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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic degrees and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lich
    -0.16
    918
    -0.16
     srd
    -0.15
    aines
    -0.15
    ictionary
    -0.15
    athe
    -0.14
    isor
    -0.14
    543
    -0.14
    921
    -0.14
    ular
    -0.14
    POSITIVE LOGITS
     Wong
    0.17
     Laws
    0.16
     Science
    0.15
    alara
    0.15
     Ting
    0.15
    积
    0.14
     nominal
    0.14
     Tet
    0.14
     Integr
    0.14
     science
    0.14
    Act Density 0.012%

    No Known Activations