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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different entities or objects

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accessed
    -0.71
    frey
    -0.68
     respectively
    -0.68
    illion
    -0.67
    SPONSORED
    -0.66
     furthermore
    -0.65
    meg
    -0.64
    iband
    -0.63
     anew
    -0.63
    isin
    -0.62
    POSITIVE LOGITS
     rest
    1.42
     originals
    1.29
     others
    1.25
     usual
    1.18
     ones
    1.16
     previous
    1.13
     norm
    1.10
     preceding
    1.03
     original
    1.02
     typical
    0.99
    Act Density 0.238%

    No Known Activations