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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official procedures or requests

    oai_token-act-pair · gpt-3.5-turbo

    references to formal processes or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.91
    =-=-=-=-=-=-=-=-
    -0.79
    Phones
    -0.71
     Expand
    -0.70
    RH
    -0.69
    ONES
    -0.66
     Indies
    -0.65
     maniac
    -0.65
    ï¸
    -0.64
    nesota
    -0.63
    POSITIVE LOGITS
    ities
    1.33
    ized
    1.14
    ised
    1.01
    isations
    0.95
    izing
    0.92
     complaint
    0.92
     formal
    0.91
    ité
    0.91
    ization
    0.91
    izations
    0.90
    Act Density 0.031%

    No Known Activations