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

    Neuronpedia

    INDEX
    Explanations

    online content sharing features such as likes, loading indicators, and other related social media buttons

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Issa
    -0.65
     Hoy
    -0.62
     Halls
    -0.60
    igans
    -0.58
    issance
    -0.58
     Oaks
    -0.57
     tant
    -0.57
    erness
    -0.57
    verages
    -0.57
    igating
    -0.56
    POSITIVE LOGITS
     guiActive
    0.89
    iframe
    0.88
    ick
    0.72
     bookmark
    0.71
     Follow
    0.70
    Stre
    0.69
     Advertisement
    0.64
    php
    0.63
    Prev
    0.62
    catentry
    0.61
    Act Density 0.040%

    No Known Activations