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

    Neuronpedia

    INDEX
    Explanations

    punctuation and periods in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chter
    -0.16
    icap
    -0.16
    ispecies
    -0.15
    ’B
    -0.15
    astery
    -0.15
    enal
    -0.14
    .trailing
    -0.14
     invest
    -0.14
    akin
    -0.14
     Hos
    -0.14
    POSITIVE LOGITS
    oya
    0.15
    abr
    0.15
    лÑıн
    0.15
    ÙĬا
    0.15
    olit
    0.15
    orado
    0.15
    omed
    0.14
    hangi
    0.13
    DTD
    0.13
    gra
    0.13
    Act Density 0.003%

    No Known Activations