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

    Neuronpedia

    INDEX
    Explanations

    references to popular science fiction franchises and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trilogy
    -0.14
    anst
    -0.14
    leh
    -0.14
    668
    -0.14
    eo
    -0.14
    165
    -0.14
    259
    -0.14
     Trom
    -0.13
    amedi
    -0.13
    799
    -0.13
    POSITIVE LOGITS
     tie
    0.34
     Tie
    0.29
    tie
    0.27
     spin
    0.25
     oficial
    0.24
     Official
    0.23
     official
    0.23
     authorized
    0.22
    Official
    0.22
    spin
    0.21
    Act Density 0.147%

    No Known Activations