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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and commands, such as curly braces and keywords

    oai_token-act-pair · gpt-3.5-turbo

    coding syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.71
     behavi
    -0.71
    ience
    -0.69
    ulence
    -0.65
    itability
    -0.65
     ethics
    -0.63
    sense
    -0.62
    agi
    -0.62
     aggregation
    -0.62
     fragment
    -0.62
    POSITIVE LOGITS
    lished
    1.21
     Played
    1.20
     pushed
    1.19
    pleted
    1.16
     clicked
    1.16
    Used
    1.15
     avoided
    1.15
    Removed
    1.14
     blasted
    1.14
     Killed
    1.14
    Act Density 0.200%

    No Known Activations