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

    Neuronpedia

    INDEX
    Explanations

    sources of information, such as news outlets and individuals involved in reporting

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news organizations or media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     screws
    -0.73
    stood
    -0.67
     retard
    -0.66
     supposedly
    -0.66
     swast
    -0.65
    soDeliveryDate
    -0.62
     flaming
    -0.62
    isSpecialOrderable
    -0.61
     barg
    -0.61
     extingu
    -0.60
    POSITIVE LOGITS
    News
    0.96
     interviewer
    0.90
    aretz
    0.87
    Politics
    0.84
    news
    0.83
     News
    0.80
     Observer
    0.80
    Crunch
    0.79
    Media
    0.78
    Daily
    0.78
    Act Density 0.134%

    No Known Activations