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

    Neuronpedia

    INDEX
    Explanations

    phrases related to embarking on journeys or missions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intentions or goals to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.78
    antry
    -0.62
    iceps
    -0.59
     Corpus
    -0.57
    eyes
    -0.57
    Pin
    -0.57
    raph
    -0.56
    activate
    -0.55
    TX
    -0.55
    ulous
    -0.55
    POSITIVE LOGITS
    posts
    0.85
    fitted
    0.80
    llor
    0.75
    ãģ¦
    0.74
    sonian
    0.73
    stretched
    0.73
    )=(
    0.71
    lessness
    0.69
    rer
    0.68
    lled
    0.68
    Act Density 0.021%

    No Known Activations