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

    Neuronpedia

    INDEX
    Explanations

    words related to actions and verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.35
    3:0.03
    4:0.09
    5:0.04
    6:0.02
    7:0.07
    8:0.03
    9:0.06
    10:0.14
    11:0.07
    Negative Logits
    imar
    -1.44
    arat
    -1.28
     Wyn
    -1.20
     Galile
    -1.13
    anqu
    -1.08
    ndra
    -1.07
     Breat
    -1.03
     Dough
    -1.02
    othy
    -1.01
     Hear
    -1.01
    POSITIVE LOGITS
    cli
    1.24
    ️
    1.11
    operation
    1.11
    SHIP
    1.08
    owder
    1.02
    ALLY
    1.01
    hedral
    1.01
    aign
    1.01
    (*
    1.00
    olicy
    0.98
    Act Density 0.155%

    No Known Activations