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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "large" and its variations, indicating a focus on significant quantities or sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.69
     classNames
    -0.60
     ActionListener
    -0.58
    awin
    -0.58
     chrono
    -0.57
     kaarangay
    -0.57
     TimeUnit
    -0.56
     Odyssey
    -0.55
    AppMethodBeat
    -0.55
     checksum
    -0.55
    POSITIVE LOGITS
     large
    1.50
    Large
    1.46
     Large
    1.45
    large
    1.40
     LARGE
    1.34
    LARGE
    1.22
     larger
    0.98
     larges
    0.94
     Larger
    0.93
     largest
    0.91
    Act Density 0.148%

    No Known Activations