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

    Neuronpedia

    INDEX
    Explanations

    names of countries

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and associated numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.88
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    isson
    -0.70
    ordan
    -0.70
    ILA
    -0.68
    ocument
    -0.67
     1862
    -0.67
    ngth
    -0.66
    noon
    -0.66
    0002
    -0.65
    POSITIVE LOGITS
    Unix
    0.72
     unaff
    0.71
     Sapphire
    0.69
     forwards
    0.64
     dstg
    0.64
     Judah
    0.62
     whites
    0.60
     upside
    0.58
     Alpha
    0.58
     outer
    0.58
    Act Density 0.149%

    No Known Activations