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

    Neuronpedia

    INDEX
    Explanations

    dates and locations in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scept
    -0.77
     stuff
    -0.76
     imperson
    -0.76
     tack
    -0.75
     dislike
    -0.75
     blackmail
    -0.74
     mistress
    -0.70
     mockery
    -0.70
     loaf
    -0.70
     disgust
    -0.69
    POSITIVE LOGITS
     YORK
    1.05
    DAQ
    0.95
    PRESS
    0.95
     RELEASE
    0.94
     Congratulations
    0.92
    Published
    0.91
     PRES
    0.91
    reetings
    0.91
    WASHINGTON
    0.88
    FIELD
    0.86
    Act Density 0.196%

    No Known Activations