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

    Neuronpedia

    INDEX
    Explanations

    scripts or writing instructions related to creating something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     intit
    -0.52
     radeon
    -0.51
    dentes
    -0.50
     Fortun
    -0.48
     Persson
    -0.48
     Adnan
    -0.48
     disting
    -0.48
     accla
    -0.47
     betra
    -0.46
     Balk
    -0.46
    POSITIVE LOGITS
     script
    1.54
     scripts
    1.46
    script
    1.36
     Script
    1.36
    Script
    1.28
     SCRIPT
    1.23
     Scripts
    1.23
    SCRIPT
    1.20
     scripting
    1.20
    scripts
    1.12
    Act Density 0.086%

    No Known Activations