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

    Neuronpedia

    INDEX
    Explanations

    statements that come across as definitive or conclusive

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, especially periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.75
     rall
    -0.72
     targ
    -0.72
     submerged
    -0.69
     eligibility
    -0.69
     sidel
    -0.69
     warr
    -0.68
     wagon
    -0.66
     surf
    -0.65
     culinary
    -0.65
    POSITIVE LOGITS
     Because
    1.38
     Anyway
    1.33
     Absolutely
    1.24
     That
    1.13
     Exactly
    1.12
     Especially
    1.11
     Secondly
    1.10
     Seriously
    1.10
     But
    1.10
     And
    1.09
    Act Density 0.270%

    No Known Activations