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

    Neuronpedia

    INDEX
    Explanations

    words related to physical attachment or connection

    oai_token-act-pair · gpt-3.5-turbo

    references to structural components and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ull
    -0.66
    alm
    -0.65
    marg
    -0.64
    è¦ļéĨĴ
    -0.63
    vind
    -0.63
    Hunt
    -0.62
    kees
    -0.62
     anecd
    -0.61
    arna
    -0.60
    Edited
    -0.60
    POSITIVE LOGITS
     everything
    0.69
     denote
    0.68
     conve
    0.66
     transmitting
    0.66
    interstitial
    0.65
     entrances
    0.65
    rium
    0.64
     signify
    0.64
     anch
    0.64
    ESA
    0.63
    Act Density 0.364%

    No Known Activations