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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    they
    -0.56
     között
    -0.56
    adays
    -0.56
     οποία
    -0.55
     برانيه
    -0.55
    queryInterface
    -0.55
     setuptools
    -0.52
    windowFixed
    -0.50
     يتيمه
    -0.49
    They
    -0.48
    POSITIVE LOGITS
     the
    1.45
     those
    1.15
     our
    1.02
     these
    1.00
     their
    0.98
     your
    0.93
     another
    0.90
     its
    0.88
     any
    0.86
     them
    0.83
    Act Density 0.329%

    No Known Activations