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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns ("your", "their") followed by possessive nouns related to a strategic card game

    oai_token-act-pair · gpt-3.5-turbo

    references to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vertisements
    -0.70
    urb
    -0.70
    terms
    -0.69
    Å¡
    -0.69
    atable
    -0.68
    ingham
    -0.68
    bill
    -0.68
    itutional
    -0.68
     Pulitzer
    -0.68
    ocument
    -0.66
    POSITIVE LOGITS
     teammates
    1.24
     opponent
    1.24
     teammate
    1.13
     opponents
    1.08
     own
    1.01
     arsenal
    1.01
     avatar
    0.99
     faction
    0.96
     squad
    0.96
     allies
    0.95
    Act Density 0.107%

    No Known Activations