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

    Neuronpedia

    INDEX
    Explanations

    information related to medical health conditions and reports

    oai_token-act-pair · gpt-3.5-turbo

    references to negative health conditions or reports of well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     civilisation
    -0.62
     licence
    -0.62
     ®
    -0.60
     patent
    -0.57
     interstellar
    -0.57
     arsen
    -0.56
     Principle
    -0.56
     graphene
    -0.54
     maths
    -0.54
     Nasa
    -0.54
    POSITIVE LOGITS
    comments
    0.74
     complaining
    0.73
    terday
    0.72
    Gov
    0.70
     announcing
    0.68
     noticing
    0.66
     apologizing
    0.66
     blaming
    0.66
     Saying
    0.65
    uesday
    0.64
    Act Density 1.345%

    No Known Activations