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

    Neuronpedia

    INDEX
    Explanations

    the verb "put" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "put."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lus
    -0.65
     Beginning
    -0.62
     Story
    -0.61
    majority
    -0.61
    reporting
    -0.60
     Sins
    -0.59
     Travels
    -0.59
    scenes
    -0.59
     Specifications
    -0.59
    eworthy
    -0.59
    POSITIVE LOGITS
     put
    2.95
    Put
    1.93
     puts
    1.83
    put
    1.80
     Put
    1.72
     placed
    1.50
     putting
    1.43
     Putting
    1.23
    Putting
    1.22
     set
    1.14
    Act Density 0.043%

    No Known Activations