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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to governmental statements or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional or psychological conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatures
    -0.78
     behav
    -0.74
     proble
    -0.74
     agre
    -0.73
     srf
    -0.68
    ursday
    -0.64
     occas
    -0.64
    ukong
    -0.63
     enthusi
    -0.63
     chall
    -0.63
    POSITIVE LOGITS
    ãĤĮ
    0.83
    âĸĢ
    0.78
    %"
    0.78
    ãģį
    0.75
    é¾į
    0.72
    μ
    0.70
    âĸĪâĸĪâĸĪâĸĪ
    0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.68
    çļĦ
    0.67
    âĸij
    0.66
    Act Density 0.271%

    No Known Activations