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

    Neuronpedia

    INDEX
    Explanations

    informational phrases that provide insights or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to illuminating or clarifying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teness
    -0.75
    anwhile
    -0.73
     Pav
    -0.70
    trak
    -0.66
    ;;;;;;;;;;;;
    -0.64
    odore
    -0.63
    War
    -0.62
    efe
    -0.61
    ournals
    -0.61
    ierra
    -0.60
    POSITIVE LOGITS
     shed
    1.16
     sheds
    1.04
    ittal
    0.92
    brid
    0.87
     shedding
    0.84
    iencies
    0.78
    yard
    0.77
     Shed
    0.77
    yards
    0.77
     hairs
    0.75
    Act Density 0.007%

    No Known Activations