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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets and related text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific programming or technical language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     outwe
    -0.79
     Carlton
    -0.77
     prize
    -0.74
     tender
    -0.73
     lunch
    -0.72
     arri
    -0.69
     hospitality
    -0.68
     slam
    -0.68
     paran
    -0.66
     inexper
    -0.66
    POSITIVE LOGITS
    Output
    1.01
    Example
    1.00
    example
    0.97
    Same
    0.96
    Gener
    0.96
    Usage
    0.93
    Note
    0.92
    PUT
    0.91
    output
    0.90
    Simple
    0.89
    Act Density 0.109%

    No Known Activations