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

    Neuronpedia

    INDEX
    Explanations

    the word "are" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Église
    -0.58
    dopodob
    -0.56
     fatt
    -0.54
    췄
    -0.54
     Keats
    -0.53
     Lázaro
    -0.53
    PyExc
    -0.53
     frito
    -0.53
     itſelf
    -0.52
    setof
    -0.52
    POSITIVE LOGITS
     are
    2.82
     were
    2.22
     ARE
    2.21
     Are
    2.06
    Are
    1.95
     WERE
    1.88
    are
    1.75
     Were
    1.75
    were
    1.73
    Were
    1.61
    Act Density 0.423%

    No Known Activations