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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trouble
    -0.74
     troubles
    -0.70
     finalized
    -0.68
     commute
    -0.65
     wre
    -0.65
     controversy
    -0.63
     seams
    -0.62
     firewall
    -0.62
     festivities
    -0.62
     giveaway
    -0.61
    POSITIVE LOGITS
     "âĢ¦
    1.16
     "...
    1.09
     "'
    1.00
     '[
    0.97
     "[
    0.97
     ""
    0.96
     "(
    0.92
     "$
    0.87
     "@
    0.83
     ".
    0.82
    Act Density 0.070%

    No Known Activations