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

    Neuronpedia

    INDEX
    Explanations

    dates or time intervals represented in a specific format with arrows in between

    oai_token-act-pair · gpt-3.5-turbo

    the presence of unique symbols or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urn
    -0.83
    bryce
    -0.72
    opher
    -0.70
     nodd
    -0.68
     insect
    -0.67
     wedd
    -0.64
    Ļ½
    -0.63
    ©¶æ
    -0.63
    ike
    -0.63
     herb
    -0.63
    POSITIVE LOGITS
    ––
    0.78
    âĢ¢âĢ¢
    0.70
     Vulkan
    0.70
     Introduction
    0.70
     RTX
    0.69
     Jere
    0.69
     Dalai
    0.68
     Pesh
    0.64
     Puerto
    0.64
    batch
    0.64
    Act Density 0.041%

    No Known Activations