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

    Neuronpedia

    INDEX
    Explanations

    color codes or hashtags

    oai_token-act-pair · gpt-3.5-turbo

    hashtags and their numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commission
    -0.78
     cler
    -0.74
     jog
    -0.72
     foremost
    -0.71
     disturbed
    -0.70
     staggered
    -0.70
     convers
    -0.70
     gest
    -0.69
     lag
    -0.68
     afore
    -0.68
    POSITIVE LOGITS
    DIV
    1.40
    ################################
    1.39
    define
    1.36
    !/
    1.30
    ################
    1.25
    ########
    1.23
    1
    1.23
    Gamer
    1.21
    VALUE
    1.21
    ###
    1.19
    Act Density 0.024%

    No Known Activations