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

    Neuronpedia

    INDEX
    Explanations

    references to institutions, industries, and notable figures within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.06
    2:0.13
    3:0.04
    4:0.02
    5:0.05
    6:0.10
    7:0.07
    8:0.25
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
    andise
    -1.23
    ギ
    -1.20
    Reviewed
    -1.10
     Dragonbound
    -1.08
     1900
    -1.08
    版
    -1.07
     VIDE
    -1.05
    �
    -1.05
     2000
    -1.04
    =]
    -1.04
    POSITIVE LOGITS
    eners
    1.13
    cius
    1.11
     narciss
    1.09
    dan
    1.07
    istries
    1.06
    ellar
    1.05
    ingers
    1.04
    thora
    1.02
     sharks
    1.02
    aults
    1.02
    Act Density 0.325%

    No Known Activations