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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and their indexing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isbury
    -0.16
     comfort
    -0.15
    kou
    -0.15
     truth
    -0.15
    /client
    -0.14
    agnost
    -0.14
    truth
    -0.14
     rud
    -0.14
    ismatic
    -0.14
     Stout
    -0.14
    POSITIVE LOGITS
     Citation
    0.29
     citation
    0.28
     citations
    0.27
     Cit
    0.26
     cit
    0.23
     cita
    0.23
     Eigen
    0.22
     citas
    0.22
     cites
    0.22
    citation
    0.21
    Act Density 0.009%

    No Known Activations