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

    Neuronpedia

    INDEX
    Explanations

    terms related to the definition and discussion of "fake news."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.18
    1:0.02
    2:0.22
    3:0.08
    4:0.04
    5:0.10
    6:0.04
    7:0.07
    8:0.06
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
     Ach
    -2.80
     Quart
    -2.68
     Hep
    -2.47
     dancer
    -2.42
     サーティワン
    -2.40
    VALUE
    -2.31
     Hes
    -2.31
     Bagg
    -2.30
     Henri
    -2.29
     Sacrifice
    -2.29
    POSITIVE LOGITS
    Fake
    3.96
     disinformation
    3.88
     bots
    3.82
     spam
    3.82
     retweet
    3.74
    fake
    3.66
     hoax
    3.49
     debunk
    3.37
     Fake
    3.37
     CNN
    3.31
    Act Density 0.019%

    No Known Activations