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

    Neuronpedia

    INDEX
    Explanations

    embedded mentions or references in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Embed" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.84
    姫
    -0.81
    ãĥĥãĥĪ
    -0.78
    ãĥīãĥ©
    -0.78
     è£ı
    -0.76
    ãĥīãĥ©ãĤ´ãĥ³
    -0.73
    BuyableInstoreAndOnline
    -0.72
    creen
    -0.71
    gers
    -0.68
    ãĥ¼ãĥ³
    -0.68
    POSITIVE LOGITS
    arrass
    1.25
    edded
    1.20
    odied
    1.17
    argo
    1.07
    assies
    1.01
    attled
    0.99
    olicy
    0.93
    assy
    0.92
    raper
    0.92
    edd
    0.92
    Act Density 0.020%

    No Known Activations