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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating less intensity or quantity

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

    less quantity or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.48
     ComVisible
    -0.46
    PreferredItem
    -0.45
    Portail
    -0.44
    GEBURTSDATUM
    -0.41
     Rathaus
    -0.41
     parseFrom
    -0.40
     ویکی‌پدیا
    -0.40
     
    -0.39
    bodyParser
    -0.38
    POSITIVE LOGITS
    Smaller
    0.81
     weaker
    0.81
     smaller
    0.81
     less
    0.77
     shorter
    0.77
    smaller
    0.76
     lesser
    0.75
     Less
    0.73
    Less
    0.73
     Smaller
    0.71
    Act Density 0.081%

    No Known Activations