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

    Neuronpedia

    INDEX
    Explanations

    symbols and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    instances of performance-related metrics or indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waged
    -0.79
     cherished
    -0.78
     commemor
    -0.76
     foul
    -0.76
     furthe
    -0.75
     fiercely
    -0.74
     photographed
    -0.74
     lost
    -0.74
     tire
    -0.74
     cement
    -0.73
    POSITIVE LOGITS
    Usage
    1.75
    Example
    1.75
    Installation
    1.65
    Creating
    1.54
    Using
    1.54
    Requirements
    1.54
    License
    1.53
    Examples
    1.53
    <?
    1.53
    Simple
    1.52
    Act Density 0.188%

    No Known Activations