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

    Neuronpedia

    INDEX
    Explanations

    the word "this" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to actions or processes being performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.72
     Flavoring
    -0.66
     Dur
    -0.65
    ãĤ¦ãĤ¹
    -0.64
     Surprise
    -0.62
    ontent
    -0.62
     Protector
    -0.62
     Claims
    -0.60
    aws
    -0.60
    usha
    -0.59
    POSITIVE LOGITS
     justice
    0.81
     thing
    0.79
     anecd
    0.78
    tical
    0.76
     differently
    0.75
     legally
    0.74
     cheaply
    0.72
     deed
    0.71
    pez
    0.71
     destro
    0.70
    Act Density 0.044%

    No Known Activations