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

    Neuronpedia

    INDEX
    Explanations

    phrases related to differentiated text-based visuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to programming and computational tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.70
    emale
    -0.67
     thous
    -0.65
    ãĥ¼ãĥĨ
    -0.63
    ilaterally
    -0.63
    ãĥĩãĤ£
    -0.60
    æµ
    -0.60
     referen
    -0.58
     helicop
    -0.58
    åĮ
    -0.57
    POSITIVE LOGITS
    CRIPTION
    0.54
     DRAGON
    0.52
    SELECT
    0.52
     largeDownload
    0.52
     DRAG
    0.50
     DARK
    0.50
     Coverage
    0.50
     Caption
    0.49
     SUPPORT
    0.49
    lement
    0.49
    Act Density 2.737%

    No Known Activations