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

    Neuronpedia

    INDEX
    Explanations

    captions or headings in articles

    oai_token-act-pair · gpt-3.5-turbo

    text formatting indicators and structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     112
    -0.70
     82
    -0.67
    112
    -0.64
     78
    -0.63
    ERC
    -0.62
     1932
    -0.62
     222
    -0.61
     138
    -0.61
    138
    -0.60
     132
    -0.60
    POSITIVE LOGITS
    5
    1.34
     5
    1.24
    Fif
    0.97
    five
    0.92
    fifth
    0.90
     fifth
    0.90
     525
    0.87
    ķ
    0.85
    505
    0.85
    525
    0.84
    Act Density 0.065%

    No Known Activations