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

    Neuronpedia

    INDEX
    Explanations

    birthplaces and birthdates of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ologies
    -0.76
     Extend
    -0.76
    lag
    -0.73
    Includes
    -0.71
    Duration
    -0.67
     Which
    -0.66
    rates
    -0.66
    lies
    -0.66
     Compare
    -0.65
    ¨
    -0.64
    POSITIVE LOGITS
     born
    1.56
     diagnosed
    1.19
     baptized
    1.13
     arrested
    1.13
     sentenced
    1.10
     assassinated
    1.09
     recruited
    1.08
     murdered
    1.07
     ordained
    1.07
     bitten
    1.06
    Act Density 0.218%

    No Known Activations