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

    Neuronpedia

    INDEX
    Explanations

    references to academic awards and recognitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arium
    -0.16
    itecture
    -0.15
     anthrop
    -0.15
    quarters
    -0.14
     tieten
    -0.14
    masters
    -0.14
    ucch
    -0.14
     ê°¤
    -0.13
    onga
    -0.13
    anten
    -0.13
    POSITIVE LOGITS
     hab
    0.21
     reviewer
    0.18
     Else
    0.18
    Reviewer
    0.18
     Hab
    0.17
    hab
    0.17
     COST
    0.16
    Tutorial
    0.16
     Scientist
    0.16
     Guest
    0.16
    Act Density 0.031%

    No Known Activations