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

    Neuronpedia

    INDEX
    Explanations

    the word "stretch" with different levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stretch" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nect
    -0.95
    eers
    -0.87
    eer
    -0.84
    */(
    -0.81
    ellery
    -0.80
    alty
    -0.76
    vernment
    -0.75
    eering
    -0.74
    ufact
    -0.73
    ienced
    -0.72
    POSITIVE LOGITS
     stretched
    0.86
    opian
    0.78
     Armstrong
    0.75
     stretches
    0.75
     lim
    0.73
     stretch
    0.72
     stretching
    0.67
     denim
    0.64
     beyond
    0.63
     Foods
    0.62
    Act Density 0.030%

    No Known Activations