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

    Neuronpedia

    INDEX
    Explanations

    instances of conversational phrases or statements related to personal beliefs and ethical considerations

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

    Followed by "just"

    np_acts-logits-general · gemini-2.0-flash

    just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ähkö
    -0.57
     enige
    -0.56
     الأصل
    -0.55
     оригіналу
    -0.54
    おお
    -0.54
    囗
    -0.52
     DialogInterface
    -0.52
    migrationBuilder
    -0.51
    mybatisplus
    -0.50
     forState
    -0.50
    POSITIVE LOGITS
     just
    4.18
    just
    3.65
    Just
    3.22
     Just
    3.17
     simply
    2.97
     JUST
    2.80
     juste
    2.71
    JUST
    2.57
     simplemente
    2.51
    simply
    2.46
    Act Density 0.877%

    No Known Activations