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

    Neuronpedia

    INDEX
    Explanations

    the verb "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.09
    2:0.07
    3:0.08
    4:0.08
    5:0.07
    6:0.09
    7:0.08
    8:0.08
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    nesota
    -2.19
     Amtrak
    -2.07
    Portland
    -2.00
    ggles
    -1.89
     OPT
    -1.86
    eport
    -1.80
    adelphia
    -1.79
     Oregon
    -1.77
     Appalachian
    -1.77
     EST
    -1.76
    POSITIVE LOGITS
    Maker
    2.00
     Maker
    1.96
     Secondly
    1.87
     Beard
    1.85
     whilst
    1.85
     Sark
    1.84
     Cry
    1.81
     whereas
    1.78
    nic
    1.75
     Bride
    1.74
    Act Density 0.000%

    No Known Activations