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

    Neuronpedia

    INDEX
    Explanations

    references to mascots and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.08
    4:0.05
    5:0.06
    6:0.04
    7:0.07
    8:0.05
    9:0.08
    10:0.32
    11:0.12
    Negative Logits
    advant
    -1.58
    azard
    -1.48
     *)
    -1.38
     Loans
    -1.34
     Advantage
    -1.29
     Intermediate
    -1.27
    Rated
    -1.27
    depend
    -1.25
    essions
    -1.25
     pores
    -1.23
    POSITIVE LOGITS
     mascot
    1.81
     masc
    1.64
     Circus
    1.53
     Haram
    1.46
     zoo
    1.42
     Animal
    1.40
     animal
    1.39
     gorilla
    1.38
     Cowboy
    1.38
    olver
    1.37
    Act Density 0.004%

    No Known Activations