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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting engagement or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that encourage interaction or actions from the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Originally
    -0.71
     Originally
    -0.68
    Iraq
    -0.65
    uper
    -0.65
    arious
    -0.64
    far
    -0.63
    anc
    -0.62
    responsible
    -0.62
    agen
    -0.61
    Publisher
    -0.61
    POSITIVE LOGITS
     reap
    1.10
     then
    1.08
     vo
    1.06
     THEN
    1.05
     enjoy
    1.03
     prest
    0.94
     decide
    0.93
     proceed
    0.91
    romeda
    0.90
     try
    0.89
    Act Density 0.191%

    No Known Activations