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

    Neuronpedia

    INDEX
    Explanations

    keywords related to health and education policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agnost
    -0.18
     COPYRIGHT
    -0.15
     probes
    -0.14
    PEG
    -0.14
     vat
    -0.14
    ð
    -0.14
    æ¾
    -0.13
    iform
    -0.13
    Throw
    -0.13
    loi
    -0.13
    POSITIVE LOGITS
     Healthy
    0.26
     unhealthy
    0.24
     healthy
    0.24
     tobacco
    0.23
     healthier
    0.23
     upstream
    0.20
    healthy
    0.20
     determin
    0.20
     promot
    0.19
     Tobacco
    0.19
    Act Density 0.018%

    No Known Activations