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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating absence or lack of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases negating the presence or occurrence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.66
    Cu
    -0.66
    atu
    -0.65
    Pg
    -0.65
    masters
    -0.62
    alth
    -0.61
     backgrounds
    -0.60
    omsday
    -0.58
    imir
    -0.57
    acci
    -0.57
    POSITIVE LOGITS
     dime
    1.21
     penny
    1.17
     ounce
    1.16
     single
    1.12
     shred
    1.07
     word
    1.04
     inch
    1.01
     lick
    0.99
     trace
    0.97
     cent
    0.93
    Act Density 0.152%

    No Known Activations