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

    Neuronpedia

    INDEX
    Explanations

    references to applications and the processes surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.06
    4:0.05
    5:0.05
    6:0.04
    7:0.05
    8:0.04
    9:0.07
    10:0.35
    11:0.14
    Negative Logits
    politics
    -1.37
    clip
    -1.36
    CVE
    -1.35
    Column
    -1.34
     Broadcasting
    -1.32
     Clip
    -1.32
    Movie
    -1.28
    hai
    -1.27
     Scourge
    -1.25
     Movies
    -1.25
    POSITIVE LOGITS
     prelim
    1.94
    igslist
    1.90
     elig
    1.74
     mailed
    1.71
     paperwork
    1.65
    idav
    1.64
     deposit
    1.64
     Zup
    1.63
     checklist
    1.61
     submitted
    1.58
    Act Density 0.105%

    No Known Activations