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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news articles or information reports

    oai_token-act-pair · gpt-3.5-turbo

    events related to accidents and their aftermath

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?).
    -0.75
    ?".
    -0.68
    )</
    -0.68
    )!
    -0.67
    !).
    -0.64
    ...)
    -0.61
    âĢ¦)
    -0.61
    !".
    -0.60
     Allaah
    -0.57
     somew
    -0.57
    POSITIVE LOGITS
     initially
    0.68
     Thursday
    0.64
     Wednesday
    0.64
     Sept
    0.64
     earlier
    0.63
     2010
    0.63
     last
    0.61
     Tuesday
    0.61
     eased
    0.60
     Monday
    0.59
    Act Density 1.647%

    No Known Activations