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

    Neuronpedia

    INDEX
    Explanations

    words related to justification or proving innocence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vindication and exoneration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pee
    -0.83
    OPLE
    -0.73
    atomic
    -0.71
     Reed
    -0.66
     dstg
    -0.65
     nap
    -0.64
    BOOK
    -0.63
    pmwiki
    -0.62
     Towns
    -0.62
    ffiti
    -0.62
    POSITIVE LOGITS
     vind
    1.21
    ictive
    1.00
    romeda
    0.98
    ication
    0.98
    icated
    0.97
    ortun
    0.93
    ict
    0.88
    icates
    0.86
    lehem
    0.83
    ications
    0.81
    Act Density 0.013%

    No Known Activations