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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events or personal experiences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    vernment
    -0.69
    aster
    -0.67
     neighb
    -0.65
    nce
    -0.64
    phis
    -0.63
    eries
    -0.61
    henko
    -0.61
     gren
    -0.61
     prosec
    -0.60
     headphone
    -0.60
    POSITIVE LOGITS
    âĢİ
    0.66
    iage
    0.66
    ULTS
    0.61
    ISION
    0.58
     Hungry
    0.58
     ripe
    0.58
    zona
    0.57
    vale
    0.57
    ãĤ¤ãĥĪ
    0.55
    ynthesis
    0.54
    Act Density 6.098%

    No Known Activations