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

    Neuronpedia

    INDEX
    Explanations

    references to social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of media-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.82
     Aires
    -0.67
    ç
    -0.66
     vow
    -0.61
     crust
    -0.61
     bark
    -0.60
     ranged
    -0.59
     barking
    -0.59
    stood
    -0.58
     autonom
    -0.58
    POSITIVE LOGITS
    uploads
    1.02
    tenance
    0.95
    wiki
    0.92
    Images
    0.92
    img
    0.90
    gallery
    0.89
    Pic
    0.86
    henko
    0.86
    photos
    0.85
    media
    0.84
    Act Density 0.040%

    No Known Activations