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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or proper noun phrases in sentences containing trivial information or news

    oai_token-act-pair · gpt-3.5-turbo

    instances of numbers and symbols related to data or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istries
    -0.66
     Misty
    -0.64
    keye
    -0.63
    izo
    -0.63
    heet
    -0.62
     Ally
    -0.61
     Rush
    -0.60
    ura
    -0.60
    uro
    -0.59
    ierre
    -0.59
    POSITIVE LOGITS
    [/
    0.78
    anwhile
    0.77
    à¼
    0.68
    Mex
    0.67
    didn
    0.67
    EStream
    0.67
    cum
    0.67
    Contract
    0.67
    ß
    0.66
    wait
    0.65
    Act Density 0.169%

    No Known Activations