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

    Neuronpedia

    INDEX
    Explanations

    the word "go" indicating a command or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.10
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.06
    7:0.09
    8:0.08
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
     Lump
    -2.23
     Franchise
    -2.11
     Eps
    -1.96
     Marketing
    -1.93
     Cry
    -1.93
    tal
    -1.92
     modelling
    -1.89
    bra
    -1.88
     Bones
    -1.87
     Cookies
    -1.85
    POSITIVE LOGITS
    soDeliveryDate
    2.46
     colonization
    2.27
     concess
    2.13
     cutoff
    2.04
     Nicarag
    2.02
    Interstitial
    2.00
    prev
    2.00
     concentrations
    1.99
     normalized
    1.98
     resid
    1.97
    Act Density 0.000%

    No Known Activations