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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.05
    4:0.05
    5:0.04
    6:0.47
    7:0.03
    8:0.04
    9:0.07
    10:0.07
    11:0.05
    Negative Logits
    coat
    -1.53
     Cheong
    -1.35
    iquette
    -1.21
     Brush
    -1.21
     bluff
    -1.20
    iners
    -1.20
    ILA
    -1.18
    hower
    -1.18
    icles
    -1.17
    ecause
    -1.16
    POSITIVE LOGITS
    ilib
    1.45
    ét
    1.41
    pees
    1.41
    MpServer
    1.35
    escal
    1.33
     Galaxy
    1.31
    ゼウス
    1.31
    encia
    1.28
    pez
    1.28
     Wein
    1.27
    Act Density 0.004%

    No Known Activations