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

    Neuronpedia

    INDEX
    Explanations

    instances of significant themes or motifs related to narratives and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*---
    -0.50
    bitField
    -0.40
     Books
    -0.39
    Books
    -0.39
    省市镇
    -0.37
    scriptcase
    -0.36
    Edm
    -0.36
    uxxxx
    -0.36
     digress
    -0.36
    الإنجليزية
    -0.35
    POSITIVE LOGITS
     opening
    0.85
     title
    0.76
    opening
    0.66
     central
    0.65
     titular
    0.61
     premise
    0.60
     titel
    0.59
     plot
    0.58
     narrative
    0.57
     text
    0.57
    Act Density 0.437%

    No Known Activations