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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles preceded by special characters like '@' and dates

    oai_token-act-pair · gpt-3.5-turbo

    the presence of at-signs associated with social media handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blers
    -0.77
     attractions
    -0.74
     Lans
    -0.74
    icion
    -0.72
     criminals
    -0.70
    omorphic
    -0.69
    Ĥª
    -0.66
     treatments
    -0.66
    Ļ½
    -0.64
    houses
    -0.64
    POSITIVE LOGITS
    TPS
    0.84
    Twe
    0.76
    76561
    0.76
     VIDEOS
    0.75
    Official
    0.74
     Ùħ
    0.69
     Tweet
    0.68
    à¼
    0.67
    arthed
    0.67
     âĶľ
    0.66
    Act Density 0.033%

    No Known Activations