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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tags or labeling

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific keywords or tags related to topics of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isky
    -0.78
     Seym
    -0.71
     Monetary
    -0.67
    ¬¼
    -0.65
    theless
    -0.64
     Side
    -0.62
    gow
    -0.60
     sclerosis
    -0.59
    rawdownloadcloneembedreportprint
    -0.58
     Continental
    -0.58
    POSITIVE LOGITS
    gers
    1.19
    ged
    1.15
    alog
    1.12
    gery
    1.07
    ger
    1.02
    ging
    1.01
    tag
    0.95
    tags
    0.94
    liam
    0.94
    lines
    0.93
    Act Density 0.038%

    No Known Activations