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

    Neuronpedia

    INDEX
    Explanations

    references to "The New York Times" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.24
    1:0.03
    2:0.02
    3:0.04
    4:0.17
    5:0.17
    6:0.05
    7:0.01
    8:0.16
    9:0.04
    10:0.00
    11:0.01
    Negative Logits
     loophole
    -2.15
     filibuster
    -1.94
     assumption
    -1.92
     fence
    -1.91
     shut
    -1.83
     closed
    -1.75
     veil
    -1.74
    ouf
    -1.72
     reservation
    -1.72
     threshold
    -1.70
    POSITIVE LOGITS
    podcast
    2.26
    Dispatch
    2.21
    Trend
    1.91
    Cola
    1.89
    uters
    1.86
    Daily
    1.82
    icter
    1.78
    Week
    1.77
    Mail
    1.75
    Kind
    1.75
    Act Density 0.002%

    No Known Activations