaa
    -0.88
    oredCriteria
    -0.83
     épaules
    -0.78
     vermelhas
    -0.73
     brancas
    -0.71
     vôtre
    -0.71
     écrits
    -0.71
     comigo
    -0.70
     armées
    -0.69
     dalamnya
    -0.69
    POSITIVE LOGITS
     interi
    0.65
     marriage
    0.64
     human
    0.64
     coronavirus
    0.63
     football
    0.62
     commercial
    0.61
     firearms
    0.61
     mobile
    0.61
     food
    0.61
    QUADS
    0.61
    Act Density 2.233%

    No Known Activations