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

    Neuronpedia

    INDEX
    Explanations

    coordinated sets of words in a sentence that signal relationship or connection between ideas

    oai_token-act-pair · gpt-3.5-turbo

    connective phrases and transitional words in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...)
    -0.84
     congr
    -0.67
     Ner
    -0.67
    )--
    -0.66
     .)
    -0.65
    âĢ¦)
    -0.65
     )
    -0.63
    !)
    -0.62
     Asgard
    -0.61
     Ital
    -0.60
    POSITIVE LOGITS
    etheless
    1.07
    weather
    0.86
    ernel
    0.82
    ovie
    0.80
    values
    0.77
    ogether
    0.77
    obar
    0.76
    outine
    0.73
    xtap
    0.72
    inen
    0.72
    Act Density 0.426%

    No Known Activations