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

    Neuronpedia

    INDEX
    Explanations

    phrases containing direct speech

    oai_token-act-pair · gpt-3.5-turbo

    instances of speech attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illions
    -0.82
    emetery
    -0.78
    OTAL
    -0.76
    illion
    -0.72
     conflic
    -0.71
    EMBER
    -0.70
    respective
    -0.70
    onut
    -0.70
    ãĥİ
    -0.70
    brance
    -0.70
    POSITIVE LOGITS
     bluntly
    0.79
     sarcast
    0.78
     coy
    0.71
     rhet
    0.70
     Tsarnaev
    0.69
     herself
    0.68
     anecd
    0.65
     adamant
    0.64
     himself
    0.64
     succinct
    0.62
    Act Density 0.280%

    No Known Activations