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

    Neuronpedia

    INDEX
    Explanations

    imperatives or instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "to do this" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ao
    -0.68
    Ľ
    -0.65
    Lost
    -0.64
    aq
    -0.63
    ĸ
    -0.60
    oris
    -0.57
     Forsaken
    -0.57
    arted
    -0.57
    Ĺ
    -0.56
    annon
    -0.56
    POSITIVE LOGITS
     nonetheless
    1.09
     cautiously
    1.01
     primarily
    1.00
     mainly
    0.99
     indirectly
    0.98
     sparing
    0.98
     insofar
    0.98
     principally
    0.97
     because
    0.97
     chiefly
    0.97
    Act Density 0.667%

    No Known Activations