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

    Neuronpedia

    INDEX
    Explanations

    references to locations or names containing the word "Os"

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the term "Os" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ered
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.70
    ingly
    -0.69
    ILLE
    -0.66
    FACE
    -0.63
     spirited
    -0.62
    EEE
    -0.61
     grounds
    -0.61
    ************
    -0.60
     disregard
    -0.60
    POSITIVE LOGITS
    atell
    0.98
    awa
    0.92
    omal
    0.92
    hiba
    0.90
    lim
    0.89
    nick
    0.87
    por
    0.86
    oma
    0.86
    ullivan
    0.86
    ensible
    0.85
    Act Density 0.017%

    No Known Activations