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

    Neuronpedia

    INDEX
    Explanations

    the action of moving or proceeding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.07
    4:0.08
    5:0.06
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Prism
    -2.32
     Monstrous
    -2.28
     Tart
    -2.25
     tribunal
    -2.15
     assets
    -2.10
     Lamb
    -2.09
     Shroud
    -2.07
     Catalyst
    -2.05
     chap
    -2.02
     Cass
    -2.01
    POSITIVE LOGITS
    hower
    2.65
    eus
    2.64
    furt
    2.59
    fre
    2.58
    urbed
    2.55
    vag
    2.50
    eteria
    2.50
    uncture
    2.44
    verett
    2.44
    eneg
    2.40
    Act Density 0.000%

    No Known Activations