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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or names, particularly those ending with 'ai'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "AI" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    din
    -0.70
     Frie
    -0.70
     Rebell
    -0.70
    lain
    -0.68
    stable
    -0.67
     skelet
    -0.66
    ienced
    -0.65
     err
    -0.65
    oppy
    -0.63
    dies
    -0.63
    POSITIVE LOGITS
    ju
    1.08
    jin
    1.07
    ya
    0.96
    ji
    0.92
    yah
    0.90
    uno
    0.85
    ples
    0.84
    yan
    0.83
    jah
    0.82
    wi
    0.82
    Act Density 0.018%

    No Known Activations