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

    Neuronpedia

    INDEX
    Explanations

    references to food and drug-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocht
    -0.17
     Malone
    -0.17
    ìŀħ
    -0.15
     Woodward
    -0.15
    igon
    -0.15
    ider
    -0.15
    .infinity
    -0.15
     Kramer
    -0.14
    ille
    -0.14
     Lomb
    -0.14
    POSITIVE LOGITS
     safety
    0.24
     Safety
    0.21
    borne
    0.20
     security
    0.19
     insecure
    0.18
    chain
    0.18
     Chain
    0.17
    service
    0.17
    rien
    0.17
    Safety
    0.17
    Act Density 0.021%

    No Known Activations