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

    Neuronpedia

    INDEX
    Explanations

    words related to labeling or marking

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tag"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miscarriage
    -0.73
     Lumpur
    -0.72
    theless
    -0.71
    sburgh
    -0.71
    undai
    -0.70
    ITNESS
    -0.70
     Cox
    -0.70
    isky
    -0.67
     Ell
    -0.64
     unfocusedRange
    -0.64
    POSITIVE LOGITS
     tag
    1.09
     tags
    1.02
    tag
    0.94
    otle
    0.92
    alog
    0.87
    tags
    0.87
    gers
    0.87
    Tag
    0.85
     Tag
    0.84
    masters
    0.80
    Act Density 0.007%

    No Known Activations