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

    Neuronpedia

    INDEX
    Explanations

    words related to laws, discipline, and organization

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Dis" or its variations, often associated with notions of disappointment or disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kinnikuman
    -0.68
     hell
    -0.64
     Osw
    -0.63
    glers
    -0.62
    DragonMagazine
    -0.59
     Lans
    -0.59
     Deer
    -0.59
     Metatron
    -0.58
     Klaus
    -0.58
    mint
    -0.58
    POSITIVE LOGITS
    cipl
    1.26
    comfort
    1.25
    claimer
    1.24
    enfranch
    1.22
    cerning
    1.21
    ruption
    1.20
    qus
    1.13
    dain
    1.12
    plays
    1.12
    puted
    1.12
    Act Density 0.019%

    No Known Activations