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

    Neuronpedia

    INDEX
    Explanations

    measurements related to size and capacity

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities related to energy and physical substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.71
     Cantor
    -0.68
     Daly
    -0.67
     Franch
    -0.66
     Akin
    -0.66
    eer
    -0.64
     Treasurer
    -0.63
    apego
    -0.61
     Palace
    -0.60
     EDITION
    -0.59
    POSITIVE LOGITS
     apiece
    0.91
    imet
    0.91
    renheit
    0.89
     increments
    0.89
    bps
    0.86
     per
    0.82
     hect
    0.81
    ousand
    0.81
    bsp
    0.79
    abyte
    0.79
    Act Density 0.099%

    No Known Activations