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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking someone to a hospital for treatment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "taken" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lich
    -0.76
    ulo
    -0.75
    eers
    -0.69
    tor
    -0.64
    ler
    -0.64
    cape
    -0.64
    psey
    -0.62
     includ
    -0.61
    lers
    -0.61
    tions
    -0.60
    POSITIVE LOGITS
     aback
    1.32
    aways
    1.05
     advantage
    0.96
     care
    0.87
     heed
    0.86
    ãĤ¤ãĥĪ
    0.84
    OVER
    0.84
     cogn
    0.83
    ardless
    0.78
     away
    0.75
    Act Density 0.037%

    No Known Activations