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

    Neuronpedia

    INDEX
    Explanations

    references to audience engagement or requests for feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.09
    3:0.08
    4:0.09
    5:0.08
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    yssey
    -3.42
    reprene
    -2.87
    Employ
    -2.78
     TOD
    -2.64
     escal
    -2.63
    upp
    -2.62
    eez
    -2.60
     expire
    -2.57
    ventures
    -2.56
    rawdownloadcloneembedreportprint
    -2.53
    POSITIVE LOGITS
     Fabric
    3.09
     Patriot
    3.04
     Patri
    3.01
     Belg
    2.89
     Banner
    2.87
     Argent
    2.86
     Torrent
    2.84
     Arena
    2.82
     Fasc
    2.81
     Laur
    2.80
    Act Density 0.000%

    No Known Activations