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

    Neuronpedia

    INDEX
    Explanations

    text related to legal rights and copyright

    oai_token-act-pair · gpt-3.5-turbo

    references to copyright and ownership issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     QC
    -0.75
    cephal
    -0.74
     tiss
    -0.72
     Berks
    -0.70
     Croatia
    -0.69
    zees
    -0.68
     Kissinger
    -0.67
    ccording
    -0.67
    00007
    -0.67
    PDATE
    -0.67
    POSITIVE LOGITS
    alph
    0.70
    andy
    0.66
     amy
    0.65
    area
    0.65
    ellow
    0.63
    arl
    0.63
    arent
    0.62
    ual
    0.61
    uala
    0.60
    anny
    0.59
    Act Density 0.211%

    No Known Activations