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

    Neuronpedia

    INDEX
    Explanations

    punctuations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that present statements or comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unsus
    -0.75
     preval
    -0.74
     mosqu
    -0.72
     clerks
    -0.72
     unlucky
    -0.71
     concess
    -0.71
     subsistence
    -0.68
     transact
    -0.68
     plent
    -0.68
     dummy
    -0.67
    POSITIVE LOGITS
     "âĢ¦
    1.20
     "...
    1.14
     "(
    1.08
     "[
    1.07
     "'
    1.06
     Asked
    1.03
     Adds
    1.00
     However
    0.92
     "
    0.92
     Said
    0.90
    Act Density 0.215%

    No Known Activations