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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technology and product features

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and other forms of brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spir
    -0.76
     impeachment
    -0.73
     ris
    -0.73
     electr
    -0.71
     contend
    -0.70
     spiked
    -0.70
     nuts
    -0.69
     pale
    -0.68
     nitrogen
    -0.68
     tear
    -0.68
    POSITIVE LOGITS
    formerly
    1.34
    ...)
    1.34
    ?)
    1.31
    aka
    1.27
    sic
    1.20
    excluding
    1.19
    including
    1.19
    optional
    1.18
    emphasis
    1.14
    also
    1.14
    Act Density 0.185%

    No Known Activations