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

    Neuronpedia

    INDEX
    Explanations

    years in the 2000s mentioned in references

    oai_token-act-pair · gpt-3.5-turbo

    references to publication years in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imer
    -0.73
    pee
    -0.71
    mir
    -0.70
    pees
    -0.64
    unal
    -0.64
    Bay
    -0.64
    isec
    -0.63
    ype
    -0.63
    ety
    -0.63
    venge
    -0.63
    POSITIVE LOGITS
    å¹
    1.08
     Edition
    0.72
     EDITION
    0.70
    é¾
    0.70
     Diversity
    0.69
     Highlights
    0.69
     doctoral
    0.69
    -)
    0.68
    )—
    0.67
     UX
    0.65
    Act Density 0.067%

    No Known Activations