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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rarity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.19
    2:0.11
    3:0.07
    4:0.04
    5:0.12
    6:0.07
    7:0.02
    8:0.05
    9:0.06
    10:0.07
    11:0.04
    Negative Logits
    rek
    -1.81
    clinton
    -1.80
    utils
    -1.76
     shack
    -1.75
    cot
    -1.75
     renegoti
    -1.73
    inventoryQuantity
    -1.72
    acl
    -1.70
    acus
    -1.68
     travels
    -1.67
    POSITIVE LOGITS
    ヴァ
    1.96
     Rare
    1.94
    �
    1.92
    Beta
    1.92
    �
    1.90
    BF
    1.86
    �
    1.86
     Orc
    1.83
    Num
    1.82
    umeric
    1.81
    Act Density 0.000%

    No Known Activations