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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns related to individuals involved in incidents or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noses
    -0.19
     Deaths
    -0.17
     yourselves
    -0.17
     personalities
    -0.17
     selves
    -0.16
     Bodies
    -0.15
     Lives
    -0.15
    fad
    -0.15
    annies
    -0.14
    yms
    -0.14
    POSITIVE LOGITS
     story
    0.25
     wife
    0.21
     case
    0.20
     situation
    0.20
     remains
    0.20
     movements
    0.20
     name
    0.20
     lawyer
    0.20
     condition
    0.19
     son
    0.18
    Act Density 0.268%

    No Known Activations