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

    Neuronpedia

    INDEX
    Explanations

    the concept of movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.07
    3:0.07
    4:0.08
    5:0.09
    6:0.09
    7:0.11
    8:0.07
    9:0.09
    10:0.06
    11:0.07
    Negative Logits
     enh
    -2.06
     aids
    -2.03
    ーティ
    -1.99
    nothing
    -1.91
    \.
    -1.83
    в
    -1.83
     BALL
    -1.83
     ple
    -1.79
    izabeth
    -1.79
    notice
    -1.78
    POSITIVE LOGITS
    thood
    2.34
     landfall
    2.20
     runoff
    2.10
    iership
    2.01
     converge
    1.98
     backlog
    1.96
     Nile
    1.90
     Planetary
    1.89
    Population
    1.86
    ueller
    1.85
    Act Density 0.000%

    No Known Activations