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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being shared or published online, such as on social media platforms like YouTube or Facebook

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "posted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galile
    -0.69
    kos
    -0.68
    inho
    -0.66
    idge
    -0.65
     Gand
    -0.65
     Nebula
    -0.64
    glers
    -0.64
    phant
    -0.64
    abe
    -0.63
    ão
    -0.63
    POSITIVE LOGITS
    ulate
    0.92
    hum
    0.91
    posted
    0.86
    gres
    0.86
    uploads
    0.85
    doctoral
    0.84
     postings
    0.80
     posting
    0.80
    URL
    0.75
    aptic
    0.75
    Act Density 0.027%

    No Known Activations