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

    Neuronpedia

    INDEX
    Explanations

    the word "and" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dum
    -0.18
    ÙĦس
    -0.14
     lidi
    -0.14
    icz
    -0.14
    PÅĻÃŃ
    -0.13
    ekler
    -0.13
     Higgins
    -0.13
    iggins
    -0.13
    idge
    -0.13
    ãĤ¢ãĥ¼
    -0.13
    POSITIVE LOGITS
     alike
    0.16
     Rowe
    0.16
    abelle
    0.14
    apest
    0.14
     Abd
    0.14
    746
    0.13
    ismic
    0.13
    inos
    0.13
    736
    0.13
     Volt
    0.13
    Act Density 0.115%

    No Known Activations