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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "об", likely indicating a focus on measurement or quantification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.16
     pet
    -0.15
    .scala
    -0.14
    esel
    -0.14
    pta
    -0.14
    .GetInt
    -0.14
     kriz
    -0.14
    ernet
    -0.14
    cente
    -0.14
    ezi
    -0.14
    POSITIVE LOGITS
    lake
    0.16
     chang
    0.16
    itt
    0.15
    loh
    0.15
    chs
    0.15
     Morr
    0.15
    isko
    0.15
    ota
    0.15
     index
    0.14
    ijo
    0.14
    Act Density 0.002%

    No Known Activations