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

    Neuronpedia

    INDEX
    Explanations

    expressions related to programming and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nor
    -0.15
    ellow
    -0.14
    inar
    -0.14
    yt
    -0.14
    âĨĴ
    -0.14
     fellow
    -0.14
    neh
    -0.14
    ixel
    -0.13
    #ga
    -0.13
     Inbox
    -0.13
    POSITIVE LOGITS
     ==
    0.50
     ===
    0.32
    ==
    0.31
     ==↵
    0.29
     equals
    0.26
    ()==
    0.24
    =="
    0.23
     equal
    0.23
     !=
    0.22
    =='
    0.22
    Act Density 0.130%

    No Known Activations