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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "de" and its associations with locations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.03
    4:0.04
    5:0.04
    6:0.31
    7:0.14
    8:0.04
    9:0.05
    10:0.14
    11:0.06
    Negative Logits
    hered
    -1.51
    ateurs
    -1.43
    abase
    -1.42
    ELF
    -1.39
     anonymity
    -1.32
     defect
    -1.32
    eware
    -1.32
    BILITY
    -1.31
     ADS
    -1.25
     beware
    -1.22
    POSITIVE LOGITS
    opolis
    1.77
     Janeiro
    1.68
    eneg
    1.50
    arta
    1.45
    acan
    1.38
    士
    1.37
    ��
    1.35
     unpop
    1.31
    aca
    1.29
    hur
    1.27
    Act Density 0.001%

    No Known Activations