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

    Neuronpedia

    INDEX
    Explanations

    locations or names with initial capital letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    names of places and notable figures involved in conflicts or political situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.97
    ãĤ´ãĥ³
    -0.97
     Lovecraft
    -0.89
     Turtles
    -0.87
     Extras
    -0.82
     Grateful
    -0.79
     Wonderland
    -0.76
     Daredevil
    -0.76
     Wally
    -0.76
     Cary
    -0.76
    POSITIVE LOGITS
    akh
    1.07
    isan
    1.05
    jan
    0.94
    iy
    0.93
    abi
    0.92
    ı
    0.92
    awi
    0.90
    ovo
    0.90
    afi
    0.89
    ij
    0.89
    Act Density 0.565%

    No Known Activations