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

    Neuronpedia

    INDEX
    Explanations

    mentions of various types of "other" categories and miscellaneous items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.16
    ushi
    -0.15
    sst
    -0.15
    sted
    -0.15
    agem
    -0.15
    hare
    -0.14
    urf
    -0.14
    ãĥĮ
    -0.14
    leur
    -0.13
    ullah
    -0.13
    POSITIVE LOGITS
    ellaneous
    0.22
     Weiss
    0.17
     Fleet
    0.16
    /misc
    0.15
     nth
    0.15
    idon
    0.14
    Wis
    0.14
    vise
    0.14
    WE
    0.14
     fleet
    0.14
    Act Density 0.073%

    No Known Activations