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

    Neuronpedia

    INDEX
    Explanations

    references to a large quantity or group of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the frequency of certain experiences or sentiments shared among a group of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icut
    -0.68
    dinand
    -0.66
    moil
    -0.66
    ILA
    -0.65
    berus
    -0.63
    hern
    -0.63
     Provided
    -0.63
    ansom
    -0.60
    contained
    -0.60
     seizing
    -0.59
    POSITIVE LOGITS
     people
    1.30
     times
    1.16
     folks
    1.15
     reviewers
    1.08
     readers
    1.04
     commenters
    1.03
     guys
    1.02
     peoples
    1.01
     commentators
    1.00
     writers
    0.96
    Act Density 0.258%

    No Known Activations