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

    Neuronpedia

    INDEX
    Explanations

    dates and organizational information

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that are empty or lacking content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     worrying
    -0.69
     shove
    -0.66
     deciding
    -0.66
     tooth
    -0.62
     offerings
    -0.62
     schemes
    -0.62
     branches
    -0.61
     suspending
    -0.61
     gearing
    -0.61
     proble
    -0.60
    POSITIVE LOGITS
    utterstock
    0.92
    Anonymous
    0.90
    photos
    0.87
    ickr
    0.80
    HY
    0.80
    ipedia
    0.79
    cerpt
    0.78
    abetic
    0.78
    Review
    0.78
    Blog
    0.78
    Act Density 0.281%

    No Known Activations