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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and their associated nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    312
    -0.16
     Experience
    -0.16
     things
    -0.15
     Choice
    -0.15
    ans
    -0.14
    eg
    -0.14
    Experience
    -0.14
    Choice
    -0.14
     Things
    -0.14
     Ones
    -0.14
    POSITIVE LOGITS
     contents
    0.28
    lef
    0.28
     existence
    0.27
    contents
    0.25
    ’
    0.25
    '
    0.24
     origins
    0.24
     inception
    0.22
    existence
    0.22
     entirety
    0.21
    Act Density 0.310%

    No Known Activations