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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance of a specific element within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the significance or essential role of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Predators
    -0.72
     extremes
    -0.69
     waves
    -0.69
     ceilings
    -0.68
    incinn
    -0.66
     Skies
    -0.65
    thinkable
    -0.65
     spiders
    -0.64
     roomm
    -0.64
     faint
    -0.64
    POSITIVE LOGITS
    PsyNetMessage
    0.90
     thereof
    0.80
    stone
    0.80
    UID
    0.79
    ablishment
    0.76
    ICLE
    0.73
    tenance
    0.70
    ainer
    0.69
    clus
    0.69
     Supporting
    0.68
    Act Density 0.056%

    No Known Activations