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

    Neuronpedia

    INDEX
    Explanations

    words related to comparison or association

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Whe
    -0.68
    oria
    -0.68
    forts
    -0.67
    Published
    -0.65
    edom
    -0.64
    mint
    -0.63
    !!!!!!!!
    -0.63
    CCC
    -0.63
    whe
    -0.62
    ogram
    -0.62
    POSITIVE LOGITS
    lihood
    1.02
    liest
    0.70
     previous
    0.70
     many
    0.68
     predecessors
    0.68
     Occupations
    0.66
    lier
    0.65
     example
    0.65
     any
    0.64
     regards
    0.63
    Act Density 0.049%

    No Known Activations