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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

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

    expressions of gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.48
     createSlice
    -0.46
     canst
    -0.42
    MigrationBuilder
    -0.40
     /^\
    -0.40
     ModelExpression
    -0.39
    ✭✭
    -0.39
     cæ
    -0.38
     méd
    -0.38
    WebServlet
    -0.38
    POSITIVE LOGITS
     thanked
    0.68
    ขอบคุณ
    0.67
     thanking
    0.65
     thank
    0.61
     agradecer
    0.59
     remercier
    0.59
    Agrade
    0.58
    thank
    0.57
     the
    0.57
     ungrateful
    0.55
    Act Density 0.014%

    No Known Activations