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

    Neuronpedia

    INDEX
    Explanations

    keywords that describe written content, particularly focusing on the word "post"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    estial
    -0.77
     Orchestra
    -0.71
    ãĤ¤ãĥĪ
    -0.67
     bands
    -0.64
     leukemia
    -0.63
     Flavoring
    -0.62
     destro
    -0.62
     Bett
    -0.61
     Qiao
    -0.61
     TVs
    -0.61
    POSITIVE LOGITS
    mortem
    1.41
    gres
    1.37
    doctoral
    1.15
    hum
    1.12
    mort
    1.07
    greSQL
    1.03
    doc
    1.02
    natal
    1.00
    modern
    0.98
    script
    0.97
    Act Density 0.035%

    No Known Activations