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

    Neuronpedia

    INDEX
    Explanations

    words related to properties, particularly focusing on "prop" as a stem word

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of props, specifically in relation to production and the film industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.77
    soever
    -0.66
    lihood
    -0.66
     Intent
    -0.63
     Forever
    -0.63
     Cardinal
    -0.62
     Clover
    -0.61
    ways
    -0.61
     Leaf
    -0.60
     Waters
    -0.59
    POSITIVE LOGITS
    ulsive
    1.30
    itious
    1.23
    ylene
    0.99
    etry
    0.98
    uls
    0.95
    oster
    0.88
    idium
    0.87
    els
    0.87
    hetical
    0.85
    ounded
    0.85
    Act Density 0.028%

    No Known Activations