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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "cloaking" and variations of "Cloister" or similar terms like "clo" with a high emphasis on "Clo"ister

    oai_token-act-pair · gpt-3.5-turbo

    references to cloaking in various contexts, particularly involving the name "Clooney" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymes
    -0.72
    Murray
    -0.71
    itar
    -0.68
    ews
    -0.65
    gerald
    -0.64
    DEV
    -0.64
    tery
    -0.63
    sen
    -0.62
    izoph
    -0.61
    rators
    -0.60
    POSITIVE LOGITS
     Clo
    1.05
     Cloak
    0.89
     clo
    0.86
    robe
    0.86
    acas
    0.81
    istered
    0.79
    pless
    0.78
    wen
    0.77
    crow
    0.75
    heed
    0.75
    Act Density 0.014%

    No Known Activations