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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the overuse or repeated use of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "use" in various contexts, indicating a focus on the concept of usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    morrow
    -0.67
     behold
    -0.67
    pton
    -0.62
    Ħ¢
    -0.61
     subdiv
    -0.60
    cffffcc
    -0.60
     crest
    -0.60
     presided
    -0.59
     reorgan
    -0.59
     stead
    -0.58
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    1.02
    FUL
    0.95
    fully
    0.92
    umes
    0.90
    fulness
    0.86
    use
    0.86
    ppe
    0.85
    ful
    0.85
    ibles
    0.82
    ibility
    0.82
    Act Density 0.011%

    No Known Activations