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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical and computational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allery
    -0.15
    iyat
    -0.15
    achts
    -0.15
     Congo
    -0.14
    .Expression
    -0.14
     Maritime
    -0.14
    İ
    -0.13
     Pax
    -0.13
     tran
    -0.13
    rowse
    -0.13
    POSITIVE LOGITS
    жд
    0.16
    stral
    0.16
    ManagerInterface
    0.15
    erate
    0.15
    ãĥ¼ãĥī
    0.14
    opsy
    0.14
    azzi
    0.14
    atron
    0.14
    天åłĤ
    0.14
    ायल
    0.14
    Act Density 0.005%

    No Known Activations