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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people, places, and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheiden
    -0.06
    оз
    -0.06
    poon
    -0.06
    brahim
    -0.06
    hammad
    -0.06
     Ùģار
    -0.06
    (){}↵
    -0.06
    isz
    -0.05
    tit
    -0.05
     Thanksgiving
    -0.05
    POSITIVE LOGITS
     latter
    0.09
    elper
    0.08
    yte
    0.08
    #'
    0.07
    .avi
    0.07
    Escort
    0.07
    ActionCreators
    0.07
    deaux
    0.06
    łéĻ¤
    0.06
    aeda
    0.06
    Act Density 0.062%

    No Known Activations