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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and collective actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    case is, society, world, day, body, analysis were, them, user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.52
    prefixer
    -0.43
    บ้าง
    -0.42
     mancher
    -0.40
    mitian
    -0.40
     Réponses
    -0.39
    sembles
    -0.38
     Recognize
    -0.38
     isComment
    -0.38
    บาง
    -0.37
    POSITIVE LOGITS
    出版年
    0.70
     everything
    0.60
    everything
    0.57
     EVERYTHING
    0.57
    queryInterface
    0.55
     nonUne
    0.53
    Everything
    0.51
     transfieras
    0.51
    Tembelea
    0.50
     Everything
    0.50
    Act Density 0.069%

    No Known Activations