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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and associated third-person references in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.64
    aware
    -0.63
     Warehouse
    -0.62
    ivot
    -0.61
    geoning
    -0.60
    othy
    -0.60
    Db
    -0.59
     WP
    -0.57
    catentry
    -0.56
    Hung
    -0.56
    POSITIVE LOGITS
     bluff
    0.68
    ãĢİ
    0.67
    =\"
    0.63
     STORY
    0.62
    ITIES
    0.62
    acci
    0.61
     stories
    0.61
    ="#
    0.61
     goodbye
    0.61
     "#
    0.61
    Act Density 0.187%

    No Known Activations