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

    Neuronpedia

    INDEX
    Explanations

    code snippets with syntax highlighting and function calls

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax and function definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prising
    -0.77
    oven
    -0.71
    reviewed
    -0.70
    edged
    -0.66
    comings
    -0.66
    inki
    -0.66
    reditary
    -0.65
    amped
    -0.64
    llah
    -0.64
    bledon
    -0.63
    POSITIVE LOGITS
     /*
    1.14
     //
    1.11
     println
    1.10
     printf
    1.08
     return
    1.04
    return
    1.01
     var
    0.99
     Console
    0.98
    //
    0.96
     if
    0.95
    Act Density 0.064%

    No Known Activations