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

    Neuronpedia

    INDEX
    Explanations

    words related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Co" and its variations, likely indicating a focus on company names or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.89
     corpus
    -0.69
     RTX
    -0.63
     Halls
    -0.60
     Revel
    -0.59
     preparations
    -0.58
     Marketable
    -0.57
     PEOPLE
    -0.56
     bankruptcy
    -0.56
     differe
    -0.55
    POSITIVE LOGITS
    oley
    1.30
    asters
    1.19
    opers
    1.19
    ombs
    1.14
    lette
    1.13
    aching
    1.13
    pps
    1.12
    venants
    1.11
    efficients
    1.10
    aches
    1.09
    Act Density 0.016%

    No Known Activations