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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical properties, such as texture and appearance

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to functionality and practicality in objects or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Samar
    -0.70
     convened
    -0.63
     inaug
    -0.63
     recounts
    -0.62
     Paran
    -0.62
     Osw
    -0.61
     neuroscience
    -0.60
     redes
    -0.60
    etus
    -0.60
     consortium
    -0.60
    POSITIVE LOGITS
     when
    0.96
     whereas
    0.94
     compared
    0.92
     underneath
    0.89
     indoors
    0.88
     outdoors
    0.87
    .(
    0.87
     WITHOUT
    0.87
     whilst
    0.86
     without
    0.86
    Act Density 0.430%

    No Known Activations