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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action or instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shiny
    -0.93
    YA
    -0.88
    Hung
    -0.83
    VM
    -0.81
    Yan
    -0.79
    Yu
    -0.79
     shaved
    -0.78
    hya
    -0.78
     Mahar
    -0.75
    rag
    -0.74
    POSITIVE LOGITS
     Cooper
    1.93
     Cooke
    1.47
    Cole
    1.45
     Cole
    1.44
    Co
    1.43
     Cohen
    1.38
    co
    1.29
     Coleman
    1.28
     Co
    1.24
    CO
    1.24
    Act Density 0.353%

    No Known Activations