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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tasks or actions being performed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" and "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.78
     Flavoring
    -0.76
     Dur
    -0.70
     Tru
    -0.65
     Dwell
    -0.62
     Vehicles
    -0.60
    osponsors
    -0.59
     Surprise
    -0.59
     Mile
    -0.59
    ãĤ¦ãĤ¹
    -0.59
    POSITIVE LOGITS
     entails
    0.77
     job
    0.75
     unconsciously
    0.75
     thing
    0.74
     anecd
    0.73
     justice
    0.72
    berra
    0.71
     efficiently
    0.70
    pez
    0.70
     emulate
    0.69
    Act Density 0.042%

    No Known Activations