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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and possessive forms related to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.73
    hedon
    -0.72
     partName
    -0.68
    itect
    -0.68
    isite
    -0.68
    intendo
    -0.67
    NOW
    -0.67
    phans
    -0.67
    Insert
    -0.67
    hedral
    -0.67
    POSITIVE LOGITS
     illeg
    0.68
     suspicious
    0.67
     weakness
    0.65
     footsteps
    0.65
     nonexistent
    0.64
     personally
    0.63
    din
    0.62
     gobl
    0.61
     uncond
    0.61
     tex
    0.60
    Act Density 0.638%

    No Known Activations