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

    Neuronpedia

    INDEX
    Explanations

    instances of greeting or welcoming expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.08
    2:0.11
    3:0.05
    4:0.05
    5:0.04
    6:0.08
    7:0.08
    8:0.02
    9:0.06
    10:0.15
    11:0.05
    Negative Logits
    greSQL
    -3.21
    lance
    -2.89
    ikhail
    -2.81
     slic
    -2.81
     pg
    -2.78
    abases
    -2.74
    Marc
    -2.67
     Salmon
    -2.64
     calcium
    -2.63
     marines
    -2.62
    POSITIVE LOGITS
     Toby
    8.66
     Tob
    4.45
     Tot
    4.03
     Tick
    3.98
     Tinker
    3.92
     Tobias
    3.88
     Tara
    3.85
     Woody
    3.85
     Faw
    3.69
     Tou
    3.68
    Act Density 0.001%

    No Known Activations