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

    Neuronpedia

    INDEX
    Explanations

    temporal references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.08
    4:0.22
    5:0.03
    6:0.22
    7:0.03
    8:0.04
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    cellent
    -1.36
    dayName
    -1.34
    ebin
    -1.30
    ilogy
    -1.30
     cess
    -1.29
     trave
    -1.28
    /#
    -1.28
    arters
    -1.25
     unfit
    -1.25
    =~
    -1.24
    POSITIVE LOGITS
     Albania
    1.51
     Hydro
    1.27
    osaurs
    1.26
    dylib
    1.24
     Detail
    1.22
     Companies
    1.21
     Slovenia
    1.21
     Dian
    1.21
     Struct
    1.18
     Sweden
    1.17
    Act Density 0.006%

    No Known Activations