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

    Neuronpedia

    INDEX
    Explanations

    words related to different types of data or information sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ոյ
    -0.69
    nteral
    -0.68
    magnetism
    -0.68
    addParameter
    -0.67
    ichern
    -0.67
    SpringRunner
    -0.65
     placent
    -0.64
     padi
    -0.62
     AWAY
    -0.62
    mainAxisSize
    -0.61
    POSITIVE LOGITS
     из
    1.36
    Из
    1.23
     aus
    1.05
     Из
    1.05
     ИЗ
    1.00
    из
    0.95
     iz
    0.89
     iš
    0.81
     dintr
    0.81
     uit
    0.80
    Act Density 0.067%

    No Known Activations