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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical references, particularly highlighting the significance of specific quantities or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åħ¥ãĤĮ
    -0.14
    lesc
    -0.13
     spr
    -0.13
    976
    -0.13
    -tier
    -0.13
    oundingBox
    -0.12
     lint
    -0.12
    oci
    -0.12
    bsd
    -0.12
    igrams
    -0.12
    POSITIVE LOGITS
     among
    0.31
    among
    0.28
     Among
    0.26
    ä¹ĭä¸Ģ
    0.26
    Among
    0.24
     amongst
    0.24
     many
    0.24
    many
    0.22
     numerous
    0.20
    -many
    0.20
    Act Density 0.083%

    No Known Activations