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

    Neuronpedia

    INDEX
    Explanations

    references to "dep" or "Dep" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "deportation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥij
    -0.68
    Interstitial
    -0.63
     Pose
    -0.61
    é¾įåĸļ士
    -0.61
     boom
    -0.60
    ç¥ŀ
    -0.58
     Rhodes
    -0.58
     Rebellion
    -0.58
     Tens
    -0.58
    FORE
    -0.57
    POSITIVE LOGITS
    artments
    1.43
    uties
    1.41
    recated
    1.40
    uty
    1.35
    osit
    1.34
    osition
    1.33
    ravity
    1.32
    arted
    1.32
    raved
    1.32
    ository
    1.30
    Act Density 0.032%

    No Known Activations