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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities or numbers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and other related quantifiers or descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atics
    -0.63
    ault
    -0.62
    mart
    -0.62
    qq
    -0.61
    ulated
    -0.60
    bg
    -0.60
    Supported
    -0.60
     Finally
    -0.59
     because
    -0.59
     wisely
    -0.59
    POSITIVE LOGITS
     entire
    1.21
     slightest
    1.16
     entirety
    1.11
     latter
    1.06
     remainder
    1.03
     wearer
    1.03
     same
    1.03
     widest
    1.02
     longest
    1.01
     quickest
    0.99
    Act Density 0.245%

    No Known Activations