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

    Neuronpedia

    INDEX
    Explanations

    forms of the word "as" indicating comparisons or parallels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caf
    -0.16
     Que
    -0.15
     hier
    -0.15
    .Atomic
    -0.15
    imbledon
    -0.15
     evidenced
    -0.15
    |int
    -0.14
    uya
    -0.14
    ç´į
    -0.14
    zeug
    -0.14
    POSITIVE LOGITS
    ereotype
    0.15
     ÐĴики
    0.14
    à¹īà¸ĩ
    0.14
    -fetch
    0.14
    SBATCH
    0.14
     spear
    0.14
    graf
    0.14
    bsolute
    0.14
    ãĥĥ
    0.13
    lod
    0.13
    Act Density 0.048%

    No Known Activations