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

    Neuronpedia

    INDEX
    Explanations

    instances of contrasting choices or examples

    oai_token-act-pair · gpt-3.5-turbo

    coordinating conjunctions and conditional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.79
     ();
    -0.76
    ":[{"
    -0.73
    .............
    -0.67
    .''
    -0.66
    ();
    -0.66
    .[
    -0.65
    +.
    -0.65
    SPONSORED
    -0.64
    ":-
    -0.64
    POSITIVE LOGITS
    ?)
    1.62
    !)
    1.47
    )
    1.47
    -)
    1.44
    *)
    1.41
    ?),
    1.41
    )."
    1.37
    )"
    1.36
    ),"
    1.35
    !),
    1.34
    Act Density 0.214%

    No Known Activations