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

    Neuronpedia

    INDEX
    Explanations

    references to sources or citations in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Географиясе
    -0.56
    isSuccessful
    -0.55
    SourceChecksum
    -0.53
     الاطلاع
    -0.52
     remb
    -0.52
    windowFixed
    -0.51
    userdetails
    -0.51
    、
    -0.49
    amssymb
    -0.49
    Hentet
    -0.49
    POSITIVE LOGITS
    cite
    2.92
     cite
    1.44
    Cite
    1.30
    cited
    1.24
    citep
    1.14
     Cite
    1.09
    citet
    1.05
    citation
    1.01
     citation
    0.99
     cites
    0.99
    Act Density 0.256%

    No Known Activations