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

    Neuronpedia

    INDEX
    Explanations

    references to office settings and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illy
    -0.17
    ucci
    -0.16
    ussen
    -0.16
    otta
    -0.16
    ling
    -0.15
    ming
    -0.15
    PK
    -0.14
     obvious
    -0.14
    ÏĤ
    -0.14
    ara
    -0.14
    POSITIVE LOGITS
    yonel
    0.17
    iw
    0.17
    grown
    0.16
    imd
    0.16
    lique
    0.14
    boy
    0.14
    beam
    0.14
    ório
    0.14
    ANDOM
    0.14
    ponents
    0.14
    Act Density 0.049%

    No Known Activations