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

    Neuronpedia

    INDEX
    Explanations

    personal stories or dialogues involving emotional or interpersonal interactions

    oai_token-act-pair · gpt-3.5-turbo

    distinct personal pronouns and references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Citation
    -0.75
    terness
    -0.72
    htaking
    -0.69
    payers
    -0.68
    tesy
    -0.67
    geries
    -0.64
    ocre
    -0.64
    cussion
    -0.63
    gate
    -0.62
    een
    -0.61
    POSITIVE LOGITS
     own
    1.04
     intend
    0.75
     wished
    0.72
     intention
    0.71
     favoured
    0.70
     hoped
    0.70
     subscribed
    0.68
    Shares
    0.66
     OWN
    0.65
     wish
    0.65
    Act Density 0.793%

    No Known Activations