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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "people" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to the increase in population or the involvement of people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lazarus
    -0.72
    CHAT
    -0.72
    ij士
    -0.70
    cknow
    -0.70
     Abdel
    -0.68
     McDonnell
    -0.62
    eston
    -0.61
     Whip
    -0.61
     Griffith
    -0.60
     Begin
    -0.60
    POSITIVE LOGITS
     than
    1.46
    than
    1.08
     Than
    0.85
    catentry
    0.85
    efficient
    0.77
     besides
    0.74
    worthy
    0.71
    erous
    0.71
    osponsors
    0.70
     hassle
    0.69
    Act Density 0.244%

    No Known Activations