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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of significance or emphasis

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

    better and best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.69
    ロウィン
    -0.65
    principalColumn
    -0.65
    ﹧
    -0.63
    iſchen
    -0.63
     ſont
    -0.61
    RenderAtEndOf
    -0.60
    xiety
    -0.60
     queſto
    -0.59
     Lightboxes
    -0.59
    POSITIVE LOGITS
     Better
    0.57
    Better
    0.54
     better
    0.48
     best
    0.46
     BETTER
    0.44
    better
    0.43
     enjoy
    0.43
     besser
    0.42
     enjoyed
    0.41
     Best
    0.40
    Act Density 0.004%

    No Known Activations