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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers followed by a specific symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of hashtags and post metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     colle
    -0.76
     acknow
    -0.76
    ãĥ³ãĤ¸
    -0.75
     reve
    -0.72
    ahime
    -0.72
     weap
    -0.70
     veh
    -0.69
    nown
    -0.67
    ãĥ¼ãĥĨ
    -0.65
     cane
    -0.65
    POSITIVE LOGITS
    ########
    1.19
    ################################
    1.18
    ################
    1.09
    ###
    0.89
    nice
    0.87
     Posts
    0.81
    region
    0.80
    DIV
    0.79
    Reply
    0.77
     ##
    0.74
    Act Density 0.011%

    No Known Activations