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

    Neuronpedia

    INDEX
    Explanations

    first person singular verbs followed by personal pronouns

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences with media consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     negotiators
    -0.76
    assert
    -0.75
     Assist
    -0.75
     deterrence
    -0.75
     Workers
    -0.73
     jurisd
    -0.73
    Merit
    -0.72
    Position
    -0.71
     assurances
    -0.70
    andowski
    -0.70
    POSITIVE LOGITS
     binge
    1.39
    favorite
    1.17
     watched
    1.16
    watching
    1.16
     obsessed
    1.15
     subscribed
    1.14
     favorites
    1.12
    Favorite
    1.11
     liking
    1.11
     loved
    1.10
    Act Density 0.536%

    No Known Activations