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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical conditions and scientific research

    oai_token-act-pair · gpt-3.5-turbo

    negative physiological indicators or metrics related to health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guru
    -0.72
     Patriot
    -0.72
     Wiz
    -0.72
     perks
    -0.71
     nods
    -0.71
     Mama
    -0.69
     RBI
    -0.68
     Bes
    -0.68
     brunch
    -0.67
     Breed
    -0.67
    POSITIVE LOGITS
    derived
    1.22
    treated
    1.22
    negative
    1.21
    mediated
    1.18
    positive
    1.17
    response
    1.15
    biased
    1.15
    induced
    1.14
    containing
    1.13
    density
    1.12
    Act Density 0.160%

    No Known Activations