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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to technology and science

    oai_token-act-pair · gpt-3.5-turbo

    instances of health and safety-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paio
    -0.38
    Offline
    -0.34
    onsense
    -0.34
     rul
    -0.34
    href
    -0.33
    bard
    -0.33
     constitu
    -0.32
    cknow
    -0.32
    journal
    -0.30
    )",
    -0.30
    POSITIVE LOGITS
    cliffe
    0.38
     guiActiveUn
    0.37
    ibly
    0.37
    ELY
    0.36
    tesy
    0.36
    ãĤ©
    0.35
    lihood
    0.34
    æ©
    0.33
    UF
    0.33
    vironment
    0.33
    Act Density 5.347%

    No Known Activations