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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the term "SRI" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to research institutions or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rules
    -0.70
    dayName
    -0.69
     DeVos
    -0.67
     delay
    -0.67
    forth
    -0.65
     forthcoming
    -0.65
     Fourth
    -0.62
     turf
    -0.62
     scarcity
    -0.60
    rule
    -0.60
    POSITIVE LOGITS
    RI
    1.04
    ASON
    0.93
    ving
    0.89
    etta
    0.88
    pees
    0.87
    EF
    0.87
    YING
    0.86
    omy
    0.86
    ARCH
    0.86
    YL
    0.86
    Act Density 0.008%

    No Known Activations