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

    Neuronpedia

    INDEX
    Explanations

    references to governmental departments or agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.06
    2:0.09
    3:0.15
    4:0.02
    5:0.02
    6:0.11
    7:0.08
    8:0.09
    9:0.15
    10:0.09
    11:0.07
    Negative Logits
    imaru
    -1.26
    opian
    -1.16
    fml
    -1.12
    oor
    -1.11
    PF
    -1.10
     blanket
    -1.08
    ELY
    -1.05
    エル
    -1.04
    ikuman
    -1.02
    pless
    -1.00
    POSITIVE LOGITS
    ukong
    1.14
    lder
    1.10
     Champ
    1.06
     Wyn
    1.02
    grass
    1.00
    minist
    0.99
    inker
    0.96
     Lois
    0.96
     liv
    0.93
    Phys
    0.92
    Act Density 0.009%

    No Known Activations