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

    Neuronpedia

    INDEX
    Explanations

    trigraphs that include special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters and specific symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enthal
    -0.82
    wcs
    -0.71
     detail
    -0.66
    anmar
    -0.65
    ockets
    -0.65
    enstein
    -0.64
     CentOS
    -0.63
     slicing
    -0.62
     Mechdragon
    -0.62
    ENN
    -0.62
    POSITIVE LOGITS
    ËĪ
    1.01
    âĢ²
    0.95
    raid
    0.78
    ready
    0.76
    ¼
    0.75
    entimes
    0.73
    ãĥ¢
    0.71
    tis
    0.71
    Ê
    0.71
    É
    0.71
    Act Density 0.003%

    No Known Activations