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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating possessiveness

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hots
    -0.85
    leans
    -0.83
    hess
    -0.81
    adobe
    -0.75
    guards
    -0.75
    mill
    -0.74
    onyms
    -0.74
    atable
    -0.72
    inker
    -0.70
    groups
    -0.70
    POSITIVE LOGITS
     own
    1.33
     credibility
    1.13
     reputation
    1.13
     ability
    1.09
     chances
    1.04
     morale
    1.03
     grasp
    1.03
     psyche
    1.01
     appetite
    1.00
     efforts
    0.99
    Act Density 0.240%

    No Known Activations