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

    Neuronpedia

    INDEX
    Explanations

    words related to action or motion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.09
    3:0.08
    4:0.08
    5:0.09
    6:0.07
    7:0.08
    8:0.08
    9:0.07
    10:0.06
    11:0.08
    Negative Logits
     PCB
    -2.75
    sbm
    -2.60
     Strategy
    -2.53
     modelling
    -2.46
     Simulation
    -2.40
     simulator
    -2.36
     Armour
    -2.29
     skeletal
    -2.27
     Mechanical
    -2.27
     Tactical
    -2.27
    POSITIVE LOGITS
    ocent
    2.77
    venge
    2.59
    assador
    2.41
     ambassadors
    2.40
    izons
    2.40
     superpower
    2.37
    aunder
    2.37
    enium
    2.35
    peror
    2.29
     nomine
    2.25
    Act Density 0.000%

    No Known Activations