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

    Neuronpedia

    INDEX
    Explanations

    references to specific file paths or URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to web page indices and popular music genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thirds
    -0.77
     poles
    -0.76
     brisk
    -0.74
     outl
    -0.72
     elev
    -0.71
     liber
    -0.70
     dope
    -0.70
     wolves
    -0.69
     roller
    -0.69
     gru
    -0.68
    POSITIVE LOGITS
    tenance
    1.23
    acters
    0.98
    ularity
    0.95
    theless
    0.94
    ertodd
    0.92
    widget
    0.90
    iscopal
    0.90
    ifix
    0.87
    idy
    0.86
    uyomi
    0.86
    Act Density 0.035%

    No Known Activations