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

    Neuronpedia

    INDEX
    Explanations

    references to authors and contributors in literary contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     personality
    -0.15
    studio
    -0.14
    czy
    -0.14
    åĪĢ
    -0.14
    219
    -0.14
     Lap
    -0.13
     пÑĢоп
    -0.13
    秣
    -0.13
     lap
    -0.13
    549
    -0.13
    POSITIVE LOGITS
     stories
    0.23
     Stories
    0.20
     tales
    0.19
    Stories
    0.19
    stories
    0.19
     Shorts
    0.18
     anth
    0.17
     shorts
    0.17
    abcdefghijkl
    0.17
     anthology
    0.17
    Act Density 0.208%

    No Known Activations