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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.81
     utter
    -0.72
     transact
    -0.71
     remnant
    -0.67
     victories
    -0.65
     artisan
    -0.64
     nuts
    -0.62
     peanuts
    -0.62
     outsider
    -0.62
     sequential
    -0.61
    POSITIVE LOGITS
    lua
    0.93
    org
    0.86
    edu
    0.84
     [+
    0.81
     Originally
    0.81
    debian
    0.80
     Asked
    0.80
    dll
    0.79
     Unloaded
    0.76
     "'
    0.76
    Act Density 0.165%

    No Known Activations