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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Kings" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnation
    -0.16
    powered
    -0.15
    kenin
    -0.15
    stract
    -0.14
    arra
    -0.14
    iele
    -0.14
     Grat
    -0.14
    ãĥ³ãĥĩãĤ£
    -0.14
     Powered
    -0.14
    SHOT
    -0.13
    POSITIVE LOGITS
    chap
    0.15
    enson
    0.15
    itmap
    0.15
    åĢ«
    0.15
     stimulus
    0.15
    wiÄħ
    0.14
    o
    0.14
    èĩ
    0.14
    ocha
    0.14
    oose
    0.14
    Act Density 0.004%

    No Known Activations