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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and scholarly articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TestFixture
    -0.15
    utt
    -0.15
    rov
    -0.14
    iaux
    -0.14
    akk
    -0.13
    wo
    -0.13
     заÑĤ
    -0.13
    /documentation
    -0.13
    ķ
    -0.13
     fit
    -0.13
    POSITIVE LOGITS
     Journal
    0.32
    Journal
    0.28
     journal
    0.21
     Forum
    0.19
     Studies
    0.19
     Review
    0.18
    ournal
    0.18
     Signs
    0.17
    journal
    0.17
    boundary
    0.17
    Act Density 0.044%

    No Known Activations