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

    Neuronpedia

    INDEX
    Explanations

    terms associated with sourness and fermentation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.19
    2:0.07
    3:0.05
    4:0.05
    5:0.02
    6:0.09
    7:0.08
    8:0.04
    9:0.04
    10:0.10
    11:0.05
    Negative Logits
    Hu
    -3.42
     Tanzania
    -3.33
     Ng
    -3.20
     invis
    -3.14
     Kenya
    -3.07
     Walton
    -3.04
     Mongolia
    -3.03
    Mob
    -2.98
     opacity
    -2.95
     Huang
    -2.92
    POSITIVE LOGITS
     Sour
    8.37
     sour
    6.79
     Onion
    4.28
     acid
    3.58
     Soda
    3.42
     Acid
    3.29
     vinegar
    3.25
     sod
    3.25
     Sad
    3.24
     fru
    3.20
    Act Density 0.003%

    No Known Activations