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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.63
     outwe
    -0.54
     challeng
    -0.54
    obbies
    -0.52
    existent
    -0.51
     nodd
    -0.51
    onto
    -0.51
    bage
    -0.50
    onds
    -0.49
     destro
    -0.49
    POSITIVE LOGITS
     Houth
    0.57
    catentry
    0.56
    hra
    0.53
     Shutdown
    0.52
     Background
    0.51
     Introduction
    0.50
    )--
    0.50
    initialized
    0.49
     ..........
    0.49
     Expand
    0.48
    Act Density 0.941%

    No Known Activations