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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undi
    -0.15
    doi
    -0.15
    uns
    -0.14
     Gors
    -0.14
    urs
    -0.14
     лÑĸк
    -0.14
    oad
    -0.14
     XX
    -0.13
    pling
    -0.13
     Fa
    -0.13
    POSITIVE LOGITS
     Kon
    0.15
    par
    0.15
     par
    0.15
    ÙĦÛĮت
    0.15
    utherland
    0.14
     inf
    0.14
    askell
    0.14
    buz
    0.14
    ekk
    0.14
    esson
    0.14
    Act Density 0.006%

    No Known Activations