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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong emotional emphasis or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.09
    2:0.07
    3:0.09
    4:0.06
    5:0.07
    6:0.07
    7:0.07
    8:0.08
    9:0.09
    10:0.09
    11:0.07
    Negative Logits
     Boe
    -3.20
     Bib
    -3.15
     Hen
    -3.06
     Lionel
    -2.74
     cele
    -2.73
     Hoover
    -2.72
     Robertson
    -2.70
     Canaver
    -2.69
     MacArthur
    -2.67
     Huckabee
    -2.66
    POSITIVE LOGITS
     {*
    3.16
    \/
    2.78
     junction
    2.75
    Materials
    2.73
     Surface
    2.72
    aiden
    2.71
    Motion
    2.71
     actionGroup
    2.64
    isin
    2.63
     Velocity
    2.63
    Act Density 0.000%

    No Known Activations