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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dates and events mentioned in a specific format ("January 28," etc.), often with additional context provided

    oai_token-act-pair · gpt-3.5-turbo

    sequences of asterisks commonly used for emphasis or placeholders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.85
    liness
    -0.77
    ilia
    -0.72
    iveness
    -0.71
    ugu
    -0.67
    ively
    -0.67
    ilic
    -0.66
    ories
    -0.65
    ijk
    -0.63
     intimid
    -0.61
    POSITIVE LOGITS
    kw
    0.91
    taboola
    0.81
    Madison
    0.81
    orks
    0.77
    quote
    0.77
    Discussion
    0.75
    DER
    0.74
    Edited
    0.72
    THIS
    0.72
    learn
    0.71
    Act Density 0.035%

    No Known Activations