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

    Neuronpedia

    INDEX
    Explanations

    sections related to a rush transcript or final form of a document

    oai_token-act-pair · gpt-3.5-turbo

    references to the completeness or status of documents and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    less
    -0.70
    chall
    -0.68
    lessness
    -0.64
    rather
    -0.64
     misunderstanding
    -0.61
     rather
    -0.61
     Puzz
    -0.60
    gone
    -0.58
     differe
    -0.58
    ortment
    -0.58
    POSITIVE LOGITS
    thumbnails
    0.80
     subtitles
    0.69
     previews
    0.69
    umbnails
    0.69
     editing
    0.67
     yet
    0.66
    yet
    0.64
     fonts
    0.61
    interstitial
    0.60
     transcription
    0.60
    Act Density 0.065%

    No Known Activations