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

    Neuronpedia

    INDEX
    Explanations

    themes related to social issues and struggles within society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.18
    1:0.02
    2:0.08
    3:0.12
    4:0.10
    5:0.06
    6:0.02
    7:0.08
    8:0.03
    9:0.02
    10:0.22
    11:0.02
    Negative Logits
     srfAttach
    -2.46
     rethink
    -2.42
     revise
    -2.36
    ciation
    -2.31
    ilot
    -2.27
     recycle
    -2.24
    elligent
    -2.20
     downgrade
    -2.17
     verify
    -2.15
    cellent
    -2.09
    POSITIVE LOGITS
     looming
    2.90
     wrought
    2.65
     unfolding
    2.54
     occurring
    2.49
     wre
    2.47
     surrounding
    2.46
     inflicted
    2.43
     plag
    2.40
     happening
    2.34
     lurking
    2.33
    Act Density 0.134%

    No Known Activations