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

    Neuronpedia

    INDEX
    Explanations

    words that describe the characteristics or attributes of objects or subjects in a detailed manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.59
    неопр
    -0.55
     connues
    -0.53
    CopyWith
    -0.50
     estekak
    -0.48
     Приступљено
    -0.48
     bagay
    -0.47
     connus
    -0.47
    mıştır
    -0.46
     behoort
    -0.46
    POSITIVE LOGITS
     smelling
    0.66
     Мексичка
    0.66
     Sme
    0.59
    <?
    0.58
    OLOGÍA
    0.58
     seventh
    0.57
     MonoBehaviour
    0.56
     heavily
    0.55
     constitution
    0.55
     berper
    0.54
    Act Density 0.456%

    No Known Activations