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

    Neuronpedia

    INDEX
    Explanations

    statements about actions or events that are delayed or rescheduled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.13
    3:0.13
    4:0.35
    5:0.03
    6:0.03
    7:0.10
    8:0.02
    9:0.02
    10:0.04
    11:0.06
    Negative Logits
    iHUD
    -1.70
    ��
    -1.51
    BuyableInstoreAndOnline
    -1.50
     Cosponsors
    -1.42
    �
    -1.41
     [+
    -1.41
    ��
    -1.40
    ahime
    -1.40
    ???
    -1.37
    …………
    -1.35
    POSITIVE LOGITS
     landowners
    1.28
     royalty
    1.24
     authors
    1.22
     accus
    1.21
    pict
    1.20
     existed
    1.19
     visited
    1.19
     negatively
    1.19
    istani
    1.15
    brance
    1.15
    Act Density 0.032%

    No Known Activations