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

    Neuronpedia

    INDEX
    Explanations

    pieces of code related to data aggregation and programming syntax

    oai_token-act-pair · gpt-3.5-turbo

    programming or code-related syntax and patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ),"
    -0.87
    )"
    -0.83
    )</
    -0.82
    )",
    -0.80
    "},
    -0.72
    )).
    -0.72
    è¦ļéĨĴ
    -0.71
    )."
    -0.71
    ALSE
    -0.69
    usp
    -0.69
    POSITIVE LOGITS
     ;
    0.75
     ,
    0.73
     ...
    0.71
     cess
    0.70
     .
    0.65
     ?
    0.64
    âĶĢâĶĢâĶĢâĶĢ
    0.63
     harrowing
    0.61
     skim
    0.60
     redeem
    0.59
    Act Density 0.044%

    No Known Activations