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

    Neuronpedia

    INDEX
    Explanations

    references to financial concerns or economic struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.10
    2:0.09
    3:0.07
    4:0.08
    5:0.08
    6:0.08
    7:0.07
    8:0.08
    9:0.09
    10:0.07
    11:0.07
    Negative Logits
    ierra
    -2.94
    aniel
    -2.80
     Ender
    -2.79
    wagon
    -2.63
    elligent
    -2.60
    nings
    -2.60
    knit
    -2.56
    bre
    -2.52
    ascade
    -2.51
    fleet
    -2.50
    POSITIVE LOGITS
     Lindsay
    2.92
     Georgian
    2.62
     Document
    2.55
     Watergate
    2.53
     gum
    2.49
     Durham
    2.47
     Burr
    2.44
     Australians
    2.39
     Dumb
    2.38
     Indonesian
    2.38
    Act Density 0.000%

    No Known Activations