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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote locations or entries in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.04
    4:0.10
    5:0.02
    6:0.07
    7:0.43
    8:0.02
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
     arrang
    -1.53
    ér
    -1.53
    Delivery
    -1.52
     assurance
    -1.41
     delivering
    -1.40
    CLUD
    -1.40
    OUGH
    -1.38
    oulder
    -1.36
    rang
    -1.35
     inclination
    -1.34
    POSITIVE LOGITS
    pmwiki
    1.88
     trivia
    1.66
     entries
    1.62
     lists
    1.61
     charts
    1.59
     Wonderland
    1.50
     Lists
    1.49
    otos
    1.45
     Dictionary
    1.43
     Encyclopedia
    1.43
    Act Density 0.004%

    No Known Activations