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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    temporal references related to recent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.05
    3:0.06
    4:0.05
    5:0.06
    6:0.09
    7:0.16
    8:0.03
    9:0.05
    10:0.19
    11:0.10
    Negative Logits
    $$$$
    -0.86
    mble
    -0.85
    oooooooooooooooo
    -0.74
     Interpret
    -0.73
     Seym
    -0.73
     intangible
    -0.72
    hm
    -0.71
    ————————
    -0.70
     Dull
    -0.70
     Indies
    -0.70
    POSITIVE LOGITS
    ounter
    0.87
    itiz
    0.82
    racuse
    0.74
     guiActiveUnfocused
    0.72
     Mesa
    0.69
    ounters
    0.69
    req
    0.69
     audio
    0.67
     oct
    0.67
    thouse
    0.67
    Act Density 0.160%

    No Known Activations