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

    Neuronpedia

    INDEX
    Explanations

    references to time-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    psey
    -3.21
     pot
    -2.98
    pson
    -2.96
    ullivan
    -2.75
     pots
    -2.68
    earchers
    -2.67
    killers
    -2.62
     cooks
    -2.61
     settling
    -2.54
     unm
    -2.52
    POSITIVE LOGITS
     Socialism
    3.50
     Syri
    3.22
     Anarch
    3.04
     Assy
    2.93
    YC
    2.90
    �
    2.83
     ECB
    2.80
     Corruption
    2.74
    Euro
    2.73
     UE
    2.70
    Act Density 0.000%

    No Known Activations