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

    Neuronpedia

    INDEX
    Explanations

    information related to personal biographies or life events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongyang
    -0.82
    ramid
    -0.79
    ength
    -0.71
     goodness
    -0.67
    oning
    -0.64
    erity
    -0.63
    iology
    -0.63
    idth
    -0.62
    inately
    -0.62
    inarily
    -0.61
    POSITIVE LOGITS
     acquainted
    1.10
     accustomed
    1.09
     entangled
    1.03
     embroiled
    1.03
     extinct
    1.01
     aware
    1.00
     addicted
    0.91
     obsessed
    0.90
     disillusion
    0.87
     eligible
    0.87
    Act Density 0.055%

    No Known Activations