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

    Neuronpedia

    INDEX
    Explanations

    the word "because" followed by reasoning or consequences

    oai_token-act-pair · gpt-3.5-turbo

    repetitive use of the phrase "just because."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ku
    -0.78
    anon
    -0.64
    hani
    -0.63
    Luc
    -0.63
     lymph
    -0.62
    mented
    -0.60
    exclusive
    -0.59
     exits
    -0.59
     Lauder
    -0.58
    MH
    -0.58
    POSITIVE LOGITS
    */(
    0.94
    lihood
    0.77
    iatus
    0.71
    plin
    0.70
    ptin
    0.66
     Swordsman
    0.66
     someone
    0.66
    insk
    0.65
    hemy
    0.65
    hammad
    0.64
    Act Density 0.023%

    No Known Activations