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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different perspectives or considerations in decision-making

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the punctuation mark comma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usp
    -0.85
    sted
    -0.77
    ocl
    -0.69
    çīĪ
    -0.67
    arij
    -0.62
     Named
    -0.62
    nih
    -0.60
    Þ
    -0.58
     misunder
    -0.58
    ThumbnailImage
    -0.57
    POSITIVE LOGITS
     regardless
    1.37
     whereas
    1.31
     irrespective
    1.25
     unless
    1.17
     especially
    1.07
    unless
    1.06
     preferably
    1.03
     lest
    1.01
     hence
    1.00
     because
    0.95
    Act Density 0.359%

    No Known Activations