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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions indicating similarity or sameness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     secondary
    -0.15
    497
    -0.15
     g
    -0.15
     reck
    -0.15
     Vit
    -0.15
    ata
    -0.14
     Vitamin
    -0.14
     Stroke
    -0.14
    471
    -0.14
    Stroke
    -0.14
    POSITIVE LOGITS
    ucha
    0.15
    ÏĢη
    0.14
    ovel
    0.14
    nerg
    0.14
    anchors
    0.14
    nodoc
    0.14
    acas
    0.13
    otten
    0.13
    FileSync
    0.13
     Goods
    0.13
    Act Density 0.132%

    No Known Activations