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

    Neuronpedia

    INDEX
    Explanations

    references to time or temporal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.07
    6:0.09
    7:0.09
    8:0.09
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     MacArthur
    -3.02
     ILCS
    -2.85
    Enlarge
    -2.70
     Resolution
    -2.65
     Byrd
    -2.59
     travelers
    -2.58
     Treaty
    -2.51
    Transfer
    -2.38
    pled
    -2.38
    resolution
    -2.37
    POSITIVE LOGITS
     offence
    2.80
     ISI
    2.59
     Amp
    2.59
     criticised
    2.58
     paed
    2.58
     adul
    2.53
     doping
    2.49
    ologne
    2.44
     libel
    2.42
     apologised
    2.39
    Act Density 0.000%

    No Known Activations