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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lie
    -0.17
    ollar
    -0.17
    tz
    -0.15
    441
    -0.15
    riad
    -0.15
    ilmington
    -0.15
    bers
    -0.14
    åĿĬ
    -0.14
    imits
    -0.14
    iating
    -0.14
    POSITIVE LOGITS
    cly
    0.28
    rophe
    0.27
     cata
    0.22
    rophic
    0.20
    comb
    0.19
    stro
    0.18
     disaster
    0.17
     catast
    0.16
    ardown
    0.16
     Cata
    0.16
    Act Density 0.007%

    No Known Activations