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

    Neuronpedia

    INDEX
    Explanations

    words related to characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various sectors, demographics, and health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.79
     Wife
    -0.74
     Empty
    -0.71
    bye
    -0.70
    ynthesis
    -0.69
     Goodbye
    -0.68
     Apprentice
    -0.67
    ructose
    -0.66
    erey
    -0.65
     Piano
    -0.65
    POSITIVE LOGITS
     categories
    1.59
     formats
    1.52
     disciplines
    1.51
     contexts
    1.49
     types
    1.46
     configurations
    1.41
     sectors
    1.38
     modes
    1.37
     scenarios
    1.36
     entities
    1.36
    Act Density 0.360%

    No Known Activations