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

    Neuronpedia

    INDEX
    Explanations

    information related to a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ����
    -0.76
    DN
    -0.73
    OTA
    -0.71
    âī
    -0.69
    —-
    -0.69
    Ò
    -0.68
    ��
    -0.68
    xxx
    -0.67
    PLA
    -0.67
    angles
    -0.67
    POSITIVE LOGITS
     biggest
    1.03
     detractors
    1.02
     successor
    0.98
     newfound
    0.98
     inability
    0.97
     youngest
    0.97
    itage
    0.97
     Majesty
    0.96
     eldest
    0.94
     favourite
    0.93
    Act Density 0.132%

    No Known Activations