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

    Neuronpedia

    INDEX
    Explanations

    phrases related to newsletters and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.18
    3:0.08
    4:0.09
    5:0.03
    6:0.23
    7:0.06
    8:0.05
    9:0.07
    10:0.06
    11:0.05
    Negative Logits
    ovember
    -1.47
    ooks
    -1.41
    ynt
    -1.39
    eele
    -1.38
    lly
    -1.32
    erent
    -1.30
    lf
    -1.30
    utral
    -1.29
    aleb
    -1.27
    inav
    -1.27
    POSITIVE LOGITS
     Corpus
    1.38
     POWER
    1.21
     corrid
    1.17
    �
    1.14
     UNHCR
    1.10
    BuyableInstoreAndOnline
    1.09
     accordingly
    1.08
     Shine
    1.08
     Hispan
    1.07
     opio
    1.06
    Act Density 0.002%

    No Known Activations