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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical treatments and their effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health and treatment efficacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "/>
    -0.65
    ).[
    -0.64
     Kinnikuman
    -0.59
    Released
    -0.56
    Downloadha
    -0.55
    tumblr
    -0.55
     fetish
    -0.52
     paraph
    -0.52
    hid
    -0.51
     ital
    -0.51
    POSITIVE LOGITS
     someday
    0.66
     tomorrow
    0.63
     2019
    0.62
     ObamaCare
    0.62
    izons
    0.61
    usterity
    0.61
    apses
    0.59
     2020
    0.57
    ratom
    0.56
    carbon
    0.56
    Act Density 1.817%

    No Known Activations