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

    Neuronpedia

    INDEX
    Explanations

    HTML or programming terms related to styling text

    oai_token-act-pair · gpt-3.5-turbo

    references to text and text-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.81
    CVE
    -0.75
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.74
    pload
    -0.74
    lain
    -0.74
    rolet
    -0.70
    MAL
    -0.70
    negie
    -0.68
    deen
    -0.68
    TAIN
    -0.68
    POSITIVE LOGITS
    ured
    1.26
    uality
    1.06
    area
    0.98
    plain
    0.98
    uring
    0.94
    ual
    0.91
     text
    0.87
    ures
    0.86
     messages
    0.85
    urized
    0.82
    Act Density 0.013%

    No Known Activations