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

    Neuronpedia

    INDEX
    Explanations

    concepts related to progress, community, and emotional themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Affero
    -0.16
    hai
    -0.16
    quals
    -0.15
    .scalablytyped
    -0.15
    åĬŁ
    -0.15
    WriteBarrier
    -0.14
    developers
    -0.14
    æĬ¼
    -0.14
    endforeach
    -0.14
    essler
    -0.14
    POSITIVE LOGITS
    عة
    0.16
     fur
    0.14
     thumbs
    0.14
    period
    0.14
     without
    0.14
     FUN
    0.13
    æİ
    0.13
    opor
    0.13
    /node
    0.13
    itted
    0.13
    Act Density 0.065%

    No Known Activations