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

    Neuronpedia

    INDEX
    Explanations

    end punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.09
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.09
    10:0.08
    11:0.08
    Negative Logits
    ructose
    -2.93
    communications
    -2.79
     Schwarz
    -2.56
    schild
    -2.53
     carrier
    -2.48
     locker
    -2.42
    andestine
    -2.40
     Peb
    -2.38
    ohyd
    -2.36
     Crate
    -2.33
    POSITIVE LOGITS
     MLA
    2.89
    assetsadobe
    2.87
     Liberals
    2.74
     Median
    2.43
     remake
    2.36
     Salmon
    2.34
    maid
    2.33
     Greens
    2.30
     Australians
    2.27
    IAS
    2.23
    Act Density 0.000%

    No Known Activations