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

    Neuronpedia

    INDEX
    Explanations

    references to publications or reports

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "publication."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olulu
    -0.80
    eric
    -0.78
    yg
    -0.73
    othes
    -0.73
    inho
    -0.72
    VC
    -0.70
    zh
    -0.70
    usc
    -0.70
    hart
    -0.69
     helic
    -0.68
    POSITIVE LOGITS
    lisher
    1.14
    lishing
    0.98
    lishes
    0.94
     publication
    0.86
    DragonMagazine
    0.83
     Publishers
    0.81
     publishes
    0.79
    代
    0.76
     Publication
    0.75
     RELEASE
    0.72
    Act Density 0.008%

    No Known Activations