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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is inspired to work on their game plan

    oai_token-act-pair · gpt-3.5-turbo

    the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ressing
    -0.79
    east
    -0.68
     circumcised
    -0.66
    isters
    -0.66
    uds
    -0.66
    prus
    -0.66
     chambers
    -0.65
    umen
    -0.64
    cheon
    -0.64
    iframe
    -0.63
    POSITIVE LOGITS
     showc
    0.69
    ethy
    0.68
     marqu
    0.67
     @@
    0.66
     categ
    0.66
     fuse
    0.64
     dop
    0.64
     brav
    0.63
    bott
    0.62
     fa
    0.61
    Act Density 0.000%

    No Known Activations