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

    Neuronpedia

    INDEX
    Explanations

    names of places and specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erker
    -0.76
    taker
    -0.75
    Ó
    -0.73
    bler
    -0.72
    blogs
    -0.72
    picking
    -0.70
    maxwell
    -0.70
    Discuss
    -0.70
    Putin
    -0.70
    sheet
    -0.68
    POSITIVE LOGITS
    ño
    1.40
    ña
    1.35
     del
    1.25
    ÃŃa
    1.24
    ón
    1.22
     Mex
    1.21
    ñ
    1.20
     Grande
    1.18
     dos
    1.17
     Portug
    1.16
    Act Density 0.240%

    No Known Activations