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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and interactions between individuals in a dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     avviene
    -0.53
     används
    -0.51
     domestiques
    -0.50
    manship
    -0.49
     mourir
    -0.48
     étions
    -0.48
     prennent
    -0.47
     célèbres
    -0.47
     usamos
    -0.47
     povezave
    -0.46
    POSITIVE LOGITS
    RegressionTest
    0.73
    将
    0.72
    將
    0.67
     dir
    0.65
    afficheront
    0.63
     going
    0.61
     سير
    0.60
     sẻ
    0.58
    pond
    0.58
     youll
    0.57
    Act Density 0.073%

    No Known Activations