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

    Neuronpedia

    INDEX
    Explanations

    instances of reporting or citing sources in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.10
    4:0.20
    5:0.03
    6:0.05
    7:0.14
    8:0.07
    9:0.05
    10:0.12
    11:0.08
    Negative Logits
     handshake
    -1.56
    iors
    -1.45
     facade
    -1.38
     tremend
    -1.37
     resting
    -1.36
     satisfied
    -1.35
    matched
    -1.35
     respect
    -1.35
    ifter
    -1.33
    oooooooooooooooo
    -1.33
    POSITIVE LOGITS
     blogs
    1.73
    Buzz
    1.54
    Sources
    1.50
    Polit
    1.49
     blog
    1.49
    GMT
    1.41
    ipedia
    1.40
    Aug
    1.40
    WD
    1.40
    UTH
    1.38
    Act Density 0.003%

    No Known Activations