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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "protection"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of protection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bold
    -0.70
    ãĥ£
    -0.70
    mers
    -0.68
    nexus
    -0.63
     Kinn
    -0.63
    hig
    -0.63
    hler
    -0.58
    leaf
    -0.58
    earch
    -0.58
    sonian
    -0.58
    POSITIVE LOGITS
    ively
    1.00
    iveness
    0.97
     afforded
    0.95
    ously
    0.84
    aments
    0.80
    folios
    0.79
     against
    0.79
    dogs
    0.78
    ective
    0.77
    atively
    0.77
    Act Density 0.043%

    No Known Activations