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

    Neuronpedia

    INDEX
    Explanations

    designers and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to diversity or variety in people, places, or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     awa
    -0.71
    ocument
    -0.66
    rosso
    -0.66
    needed
    -0.65
    Adapt
    -0.64
    avorite
    -0.61
    IONS
    -0.60
     accordingly
    -0.59
    merce
    -0.59
    olson
    -0.59
    POSITIVE LOGITS
     standpoint
    1.36
     vantage
    1.04
     perspective
    0.94
     onwards
    0.89
     sources
    0.85
    ratch
    0.83
     outset
    0.82
     infancy
    0.79
     donors
    0.77
     viewpoint
    0.76
    Act Density 0.716%

    No Known Activations