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

    Neuronpedia

    INDEX
    Explanations

    frequent prepositions, conjunctions, and articles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    567
    -0.15
     Radiation
    -0.15
    gart
    -0.14
    wo
    -0.14
    .variant
    -0.14
    okol
    -0.14
    atern
    -0.14
    beros
    -0.14
    ña
    -0.13
    instein
    -0.13
    POSITIVE LOGITS
     vein
    0.15
    åĬ¡
    0.15
    alogy
    0.14
    addy
    0.14
    áo
    0.14
    MV
    0.14
     Cop
    0.13
    å¼ĺ
    0.13
     geil
    0.13
    UES
    0.13
    Act Density 0.001%

    No Known Activations