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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate time-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.10
    3:0.07
    4:0.08
    5:0.06
    6:0.08
    7:0.07
    8:0.08
    9:0.09
    10:0.07
    11:0.09
    Negative Logits
     Annotations
    -3.22
    -|
    -3.07
     Ellis
    -2.92
     DISTRICT
    -2.84
     District
    -2.84
     Data
    -2.83
     Wells
    -2.80
     Layer
    -2.80
     CODE
    -2.79
     Ellison
    -2.78
    POSITIVE LOGITS
     Reincarn
    3.10
    illon
    2.99
    Naz
    2.75
     Canaver
    2.75
     Mayhem
    2.69
    oshenko
    2.68
    ocalyptic
    2.67
    inav
    2.66
    alkyrie
    2.56
     euth
    2.55
    Act Density 0.000%

    No Known Activations