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

    Neuronpedia

    INDEX
    Explanations

    text related to coding and programming functions

    oai_token-act-pair · gpt-3.5-turbo

    syntax and structure related to programming or scripting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -1.07
     skelet
    -0.95
     kale
    -0.94
     catast
    -0.93
     pudding
    -0.93
     spir
    -0.91
     tyr
    -0.90
     dynam
    -0.89
     princ
    -0.88
     brittle
    -0.87
    POSITIVE LOGITS
    Amount
    1.85
    Off
    1.82
    Repeat
    1.82
    Minimum
    1.80
    Finish
    1.80
    Limit
    1.80
    Body
    1.80
    Remove
    1.78
    Single
    1.78
    Use
    1.78
    Act Density 0.277%

    No Known Activations