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

    Neuronpedia

    INDEX
    Explanations

    general occurrences or concepts mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "something" when discussing various topics or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    de
    -0.84
    ped
    -0.79
    xon
    -0.76
    iday
    -0.69
    DOS
    -0.69
    mes
    -0.67
    ortex
    -0.67
    stice
    -0.67
    bda
    -0.67
    xtap
    -0.66
    POSITIVE LOGITS
     else
    1.20
     akin
    0.98
    Else
    0.93
     unheard
    0.87
     we
    0.85
     that
    0.81
     you
    0.75
     sorely
    0.75
     everyone
    0.73
     Else
    0.71
    Act Density 0.043%

    No Known Activations