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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to size and magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.64
     pêche
    -0.56
    发表于
    -0.54
    出版年
    -0.52
    colhead
    -0.50
     smtplib
    -0.49
     íntima
    -0.48
     Exacts
    -0.48
     psicológico
    -0.47
     Cabello
    -0.47
    POSITIVE LOGITS
     large
    1.08
     gigantic
    1.05
     big
    1.05
     BIG
    1.04
     giant
    1.04
    Large
    1.04
     LARGE
    1.02
     XXL
    1.01
    large
    1.00
     Large
    1.00
    Act Density 0.115%

    No Known Activations