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

    Neuronpedia

    INDEX
    Explanations

    references to current events or updates in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.08
    4:0.25
    5:0.04
    6:0.21
    7:0.04
    8:0.04
    9:0.04
    10:0.09
    11:0.05
    Negative Logits
    orem
    -1.40
    efer
    -1.39
    upon
    -1.39
     Malk
    -1.36
     FTA
    -1.32
    alky
    -1.30
     District
    -1.29
     Erie
    -1.28
    osta
    -1.27
     Ag
    -1.24
    POSITIVE LOGITS
    ONSORED
    1.68
     Topic
    1.51
     Compatibility
    1.46
    VERTISEMENT
    1.46
    catentry
    1.45
    iHUD
    1.41
    ��
    1.41
    =-=-=-=-
    1.39
    ims
    1.38
    PDATE
    1.37
    Act Density 0.000%

    No Known Activations