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

    Neuronpedia

    INDEX
    Explanations

    requests or instructions involving taking action

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and connectors that create a sense of continuation or linking between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arious
    -0.69
     Originally
    -0.68
     ][
    -0.66
    Iraq
    -0.66
    Originally
    -0.65
    ļéĨĴ
    -0.65
    responsible
    -0.64
    anders
    -0.63
    ensive
    -0.63
    agen
    -0.63
    POSITIVE LOGITS
     reap
    1.15
     enjoy
    1.14
     then
    1.08
     preferably
    1.06
     THEN
    1.06
     bask
    1.01
     beware
    1.01
     proceed
    1.01
     apply
    1.00
     vo
    1.00
    Act Density 0.258%

    No Known Activations