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

    Neuronpedia

    INDEX
    Explanations

    technical or theoretical concepts mentioned in a document, focusing on phrases related to theories or principles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to theoretical versus practical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illin
    -0.76
    by
    -0.66
    ences
    -0.63
    ollar
    -0.63
    jab
    -0.63
    rients
    -0.61
     ions
    -0.61
    resses
    -0.60
    orate
    -0.60
    in
    -0.59
    POSITIVE LOGITS
     guise
    0.87
    uthor
    0.79
    ividual
    0.67
    é¾įå
    0.63
    wagen
    0.63
     recogn
    0.62
     coer
    0.57
    FTWARE
    0.56
     guiActiveUn
    0.56
    ascus
    0.56
    Act Density 0.045%

    No Known Activations