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

    Neuronpedia

    INDEX
    Explanations

    RGB color codes

    oai_token-act-pair · gpt-3.5-turbo

    hashtags, particularly those associated with colors or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vie
    -0.75
     jog
    -0.73
     disturbed
    -0.72
     regard
    -0.72
     strang
    -0.71
     commission
    -0.71
     foremost
    -0.69
     Gors
    -0.67
     cler
    -0.67
     convers
    -0.67
    POSITIVE LOGITS
    define
    1.48
    DIV
    1.38
    !/
    1.35
    include
    1.32
    ################################
    1.31
    ################
    1.20
    ########
    1.20
    VALUE
    1.19
    ###
    1.18
    NAME
    1.14
    Act Density 0.022%

    No Known Activations