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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific people or possibly social media handles

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their associations with specific actions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usc
    -0.74
     augment
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    displayText
    -0.68
    Ctrl
    -0.68
     govern
    -0.68
     subp
    -0.66
    ãĥŁ
    -0.65
     Afric
    -0.63
     ward
    -0.63
    POSITIVE LOGITS
    bies
    0.89
    smoking
    0.81
    ĸļ士
    0.79
     TAMADRA
    0.79
    zees
    0.77
    phies
    0.74
    Reviewer
    0.73
    zee
    0.73
    ansky
    0.73
    pty
    0.73
    Act Density 0.530%

    No Known Activations