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

    Neuronpedia

    INDEX
    Explanations

    legal and judicial terminology

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geries
    -0.65
     unconscious
    -0.64
    è¦ļéĨĴ
    -0.62
     abstinence
    -0.62
     ducks
    -0.61
     bluff
    -0.61
     scissors
    -0.61
     undecided
    -0.59
     assemb
    -0.59
    berman
    -0.59
    POSITIVE LOGITS
    tml
    0.77
     Ensure
    0.74
    tab
    0.73
    vor
    0.73
    externalActionCode
    0.73
    Compare
    0.73
    âĶĢ
    0.72
     =================================================================
    0.71
     Likewise
    0.70
    İ
    0.69
    Act Density 0.259%

    No Known Activations