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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and contextually relevant keywords related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aura
    -0.17
    ignKey
    -0.16
    ront
    -0.16
    otch
    -0.15
    .vars
    -0.15
    ullan
    -0.14
    icensed
    -0.14
    arf
    -0.14
    adero
    -0.13
    पत
    -0.13
    POSITIVE LOGITS
     Bor
    0.15
    êu
    0.14
    [Unit
    0.14
    γη
    0.14
     agre
    0.14
    ugg
    0.14
    Attempt
    0.13
    pedia
    0.13
     incons
    0.13
    .rmi
    0.13
    Act Density 0.318%

    No Known Activations