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

    Neuronpedia

    INDEX
    Explanations

    themes related to relationships and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.16
    swire
    -0.16
    	freopen
    -0.15
     overthrow
    -0.15
    irty
    -0.14
    rvine
    -0.14
    ساÙĨ
    -0.14
     à¤ĸड
    -0.14
    rtle
    -0.14
    raç
    -0.14
    POSITIVE LOGITS
     Boxing
    0.17
     lately
    0.17
     narrator
    0.16
     bestselling
    0.16
    .Management
    0.14
     isolated
    0.14
     Blitz
    0.14
     Prosper
    0.14
    isol
    0.14
    384
    0.14
    Act Density 0.174%

    No Known Activations