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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structured elements in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hollow
    -0.15
     Bol
    -0.14
     Leader
    -0.14
     drivers
    -0.14
    ills
    -0.13
    ling
    -0.13
     Pro
    -0.13
    ouz
    -0.13
    tr
    -0.13
    addock
    -0.13
    POSITIVE LOGITS
    ENCHMARK
    0.15
    -dess
    0.15
    pNet
    0.15
     discrepan
    0.15
    ULER
    0.15
     ÙħاÙĦ
    0.15
    ONGO
    0.15
    UNET
    0.15
    åĿĬ
    0.14
    -LAST
    0.14
    Act Density 1.667%

    No Known Activations