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

    Neuronpedia

    INDEX
    Explanations

    timestamps or dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "posted" and related terms indicating publication dates or editing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.80
    rium
    -0.67
    ovan
    -0.66
    knit
    -0.64
    oter
    -0.62
    acl
    -0.61
    rouse
    -0.60
    quin
    -0.60
    zos
    -0.60
    gars
    -0.59
    POSITIVE LOGITS
     Next
    0.70
    Published
    0.62
    Lear
    0.61
    icio
    0.61
     Manga
    0.60
    javascript
    0.60
     Posts
    0.59
    Jump
    0.58
    Tue
    0.57
     Posted
    0.57
    Act Density 0.055%

    No Known Activations