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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arto
    -0.17
    alore
    -0.16
     McMaster
    -0.15
    illard
    -0.15
    ELS
    -0.14
    ogne
    -0.14
    igure
    -0.14
    illac
    -0.14
    ç³»
    -0.14
     Hawth
    -0.14
    POSITIVE LOGITS
    axon
    0.17
    agen
    0.17
     Kl
    0.17
     conf
    0.16
    ặng
    0.16
    .ToShort
    0.16
     kl
    0.15
    زا
    0.15
    udget
    0.15
    atch
    0.15
    Act Density 0.007%

    No Known Activations