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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raÄį
    -0.15
    actionDate
    -0.14
    strup
    -0.14
    bjerg
    -0.14
    UTTON
    -0.14
    jets
    -0.14
    icao
    -0.14
    ayet
    -0.14
    arta
    -0.14
    олом
    -0.13
    POSITIVE LOGITS
    ideos
    0.16
    hta
    0.14
    agma
    0.14
    ori
    0.14
    abor
    0.14
    edis
    0.14
    elder
    0.14
     vir
    0.14
    archy
    0.13
    umo
    0.13
    Act Density 0.056%

    No Known Activations