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

    Neuronpedia

    INDEX
    Explanations

    parts or components of physical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to parts or components of objects or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    accompan
    -0.70
    registered
    -0.69
    isman
    -0.67
    CAST
    -0.67
    Bir
    -0.66
    PDATE
    -0.64
    manac
    -0.63
    Birth
    -0.63
    sett
    -0.62
    riend
    -0.62
    POSITIVE LOGITS
     of
    0.79
     ridge
    0.77
     choke
    0.74
     flank
    0.70
     thereof
    0.70
     corner
    0.68
    selage
    0.67
     loader
    0.65
     spons
    0.65
    )=(
    0.64
    Act Density 0.343%

    No Known Activations