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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by "the" and a noun, specifically related to physical locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating physical presence or actions occurring in front of something or someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.85
    aren
    -0.82
    itionally
    -0.77
    acci
    -0.73
    PDATE
    -0.73
    cu
    -0.73
    >[
    -0.72
    QL
    -0.71
    PF
    -0.71
    owe
    -0.69
    POSITIVE LOGITS
    rium
    0.73
    sight
    0.73
    thouse
    0.71
    agons
    0.70
     Vulkan
    0.66
     Gors
    0.66
     Irving
    0.65
     Fury
    0.65
    camera
    0.64
     Kessler
    0.62
    Act Density 0.034%

    No Known Activations