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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts related to surprise and unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.05
    4:0.16
    5:0.03
    6:0.05
    7:0.35
    8:0.03
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    agall
    -1.66
    inventoryQuantity
    -1.55
    spir
    -1.49
    oneliness
    -1.45
    rompt
    -1.42
     sidx
    -1.41
    onomous
    -1.40
    VOL
    -1.39
    taboola
    -1.37
    acebook
    -1.35
    POSITIVE LOGITS
     buffs
    1.40
     Lumin
    1.36
     computation
    1.35
     guests
    1.34
     Beng
    1.30
     Gö
    1.30
     HH
    1.29
     forthcoming
    1.28
     Rocks
    1.27
     Benson
    1.22
    Act Density 0.002%

    No Known Activations