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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant or groundbreaking discoveries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "discovery."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.95
    overe
    -0.81
    primary
    -0.72
    erate
    -0.70
    ña
    -0.70
     paced
    -0.69
    attery
    -0.69
    non
    -0.67
    culated
    -0.66
    paying
    -0.66
    POSITIVE LOGITS
    Ô
    0.82
    iveness
    0.78
    使
    0.77
     discovery
    0.77
     Primordial
    0.77
    éļ
    0.74
     Wond
    0.74
    gdala
    0.72
    ãĤ¦ãĤ¹
    0.72
    ãĥķ
    0.71
    Act Density 0.015%

    No Known Activations