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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases about abilities or features of products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avra
    -0.17
    ostel
    -0.16
    RowCount
    -0.16
    olon
    -0.15
    odb
    -0.15
    uges
    -0.14
    acic
    -0.14
    uktur
    -0.14
    μει
    -0.14
    roman
    -0.14
    POSITIVE LOGITS
     ideal
    0.22
     overall
    0.21
     stand
    0.20
     Ideal
    0.19
     appear
    0.19
    Ideal
    0.18
     imperative
    0.17
     seem
    0.16
    appear
    0.16
     stands
    0.16
    Act Density 0.059%

    No Known Activations