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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns indicating specific objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    воÑĢ
    -0.17
    aji
    -0.17
    onym
    -0.16
     phong
    -0.16
    ophon
    -0.15
     пой
    -0.15
    elda
    -0.14
    endor
    -0.14
    adoo
    -0.14
    odiac
    -0.14
    POSITIVE LOGITS
     regard
    0.40
     regards
    0.37
     instance
    0.31
     case
    0.29
     respect
    0.28
     respects
    0.28
     vein
    0.25
     context
    0.25
    respect
    0.24
    instance
    0.23
    Act Density 0.067%

    No Known Activations