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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and control flow structures commonly found in programming code

    oai_token-act-pair · gpt-3.5-turbo

    programming constructs related to conditional statements and returns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.88
    assic
    -0.86
    ufact
    -0.78
    ãĥ¤
    -0.77
    intend
    -0.76
    leased
    -0.75
    adden
    -0.74
    natureconservancy
    -0.72
    ellar
    -0.71
    afety
    -0.70
    POSITIVE LOGITS
     Âł Âł
    0.88
     ;
    0.79
     ];
    0.79
     {
    0.77
     ((
    0.75
     bool
    0.74
     Âł Âł Âł Âł
    0.74
     fn
    0.73
     }}
    0.71
     ;;
    0.71
    Act Density 0.047%

    No Known Activations