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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spoken or quoted content

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.67
    icter
    -0.66
    aucuses
    -0.61
     visionary
    -0.59
    ingu
    -0.59
    uscript
    -0.58
    ĨĴ
    -0.57
    inct
    -0.57
     foundational
    -0.56
    chest
    -0.56
    POSITIVE LOGITS
     adds
    1.07
     added
    0.98
     meanwhile
    0.92
     secondly
    0.87
     replied
    0.83
     adding
    0.82
     countered
    0.81
     referring
    0.74
     emphas
    0.71
     another
    0.71
    Act Density 0.238%

    No Known Activations