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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.07
    7:0.08
    8:0.08
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     Paste
    -2.49
    Clear
    -2.35
    �
    -2.24
     Matrix
    -2.18
     Vox
    -2.13
    True
    -2.12
    Apps
    -2.08
    Orange
    -2.06
     Django
    -2.04
     Method
    -2.01
    POSITIVE LOGITS
     guiActiveUn
    2.93
     prey
    2.37
     injure
    2.31
     hinder
    2.23
     patrol
    2.19
     retaliate
    2.17
    lag
    2.13
     grazing
    2.12
     labou
    2.10
    ffer
    2.09
    Act Density 0.000%

    No Known Activations