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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases indicating measurements, quantities, or references to physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Medi
    -0.15
    ãĥ³ãĥĪ
    -0.15
    abin
    -0.15
    ,
    -0.15
     below
    -0.14
    rosse
    -0.14
     Blanch
    -0.14
     Hood
    -0.14
     Econom
    -0.14
    ajs
    -0.14
    POSITIVE LOGITS
    ymax
    0.18
    æĭĶ
    0.15
    ENTION
    0.15
    Maintenance
    0.15
    ismatch
    0.15
    .exit
    0.14
    à¤¾à¤Ł
    0.14
    clist
    0.14
    838
    0.14
    _MAC
    0.14
    Act Density 0.014%

    No Known Activations