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

    Neuronpedia

    INDEX
    Explanations

    numerical figures or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or counts related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swe
    -0.69
     creature
    -0.66
     bear
    -0.64
     cens
    -0.63
     lifes
    -0.62
     tongues
    -0.62
     axe
    -0.61
     trump
    -0.61
     tram
    -0.60
     unconditional
    -0.60
    POSITIVE LOGITS
    Advertisement
    1.23
    Meanwhile
    1.22
    However
    1.20
    Besides
    1.18
    Also
    1.16
    Similarly
    1.16
    Likewise
    1.15
    Some
    1.14
    Related
    1.14
    Both
    1.14
    Act Density 0.673%

    No Known Activations