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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal qualifications and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     backs
    -0.18
    entes
    -0.17
    ente
    -0.16
    ebb
    -0.16
     Quinn
    -0.15
    esin
    -0.15
    ights
    -0.15
    hip
    -0.15
     Ruf
    -0.14
    ighton
    -0.14
    POSITIVE LOGITS
    éĹª
    0.16
    utters
    0.16
    ewise
    0.15
    лÑĸÑĤ
    0.15
    lendir
    0.15
    FLOW
    0.15
    ãĤ
    0.15
    trait
    0.14
    referer
    0.14
    ÏĢÏīÏĤ
    0.14
    Act Density 0.000%

    No Known Activations