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

    Neuronpedia

    INDEX
    Explanations

    phrases related to active involvement or participation in various activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "actively" and its variations, indicating engagement or initiative in actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parables
    -0.80
    ridge
    -0.76
     Moments
    -0.70
    thood
    -0.68
    wich
    -0.67
    Dex
    -0.67
     finally
    -0.66
    aster
    -0.66
    inally
    -0.65
     Quarter
    -0.65
    POSITIVE LOGITS
     pursued
    1.21
     lobbied
    1.14
     engaged
    1.12
     discouraged
    1.03
     pursuing
    1.03
     sought
    1.02
     campaigned
    1.00
     pursue
    1.00
     encouraged
    0.98
     cour
    0.98
    Act Density 0.056%

    No Known Activations