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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "you" emphasizing direct address or engagement with the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stadt
    -0.69
     Hyde
    -0.65
    former
    -0.64
    grave
    -0.62
     Quarterly
    -0.61
    kamp
    -0.61
    hover
    -0.60
     Verge
    -0.60
    acca
    -0.60
    iday
    -0.58
    POSITIVE LOGITS
    're
    1.40
     guys
    1.35
    've
    1.17
     gotta
    1.08
    'll
    0.96
    tub
    0.96
     guessed
    0.94
     realize
    0.89
    ngth
    0.88
    'd
    0.87
    Act Density 0.202%

    No Known Activations