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

    Neuronpedia

    INDEX
    Explanations

    mentions of news and updates related to events and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.04
    2:0.33
    3:0.06
    4:0.15
    5:0.04
    6:0.03
    7:0.03
    8:0.04
    9:0.10
    10:0.05
    11:0.02
    Negative Logits
    ush
    -1.29
     commissions
    -1.23
    yip
    -1.22
    ussia
    -1.17
    weed
    -1.16
    vertisements
    -1.15
    flix
    -1.14
    olls
    -1.13
    vet
    -1.12
    fle
    -1.12
    POSITIVE LOGITS
    vironment
    1.48
    TOP
    1.47
    WARE
    1.46
    DIS
    1.42
    ource
    1.40
    pta
    1.36
    enment
    1.31
    itia
    1.30
    ciating
    1.29
    MENTS
    1.28
    Act Density 0.003%

    No Known Activations