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

    Neuronpedia

    INDEX
    Explanations

    detailed explanations or analyses within text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe various aspects or components of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reperto
    -0.74
     subsequ
    -0.68
     partName
    -0.66
     ende
    -0.64
    aucuses
    -0.64
    nown
    -0.60
    elsius
    -0.60
    irs
    -0.59
    igue
    -0.59
    cms
    -0.59
    POSITIVE LOGITS
     sorts
    1.00
     course
    0.91
    icial
    0.89
    enance
    0.84
    ãĤ¯
    0.82
     ours
    0.75
    course
    0.73
     the
    0.69
     these
    0.68
     Course
    0.63
    Act Density 0.963%

    No Known Activations