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

    Neuronpedia

    INDEX
    Explanations

    references to digital services and data privacy issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ori
    -0.16
    öm
    -0.15
    еж
    -0.15
    itel
    -0.15
     Harness
    -0.15
    tti
    -0.15
    awy
    -0.15
    ezi
    -0.14
    vana
    -0.14
    uku
    -0.14
    POSITIVE LOGITS
     Karlov
    0.16
    antic
    0.15
    alse
    0.15
    obuf
    0.14
    鬼
    0.14
    ilden
    0.14
    spath
    0.14
     Sachs
    0.14
    ãĥ³ãĥģ
    0.13
    -circle
    0.13
    Act Density 0.008%

    No Known Activations