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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "take" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulo
    -0.67
    ingen
    -0.66
     david
    -0.63
     sidebar
    -0.62
    Cong
    -0.62
     Smile
    -0.62
     Colleg
    -0.60
    edded
    -0.60
    witz
    -0.60
    earances
    -0.59
    POSITIVE LOGITS
    aways
    1.08
     advantage
    0.88
     aback
    0.87
    offs
    0.83
    arnaev
    0.80
     baths
    0.80
     care
    0.79
    Ĺ
    0.79
     heed
    0.78
     Mehran
    0.77
    Act Density 0.091%

    No Known Activations