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

    Neuronpedia

    INDEX
    Explanations

    references to kings and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.05
    3:0.05
    4:0.03
    5:0.03
    6:0.40
    7:0.12
    8:0.03
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
     Helpful
    -1.59
    inarily
    -1.53
     omission
    -1.38
    ibilities
    -1.38
     trustworthy
    -1.38
    atform
    -1.36
    etitive
    -1.36
    chnology
    -1.34
    PLIED
    -1.27
    pter
    -1.27
    POSITIVE LOGITS
    王
    1.44
     Shogun
    1.37
    ikuman
    1.35
     Mania
    1.33
     Sioux
    1.32
     XVI
    1.31
     Decay
    1.31
     Answers
    1.30
     Spirits
    1.27
    agos
    1.27
    Act Density 0.007%

    No Known Activations