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

    Neuronpedia

    INDEX
    Explanations

    expressions related to programming code and data aggregation

    oai_token-act-pair · gpt-3.5-turbo

    coding or programming constructs related to data structures and aggregation functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )+
    -0.98
    ).[
    -0.88
    )=
    -0.86
    )</
    -0.86
    ),"
    -0.83
    ãĢı
    -0.81
    )",
    -0.81
    )"
    -0.81
    Advertisements
    -0.80
    )).
    -0.79
    POSITIVE LOGITS
     ...
    1.12
     ....
    0.87
     ......
    0.81
     ..
    0.80
     --
    0.78
     ?
    0.77
     ---
    0.77
     ;
    0.75
     ........
    0.74
     ,
    0.73
    Act Density 0.047%

    No Known Activations