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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey direction or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.05
    4:0.15
    5:0.02
    6:0.08
    7:0.37
    8:0.04
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    lihood
    -1.50
     Participation
    -1.50
    bucks
    -1.49
    mentation
    -1.46
    psey
    -1.41
    ETF
    -1.39
    66666666
    -1.37
     sidx
    -1.36
    enos
    -1.35
    eny
    -1.33
    POSITIVE LOGITS
    SOURCE
    1.74
     helm
    1.73
    COLOR
    1.51
    Graph
    1.49
     minimalist
    1.32
    direction
    1.32
    RECT
    1.32
     parchment
    1.28
    Applic
    1.28
     utilitarian
    1.26
    Act Density 0.002%

    No Known Activations