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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases related to diverse topics and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.82
     Included
    -0.75
     Provided
    -0.73
     duly
    -0.70
     supplied
    -0.68
    contained
    -0.68
     Recall
    -0.66
    è¦ļéĨĴ
    -0.66
    Detailed
    -0.66
    Excellent
    -0.65
    POSITIVE LOGITS
     people
    1.22
     guys
    1.21
     kids
    1.17
     rappers
    1.14
     girls
    1.11
     everybody
    1.10
     moms
    1.08
     comedians
    1.06
     teenagers
    1.05
     athletes
    1.04
    Act Density 0.439%

    No Known Activations