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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "per" within the text

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "per" in various forms or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.87
     Lazarus
    -0.70
    enegger
    -0.68
    ARDIS
    -0.66
    ForgeModLoader
    -0.64
    MpServer
    -0.64
     Plague
    -0.63
     makers
    -0.61
     Boots
    -0.61
     Scholars
    -0.61
    POSITIVE LOGITS
     capita
    1.35
    tains
    1.17
    missive
    1.09
    ishable
    1.07
    malink
    1.05
    verting
    1.02
    severe
    1.01
    tained
    0.99
    secut
    0.98
    verted
    0.95
    Act Density 0.027%

    No Known Activations