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

    Neuronpedia

    INDEX
    Explanations

    political and news-related terms and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,[
    -0.59
    FTWARE
    -0.56
    lication
    -0.54
     Valve
    -0.53
     Metall
    -0.51
    viation
    -0.48
     dressing
    -0.48
    stones
    -0.47
    ministic
    -0.47
     setting
    -0.47
    POSITIVE LOGITS
     WATCHED
    0.87
     HuffPost
    0.81
     VIDEOS
    0.81
     UNCLASSIFIED
    0.81
    <|endoftext|>
    0.78
     Advertisement
    0.77
    News
    0.77
    cerpt
    0.77
     Comments
    0.76
     Shutterstock
    0.75
    Act Density 0.719%

    No Known Activations