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

    Neuronpedia

    INDEX
    Explanations

    instructions for using or managing software features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eniable
    -0.15
    -quote
    -0.14
    нина
    -0.13
    inspace
    -0.13
    Quotes
    -0.13
    quotes
    -0.12
    è¡¡
    -0.12
    QM
    -0.12
    Traits
    -0.12
     Synopsis
    -0.12
    POSITIVE LOGITS
     instructions
    0.53
     instruction
    0.47
     step
    0.47
     steps
    0.45
     guides
    0.43
    instructions
    0.43
     guide
    0.42
     tutorial
    0.42
     Instructions
    0.41
     directions
    0.39
    Act Density 0.389%

    No Known Activations