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

    Neuronpedia

    INDEX
    Explanations

    technological tools and platforms

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with protection and security in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ones
    -0.64
    ussions
    -0.64
    rogens
    -0.62
     Highlander
    -0.62
    racuse
    -0.61
    stad
    -0.59
     Sections
    -0.58
    nant
    -0.56
     Moz
    -0.55
     Distribut
    -0.54
    POSITIVE LOGITS
    âĺ
    0.74
    ĸļ
    0.72
    eworld
    0.72
    mma
    0.72
     selves
    0.72
    é¾įåĸļ士
    0.68
    adle
    0.64
    ultimate
    0.64
    ãĥ¯
    0.63
     spree
    0.62
    Act Density 0.542%

    No Known Activations