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

    Neuronpedia

    INDEX
    Explanations

    documentation-style comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [](
    -0.15
    cki
    -0.15
    enberg
    -0.15
    pill
    -0.14
     Schwartz
    -0.14
    eki
    -0.14
    amarin
    -0.14
    emonic
    -0.14
    elper
    -0.14
    gee
    -0.14
    POSITIVE LOGITS
     abs
    0.15
     Ut
    0.15
    infeld
    0.14
     round
    0.14
    کا
    0.14
    nces
    0.14
    Ī
    0.14
     Satellite
    0.13
     ag
    0.13
    icity
    0.13
    Act Density 0.007%

    No Known Activations