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

    Neuronpedia

    INDEX
    Explanations

    phone numbers with area codes

    oai_token-act-pair · gpt-3.5-turbo

    structured numerical information, particularly contact numbers and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     twins
    -0.69
     Britons
    -0.61
    warts
    -0.61
    phabet
    -0.60
     draw
    -0.58
     doomed
    -0.58
     psychologists
    -0.57
     tradition
    -0.57
     noses
    -0.57
     Conclusion
    -0.57
    POSITIVE LOGITS
    Fax
    0.75
    aban
    0.74
    -+-+
    0.72
    fleet
    0.68
    fax
    0.68
    enburg
    0.68
     License
    0.67
    resp
    0.67
    forge
    0.67
    robe
    0.66
    Act Density 0.067%

    No Known Activations