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

    Neuronpedia

    INDEX
    Explanations

    the word "pernicious."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.82
    enegger
    -0.66
    ForgeModLoader
    -0.66
     shortened
    -0.64
     Bonds
    -0.64
    MpServer
    -0.63
    ARDIS
    -0.61
     Wag
    -0.61
     Raleigh
    -0.60
     Lazarus
    -0.60
    POSITIVE LOGITS
    tains
    1.39
     capita
    1.36
    malink
    1.21
    tained
    1.15
    missive
    1.12
    chance
    1.10
    tain
    1.10
    verting
    1.06
    severe
    1.05
    ishable
    1.05
    Act Density 0.027%

    No Known Activations