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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tale" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "tale" and its context in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erate
    -0.94
    bledon
    -0.85
    ividual
    -0.75
    atever
    -0.75
    ervatives
    -0.72
    apsed
    -0.70
    rotein
    -0.69
    efficients
    -0.69
    itters
    -0.68
    ussy
    -0.68
    POSITIVE LOGITS
     tales
    1.26
     tale
    1.18
    tale
    1.06
     Tales
    1.01
     Reincarn
    0.94
     Tale
    0.91
    tell
    0.88
    ttes
    0.80
    telling
    0.79
    Narr
    0.76
    Act Density 0.035%

    No Known Activations