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

    Neuronpedia

    INDEX
    Explanations

    mentions of reports

    oai_token-act-pair · gpt-3.5-turbo

    references to reports and memorandums related to regulatory or investigative findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.68
    ¯
    -0.66
    ãĥİ
    -0.63
    âĹ¼
    -0.61
    vp
    -0.60
    ventus
    -0.59
    Offline
    -0.57
     invincible
    -0.56
    instead
    -0.55
    wcs
    -0.55
    POSITIVE LOGITS
     concludes
    1.17
     recommends
    1.09
     notes
    1.02
     emphasizes
    1.00
     cites
    0.98
     argues
    0.96
     acknowledges
    0.96
     summarizes
    0.95
     suggests
    0.94
     proposes
    0.93
    Act Density 0.428%

    No Known Activations