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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to going "above and beyond."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.12
    3:0.29
    4:0.01
    5:0.01
    6:0.09
    7:0.05
    8:0.09
    9:0.12
    10:0.04
    11:0.09
    Negative Logits
    olkien
    -1.30
    clerosis
    -1.26
     Sweeney
    -1.20
     differently
    -1.18
    weeney
    -1.17
    sole
    -1.15
    bnb
    -1.10
     Genie
    -1.06
    Tea
    -1.03
    arios
    -1.02
    POSITIVE LOGITS
    �
    1.24
     scenes
    1.21
     horizon
    1.15
    ctors
    1.12
    =-=-
    1.11
    orest
    1.08
     Scenes
    1.06
     Holo
    1.01
     parap
    1.01
    empt
    1.01
    Act Density 0.014%

    No Known Activations