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

    Neuronpedia

    INDEX
    Explanations

    code snippets or sequences related to programming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    reb
    -0.77
    æĪ¦
    -0.77
    ãĥ´
    -0.74
    cro
    -0.72
    PAC
    -0.71
    çĶ°
    -0.71
    çķ
    -0.70
    Charl
    -0.70
    anship
    -0.70
    chest
    -0.70
    POSITIVE LOGITS
     =>
    1.26
     println
    1.23
     ;;
    1.18
     ¶
    1.12
     endif
    1.09
     def
    1.04
    ;;
    1.02
     assert
    1.02
     Returns
    1.01
     {:
    0.99
    Act Density 0.115%

    No Known Activations