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

    Neuronpedia

    INDEX
    Explanations

    the phrase constructions related to "of" and numbers indicating quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ows
    -0.16
    bero
    -0.15
    ÙİÙĬ
    -0.15
    iment
    -0.14
    ade
    -0.14
    ves
    -0.14
    ements
    -0.14
    опаÑģ
    -0.14
    -foot
    -0.13
    quette
    -0.13
    POSITIVE LOGITS
    ters
    0.18
     Zucker
    0.16
    ulton
    0.16
    urance
    0.15
    /out
    0.15
    atatype
    0.15
    ensive
    0.15
    abox
    0.14
    wards
    0.14
     bounds
    0.14
    Act Density 0.055%

    No Known Activations