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

    Neuronpedia

    INDEX
    Explanations

    words related to importance, value, and impact

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing the significance of various concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icion
    -0.71
    taboola
    -0.59
     Swap
    -0.57
    ciation
    -0.57
    folios
    -0.55
     Dictionary
    -0.55
    ciating
    -0.54
    çļ
    -0.54
     Again
    -0.53
    }}}
    -0.53
    POSITIVE LOGITS
     than
    1.99
    than
    1.73
     Than
    1.50
     then
    0.98
     TH
    0.87
     nowadays
    0.86
     today
    0.86
     now
    0.82
    Th
    0.80
     THEN
    0.72
    Act Density 0.300%

    No Known Activations