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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to autographs

    oai_token-act-pair · gpt-3.5-turbo

    references to autographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.80
    imaru
    -0.79
    IRO
    -0.77
    BLE
    -0.73
     Soda
    -0.71
    UTION
    -0.70
    BE
    -0.69
    ORK
    -0.69
     Passage
    -0.68
    edin
    -0.67
    POSITIVE LOGITS
    ographs
    1.26
    ograph
    1.23
    opsy
    1.11
    ographed
    1.08
    umn
    1.07
    ogyn
    1.01
    ocom
    1.00
    iques
    0.99
    oly
    0.98
    istically
    0.98
    Act Density 0.016%

    No Known Activations