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

    Neuronpedia

    INDEX
    Explanations

    phrases containing specific keywords related to technical topics

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wet
    -0.74
     wip
    -0.69
     overtime
    -0.68
     toile
    -0.65
     sculpt
    -0.64
     retard
    -0.63
     neighb
    -0.63
     deductions
    -0.63
     goalie
    -0.63
     unaccount
    -0.62
    POSITIVE LOGITS
    ccording
    1.37
    Advertisements
    1.11
    Spoiler
    1.11
    Whether
    1.09
    ////////////////////////////////
    1.09
    Since
    1.09
    ========
    1.08
    Sometimes
    1.07
    There
    1.07
    Given
    1.06
    Act Density 0.200%

    No Known Activations