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

    Neuronpedia

    INDEX
    Explanations

    family relationships and emotional statements in news articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     soggior
    -0.95
     archivio
    -0.84
     bandung
    -0.84
     maroc
    -0.82
     cammin
    -0.82
     LIRE
    -0.80
     cioc
    -0.79
     tenda
    -0.79
     torba
    -0.78
     Luglio
    -0.78
    POSITIVE LOGITS
     distraught
    0.56
     grieving
    0.54
     understandably
    0.53
     stepfather
    0.50
    PropertyChanging
    0.50
     contacted
    0.48
     tear
    0.48
     said
    0.48
     Před
    0.47
     grief
    0.47
    Act Density 0.316%

    No Known Activations