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

    Neuronpedia

    INDEX
    Explanations

    references to multiple "tables" and their attributes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tura
    -0.17
    иÑĩна
    -0.16
    971
    -0.15
    883
    -0.15
    813
    -0.15
    ILLA
    -0.15
    inters
    -0.15
     Robbins
    -0.15
     taller
    -0.14
    253
    -0.14
    POSITIVE LOGITS
     mism
    0.18
     prime
    0.17
     siguientes
    0.17
    ghi
    0.17
    istrovstvÃŃ
    0.16
     últ
    0.16
    mani
    0.16
     primer
    0.16
     principales
    0.15
    andin
    0.15
    Act Density 0.012%

    No Known Activations