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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Millions"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity, particularly "Mill."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redress
    -0.66
     manifest
    -0.66
     Bind
    -0.65
     fuse
    -0.64
     compelling
    -0.62
     effected
    -0.60
     Erdogan
    -0.60
     Ae
    -0.60
     reass
    -0.60
     Chak
    -0.60
    POSITIVE LOGITS
    enium
    1.74
    isec
    1.40
    ennial
    1.37
    imet
    1.35
    icent
    1.35
    imeter
    1.34
    enn
    1.26
    imeters
    1.23
    iard
    1.20
    inery
    1.17
    Act Density 0.018%

    No Known Activations