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

    Neuronpedia

    INDEX
    Explanations

    instances of comparison with a strong degree of certainty

    oai_token-act-pair · gpt-3.5-turbo

    the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olla
    -0.49
    gery
    -0.49
    Reply
    -0.46
    patient
    -0.46
    effect
    -0.45
    humane
    -0.44
    ļéĨĴ
    -0.44
    oleon
    -0.43
    iak
    -0.43
     halting
    -0.43
    POSITIVE LOGITS
     are
    2.37
     aren
    1.98
     were
    1.76
     ARE
    1.75
    're
    1.61
     weren
    1.58
    are
    1.51
    Are
    1.40
     Are
    1.39
    were
    1.32
    Act Density 0.217%

    No Known Activations