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

    Neuronpedia

    INDEX
    Explanations

    concepts related to identity and belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritz
    -0.15
    Æ¡
    -0.13
    uyết
    -0.13
     verge
    -0.13
    arius
    -0.13
    ajÃŃ
    -0.12
    oser
    -0.12
    regor
    -0.12
     normals
    -0.12
     resmi
    -0.12
    POSITIVE LOGITS
     inse
    0.28
     intimately
    0.27
     rooted
    0.27
     grounded
    0.26
     tied
    0.26
     founded
    0.26
     shaped
    0.26
     prem
    0.24
     informed
    0.24
     wed
    0.24
    Act Density 0.276%

    No Known Activations