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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edly
    -0.18
     addCriterion
    -0.18
    vk
    -0.16
    era
    -0.16
    acre
    -0.15
    plex
    -0.15
    erus
    -0.15
    ίοÏĤ
    -0.15
    arin
    -0.15
    ensions
    -0.15
    POSITIVE LOGITS
    ta
    0.35
     onto
    0.23
    tah
    0.21
    TA
    0.20
     khá»ıi
    0.20
    onto
    0.19
     Ont
    0.18
    tas
    0.18
     alive
    0.18
     Alive
    0.16
    Act Density 0.050%

    No Known Activations