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

    Neuronpedia

    INDEX
    Explanations

    references to different editions of a publication

    oai_token-act-pair · gpt-3.5-turbo

    various editions of publications or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oted
    -0.74
     blat
    -0.68
    bors
    -0.67
    mercial
    -0.67
    asive
    -0.65
    apped
    -0.63
    amera
    -0.63
    jab
    -0.63
    ayers
    -0.62
    pload
    -0.62
    POSITIVE LOGITS
     thereof
    0.76
     edition
    0.75
    velop
    0.71
     Cullen
    0.70
     EDITION
    0.68
    ansion
    0.68
    edition
    0.64
    DragonMagazine
    0.64
    ARCH
    0.62
    osaurus
    0.62
    Act Density 0.023%

    No Known Activations