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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as names and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of editors and reporting tasks in a journalistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steam
    -0.70
     evid
    -0.69
    iments
    -0.68
    sbm
    -0.66
    gress
    -0.66
    Sync
    -0.66
     segreg
    -0.66
     scrimmage
    -0.65
     scrim
    -0.65
    Applications
    -0.64
    POSITIVE LOGITS
    inion
    0.94
     POLITICO
    0.89
    Edited
    0.83
     HuffPost
    0.81
     Investigative
    0.75
    olkien
    0.75
     Huffington
    0.73
     counterterrorism
    0.72
     Juliet
    0.72
     Coverage
    0.71
    Act Density 0.204%

    No Known Activations