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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate sequence and order in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.10
    3:0.08
    4:0.06
    5:0.01
    6:0.02
    7:0.49
    8:0.03
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
    bern
    -1.74
    urate
    -1.73
    elf
    -1.73
    boards
    -1.73
    acebook
    -1.69
    ores
    -1.69
    iencies
    -1.59
    iety
    -1.59
    aceous
    -1.58
    ivated
    -1.55
    POSITIVE LOGITS
     unsuccessful
    1.71
     lash
    1.62
     chronological
    1.58
    dies
    1.52
     series
    1.51
     qualitative
    1.50
     successful
    1.46
     dismissive
    1.44
     approvals
    1.44
     axe
    1.43
    Act Density 0.037%

    No Known Activations