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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to computer programming

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific non-standard character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inx
    -0.85
    iferation
    -0.76
    oresc
    -0.74
    oids
    -0.72
    azo
    -0.72
    orescence
    -0.71
    arine
    -0.70
    orah
    -0.70
    othal
    -0.67
    ulhu
    -0.67
    POSITIVE LOGITS
     ��������
    0.98
     ����
    0.93
    ternity
    0.72
     Nationwide
    0.72
    bold
    0.68
    ¢
    0.68
    Rah
    0.68
     �
    0.67
    mons
    0.67
    CDC
    0.66
    Act Density 0.010%

    No Known Activations