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

    Neuronpedia

    INDEX
    Explanations

    the word "pat" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of giving praise or commendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Measure
    -0.65
    é¾
    -0.65
    é¾įå
    -0.62
     Incarn
    -0.61
     Galile
    -0.61
    displayText
    -0.60
     Controlled
    -0.60
    Shape
    -0.60
    omething
    -0.59
    STD
    -0.59
    POSITIVE LOGITS
    reon
    1.42
    hetically
    1.34
    ricia
    1.32
    terson
    1.26
    riots
    1.21
    riot
    1.20
    rolled
    1.15
    tered
    1.15
    ric
    1.15
    ting
    1.14
    Act Density 0.026%

    No Known Activations