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

    Neuronpedia

    INDEX
    Explanations

    expressions related to movement or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.06
    4:0.15
    5:0.03
    6:0.07
    7:0.33
    8:0.04
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     concess
    -1.77
     award
    -1.62
     awarding
    -1.62
     awarded
    -1.59
     incumbent
    -1.57
     grant
    -1.50
     sacrific
    -1.48
     grounding
    -1.47
     certificate
    -1.46
     reprim
    -1.46
    POSITIVE LOGITS
     corridors
    2.11
     halls
    2.00
    abouts
    1.97
     rooft
    1.89
    veyard
    1.87
     bushes
    1.86
    adders
    1.84
     nests
    1.78
    stores
    1.76
     hither
    1.67
    Act Density 0.005%

    No Known Activations