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

    Neuronpedia

    INDEX
    Explanations

    stories or narratives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate contrasting narratives or viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isk
    -0.70
    aband
    -0.70
    tarian
    -0.67
    tarians
    -0.65
    edition
    -0.65
    eligible
    -0.65
    poon
    -0.64
    ktop
    -0.64
     [+
    -0.63
    qus
    -0.63
    POSITIVE LOGITS
     tale
    1.63
     story
    1.63
     stories
    1.50
     tales
    1.36
     Story
    1.29
     STORY
    1.29
     truth
    1.28
     anecdote
    1.19
     truths
    1.15
     Stories
    1.14
    Act Density 0.154%

    No Known Activations