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

    Neuronpedia

    INDEX
    Explanations

    connections, relationships, or linkages between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nw
    -0.67
    ���
    -0.65
    heads
    -0.64
    spir
    -0.63
    DX
    -0.63
    microsoft
    -0.62
    HQ
    -0.62
    Deal
    -0.62
    bub
    -0.61
    æµ
    -0.61
    POSITIVE LOGITS
    romeda
    1.06
    hra
    0.96
     thence
    0.93
     consequently
    0.92
    rew
    0.92
    alus
    0.91
    rogens
    0.89
     vice
    0.88
     then
    0.86
     secondly
    0.86
    Act Density 0.181%

    No Known Activations