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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or singularity

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing exclusivity or singular focus on a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mushroom
    -0.80
     Neighbor
    -0.77
     Nurs
    -0.72
    enegger
    -0.70
     Chaser
    -0.66
     Signs
    -0.65
     Tycoon
    -0.64
    Prince
    -0.64
     Rampage
    -0.63
     Enemies
    -0.63
    POSITIVE LOGITS
     solely
    1.02
     rely
    0.85
     reliant
    0.84
     relying
    0.76
     relied
    0.74
     revolves
    0.74
     focused
    0.74
     incidental
    0.74
    retion
    0.72
     relies
    0.71
    Act Density 0.003%

    No Known Activations