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

    Neuronpedia

    INDEX
    Explanations

    references to size, dimensions, and volume of objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tiny
    -0.59
    Tiny
    -0.57
     estrecha
    -0.55
     diminutive
    -0.54
    tiny
    -0.54
     pequenos
    -0.53
     små
    -0.52
    的小
    -0.50
     Exacts
    -0.49
    发表于
    -0.49
    POSITIVE LOGITS
     gigantic
    1.20
     big
    1.18
     giant
    1.15
     BIG
    1.12
     huge
    1.11
     XXL
    1.11
     Huge
    1.10
     large
    1.09
     massive
    1.06
     LARGE
    1.05
    Act Density 0.728%

    No Known Activations