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

    Neuronpedia

    INDEX
    Explanations

    terms related to reports, descriptions, and analyses of data or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.12
    3:0.06
    4:0.01
    5:0.05
    6:0.05
    7:0.07
    8:0.24
    9:0.16
    10:0.07
    11:0.07
    Negative Logits
    iaz
    -1.25
    itect
    -1.06
     realise
    -1.05
    esters
    -1.01
    ogun
    -0.99
    construct
    -0.98
    arge
    -0.95
     exerc
    -0.95
    ecake
    -0.95
    aez
    -0.94
    POSITIVE LOGITS
    links
    1.27
    folio
    1.27
    MpServer
    1.20
     newsletters
    1.15
    foundland
    1.13
     newsletter
    1.12
    upt
    1.10
    DragonMagazine
    1.08
     VG
    1.02
    daily
    1.02
    Act Density 0.024%

    No Known Activations