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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     veterinarian
    -0.51
     preferably
    -0.50
     tragically
    -0.50
     notoriously
    -0.49
    Fortunately
    -0.49
     ensu
    -0.48
    Luckily
    -0.48
    arthy
    -0.48
     happiest
    -0.48
     rightfully
    -0.46
    POSITIVE LOGITS
    arthed
    0.66
    MSN
    0.57
    DCS
    0.55
    ebus
    0.55
    romeda
    0.54
    EStream
    0.52
    tions
    0.51
     ----------------------------------------------------------------
    0.51
    results
    0.51
    }.
    0.51
    Act Density 1.514%

    No Known Activations