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

    Neuronpedia

    INDEX
    Explanations

    demographic statistics and trends related to various populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.04
    2:0.02
    3:0.12
    4:0.32
    5:0.08
    6:0.03
    7:0.02
    8:0.10
    9:0.07
    10:0.01
    11:0.01
    Negative Logits
    rawdownloadcloneembedreportprint
    -2.44
    RAW
    -2.28
     Mub
    -1.96
    DragonMagazine
    -1.94
    epad
    -1.89
     extraord
    -1.86
    soType
    -1.85
    issance
    -1.85
     horm
    -1.74
     obscurity
    -1.73
    POSITIVE LOGITS
    enger
    2.42
     died
    2.33
     polled
    2.21
     accounted
    2.17
    orers
    2.16
     perished
    2.16
    ievers
    2.14
     were
    2.08
    engers
    2.05
    were
    2.04
    Act Density 0.169%

    No Known Activations