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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gezocht
    -0.15
    ÄįÃŃ
    -0.15
     lấy
    -0.15
     táºŃn
    -0.15
    aled
    -0.14
    ToOne
    -0.14
    eket
    -0.14
    .builders
    -0.14
    ToDevice
    -0.14
     nond
    -0.13
    POSITIVE LOGITS
     meaning
    0.16
     meaningful
    0.15
    ocup
    0.15
    idlo
    0.15
    ivet
    0.14
    bish
    0.14
    çĶļ
    0.14
    ivre
    0.14
    enou
    0.14
    zas
    0.13
    Act Density 0.008%

    No Known Activations