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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emphasizing or directing attention to specific parts of the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of specific points or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indefinitely
    -0.79
    then
    -0.76
    adays
    -0.72
    liam
    -0.71
    soever
    -0.70
     someday
    -0.69
    HAM
    -0.69
    ledged
    -0.69
    onse
    -0.69
    aligned
    -0.69
    POSITIVE LOGITS
     fray
    1.02
     proverbial
    1.01
     madness
    0.98
     joke
    0.93
     fun
    0.92
     irony
    0.91
     latter
    0.90
     basics
    0.88
     gist
    0.87
     tale
    0.87
    Act Density 0.315%

    No Known Activations