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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "each other."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.16
    2:0.04
    3:0.04
    4:0.06
    5:0.20
    6:0.03
    7:0.03
    8:0.05
    9:0.05
    10:0.12
    11:0.05
    Negative Logits
    BuyableInstoreAndOnline
    -2.65
    basic
    -2.02
     magnification
    -1.98
    ACP
    -1.92
    paralle
    -1.90
    �
    -1.89
    Pear
    -1.86
    canon
    -1.85
    FY
    -1.83
    dollar
    -1.83
    POSITIVE LOGITS
     selves
    2.07
    selves
    1.96
     Scene
    1.95
    ezvous
    1.87
    emate
    1.81
     Rage
    1.81
     Together
    1.81
     Graveyard
    1.78
     Dead
    1.74
     Addiction
    1.74
    Act Density 0.001%

    No Known Activations