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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of weight or burden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.09
    3:0.07
    4:0.16
    5:0.04
    6:0.06
    7:0.27
    8:0.05
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
    エル
    -2.04
    ortium
    -1.76
    AU
    -1.71
    xxxxxxxx
    -1.69
    uart
    -1.67
    theless
    -1.67
    UTC
    -1.65
    ipedia
    -1.64
    KEN
    -1.60
    SSL
    -1.59
    POSITIVE LOGITS
     rotting
    2.36
     fumes
    2.08
     fatigue
    1.99
     odor
    1.89
     sickness
    1.88
     haze
    1.86
     trembling
    1.84
     sweat
    1.82
     bruises
    1.80
     piles
    1.76
    Act Density 0.000%

    No Known Activations