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

    Neuronpedia

    INDEX
    Explanations

    references to advanced degrees or qualifications in specific fields of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oker
    -0.15
    æ¶Ī
    -0.14
    aby
    -0.14
    ungeon
    -0.14
    nell
    -0.13
    erdale
    -0.13
    анÑĤаж
    -0.13
     اÙĦÙħغ
    -0.13
    ais
    -0.13
    tester
    -0.13
    POSITIVE LOGITS
     degree
    0.27
    -level
    0.26
    -degree
    0.25
     degrees
    0.23
    degree
    0.23
    /master
    0.22
    mind
    0.22
     Degree
    0.21
     level
    0.20
    -Level
    0.19
    Act Density 0.013%

    No Known Activations