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

    Neuronpedia

    INDEX
    Explanations

    words related to manufacturing processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ures" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     staff
    -0.58
     loyal
    -0.58
     Goo
    -0.58
     Brother
    -0.57
     complex
    -0.57
     specific
    -0.56
     cruc
    -0.56
     Colomb
    -0.55
     else
    -0.54
     trivia
    -0.54
    POSITIVE LOGITS
    ures
    4.85
    URES
    2.90
    ure
    2.79
    ured
    2.74
    uring
    2.60
    URE
    2.48
    urers
    2.32
    urer
    1.95
    ural
    1.93
    urally
    1.87
    Act Density 0.006%

    No Known Activations