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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or qualifiers that indicate uncertainty or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ¬
    -0.16
    ovu
    -0.15
    rowned
    -0.15
     ukaz
    -0.14
    ugo
    -0.14
    mpi
    -0.14
    enos
    -0.14
    .github
    -0.14
    apon
    -0.14
    iola
    -0.14
    POSITIVE LOGITS
     mo
    0.16
    åħ¨éĥ¨
    0.15
     indeed
    0.15
     entirely
    0.15
    ClientRect
    0.15
    oland
    0.14
     æģ
    0.14
    raq
    0.14
     Cl
    0.14
    rog
    0.14
    Act Density 0.049%

    No Known Activations