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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Read" indicating requests for further information or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anner
    -0.17
    ĭ
    -0.17
    ples
    -0.17
    eldorf
    -0.16
    ped
    -0.15
    alf
    -0.15
    asc
    -0.15
    adows
    -0.14
    buie
    -0.14
    Reader
    -0.14
    POSITIVE LOGITS
    ings
    0.25
    mission
    0.24
     more
    0.23
    ying
    0.23
    ily
    0.23
    ers
    0.23
     More
    0.20
    iness
    0.20
    ym
    0.19
    missions
    0.18
    Act Density 0.015%

    No Known Activations