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

    Neuronpedia

    INDEX
    Explanations

    programming code template markers

    oai_token-act-pair · gpt-3.5-turbo

    hashtags or comment tags commonly used in programming or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vie
    -0.82
     Gors
    -0.78
     Williamson
    -0.68
     foremost
    -0.67
     Shiva
    -0.67
     Eve
    -0.65
     Burke
    -0.64
     Glas
    -0.64
     jog
    -0.63
     Thib
    -0.63
    POSITIVE LOGITS
    define
    1.55
    !/
    1.37
    include
    1.31
    endif
    1.22
    ################################
    1.21
    DIV
    1.21
    ########
    1.07
    ################
    1.03
    BRE
    0.99
    NAME
    0.99
    Act Density 0.023%

    No Known Activations