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

    Neuronpedia

    INDEX
    Explanations

    activities related to reporting and discussion in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .partial
    -0.16
    onds
    -0.14
    FW
    -0.14
    ÏĨι
    -0.14
    atrix
    -0.14
     Hund
    -0.14
    DK
    -0.14
    iom
    -0.14
    лади
    -0.14
    iciar
    -0.14
    POSITIVE LOGITS
    ToObject
    0.17
     assort
    0.16
    го
    0.15
    imson
    0.15
    ette
    0.14
    auer
    0.14
     Pok
    0.14
     Kota
    0.14
     Cha
    0.13
    etten
    0.13
    Act Density 0.025%

    No Known Activations